Filter Events:

SUN 5 DEC

4 p.m.

MON 6 DEC

1 a.m.

Tutorial:

Pay Attention to What You Need: Do Structural Priors Still Matter in the Age of Billion Parameter Models?

(ends 4:30 AM)

Tutorial:

Real-Time Optimization for Fast and Complex Control Systems

(ends 4:50 AM)

5 a.m.

Tutorial:

Machine Learning With Quantum Computers

(ends 9:00 AM)

Tutorial:

A Journey Through the Opportunity of Low Resourced Natural Language Processing — An African Lens

(ends 8:00 AM)

9 a.m.

Tutorial:

The Art of Gaussian Processes: Classical and Contemporary

(ends 1:00 PM)

Tutorial:

ML for Physics and Physics for ML

(ends 1:00 PM)

1 p.m.

Tutorial:

Beyond Fairness in Machine Learning

(ends 5:00 PM)

Tutorial:

Machine Learning and Statistics for Climate Science

(ends 5:00 PM)

5 p.m.

Tutorial:

Self-Supervised Learning: Self-Prediction and Contrastive Learning

(ends 7:21 PM)

Tutorial:

Message Passing In Machine Learning

(ends 9:00 PM)

9 p.m.

Affinity Poster Session:

Joint Affinity Poster Session

(ends 11:00 PM)

11 p.m.

Panel:

The Consequences of Massive Scaling in Machine Learning

(ends 12:00 AM)

TUE 7 DEC

midnight

Datasets and Benchmarks:

Dataset and Benchmark Track 1

(ends 2:00 AM)

Oral Session 1: Deep Learning [12:00-1:00]

Oral s 12:00-12:15

[12:00] MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers

Q&A s 12:15-12:20

[12:15] Q&A

Oral s 12:20-12:35

[12:20] Learning to Draw: Emergent Communication through Sketching

Q&A s 12:35-12:40

[12:35] Q&A

Oral s 12:40-12:55

[12:40] Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons

Q&A s 12:55-1:00

[12:55] Q&A

(ends 1:00 AM)

Oral Session 1: Deep Learning Theory and Causality [12:00-1:00]

Oral s 12:00-12:15

[12:00] Framing RNN as a kernel method: A neural ODE approach

Q&A s 12:15-12:20

[12:15] Q&A

Oral s 12:20-12:35

[12:20] A Universal Law of Robustness via Isoperimetry

Q&A s 12:35-12:40

[12:35] Q&A

Oral s 12:40-12:55

[12:40] Causal Identification with Matrix Equations

Q&A s 12:55-1:00

[12:55] Q&A

(ends 1:00 AM)

Oral Session 1: Generative Modeling [12:00-1:00]

Oral s 12:00-12:15

[12:00] E(n) Equivariant Normalizing Flows

Q&A s 12:15-12:20

[12:15] Q&A

Oral s 12:20-12:35

[12:20] Online Variational Filtering and Parameter Learning

Q&A s 12:35-12:40

[12:35] Q&A

Oral s 12:40-12:55

[12:40] Alias-Free Generative Adversarial Networks

Q&A s 12:55-1:00

[12:55] Q&A

(ends 1:00 AM)

Oral Session 1: Theory [12:00-1:00]

Oral s 12:00-12:15

[12:00] Separation Results between Fixed-Kernel and Feature-Learning Probability Metrics

Q&A s 12:15-12:20

[12:15] Q&A

Oral s 12:20-12:35

[12:20] Near-Optimal No-Regret Learning in General Games

Q&A s 12:35-12:40

[12:35] Q&A

Oral s 12:40-12:55

[12:40] Lower Bounds on Metropolized Sampling Methods for Well-Conditioned Distributions

Q&A s 12:55-1:00

[12:55] Q&A

(ends 1:00 AM)

1 a.m.

Oral Session 2: Deep Learning [1:00-2:00]

Oral s 1:00-1:15

[1:00] Attention over Learned Object Embeddings Enables Complex Visual Reasoning

Q&A s 1:15-1:20

[1:15] Q&A

Oral s 1:20-1:35

[1:20] Learning Frequency Domain Approximation for Binary Neural Networks

Q&A s 1:35-1:40

[1:35] Q&A

Oral s 1:40-1:55

[1:40] Learning Debiased Representation via Disentangled Feature Augmentation

Q&A s 1:55-2:00

[1:55] Q&A

(ends 2:00 AM)

Oral Session 2: Optimization [1:00-2:00]

Oral s 1:00-1:15

[1:00] EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback

Q&A s 1:15-1:20

[1:15] Q&A

Oral s 1:20-1:35

[1:20] Differentiable Quality Diversity

Q&A s 1:35-1:40

[1:35] Q&A

Oral s 1:40-1:55

[1:40] Hessian Eigenspectra of More Realistic Nonlinear Models

Q&A s 1:55-2:00

[1:55] Q&A

(ends 2:00 AM)

Oral Session 2: Reinforcement Learning [1:00-2:00]

Oral s 1:00-1:15

[1:00] An Exponential Lower Bound for Linearly Realizable MDP with Constant Suboptimality Gap

Q&A s 1:15-1:20

[1:15] Q&A

Oral s 1:20-1:35

[1:20] On the Expressivity of Markov Reward

Q&A s 1:35-1:40

[1:35] Q&A

Oral s 1:40-1:55

[1:40] The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition

Q&A s 1:55-2:00

[1:55] Q&A

(ends 2:00 AM)

Oral Session 2: Theory [1:00-2:00]

Oral s 1:00-1:15

[1:00] Data driven semi-supervised learning

Q&A s 1:15-1:20

[1:15] Q&A

Oral s 1:20-1:35

[1:20] Stability and Deviation Optimal Risk Bounds with Convergence Rate $O(1/n)$

Q&A s 1:35-1:40

[1:35] Q&A

Oral s 1:40-1:55

[1:40] The Complexity of Bayesian Network Learning: Revisiting the Superstructure

Q&A s 1:55-2:00

[1:55] Q&A

(ends 2:00 AM)

5 a.m.

Affinity Workshop:

Queer in AI Workshop 1

(ends 7:00 AM)

6:02 a.m.

Affinity Workshop:

New in ML 1

(ends 6:50 AM)

7 a.m.

Invited Talk:

How Duolingo Uses AI to Assess, Engage and Teach Better

Luis von Ahn

(ends 8:30 AM)

8:30 a.m.

Demonstration:

Demonstrations 1

(ends 9:35 AM)

Datasets and Benchmarks:

Dataset and Benchmark Poster Session 1

(ends 10:00 AM)

Poster Session 1 [8:30-10:00]

Non-local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation

NeurWIN: Neural Whittle Index Network For Restless Bandits Via Deep RL

Temporally Abstract Partial Models

Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations

Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization

Cardinality-Regularized Hawkes-Granger Model

Confident Anchor-Induced Multi-Source Free Domain Adaptation

SyncTwin: Treatment Effect Estimation with Longitudinal Outcomes

Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization

Improving Robustness using Generated Data

$\texttt{LeadCache}$: Regret-Optimal Caching in Networks

Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery

Factored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPs

DOCTOR: A Simple Method for Detecting Misclassification Errors

On UMAP's True Loss Function

Computer-Aided Design as Language

On Success and Simplicity: A Second Look at Transferable Targeted Attacks

Conditioning Sparse Variational Gaussian Processes for Online Decision-making

Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation

Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose

Random Noise Defense Against Query-Based Black-Box Attacks

Challenges and Opportunities in High Dimensional Variational Inference

Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning

Escape saddle points by a simple gradient-descent based algorithm

A Closer Look at the Worst-case Behavior of Multi-armed Bandit Algorithms

Locality defeats the curse of dimensionality in convolutional teacher-student scenarios

On Provable Benefits of Depth in Training Graph Convolutional Networks

The Many Faces of Adversarial Risk

Gradient-based Hyperparameter Optimization Over Long Horizons

Validation Free and Replication Robust Volume-based Data Valuation

Linear-Time Probabilistic Solution of Boundary Value Problems

Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks

A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose

The Inductive Bias of Quantum Kernels

Adversarial Robustness without Adversarial Training: A Teacher-Guided Curriculum Learning Approach

Statistical Undecidability in Linear, Non-Gaussian Causal Models in the Presence of Latent Confounders

A novel notion of barycenter for probability distributions based on optimal weak mass transport

Implicit Semantic Response Alignment for Partial Domain Adaptation

Robust and Fully-Dynamic Coreset for Continuous-and-Bounded Learning (With Outliers) Problems

Improving Calibration through the Relationship with Adversarial Robustness

Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples

H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion

Large-Scale Wasserstein Gradient Flows

The decomposition of the higher-order homology embedding constructed from the $k$-Laplacian

Introspective Distillation for Robust Question Answering

A unified framework for bandit multiple testing

Proxy-Normalizing Activations to Match Batch Normalization while Removing Batch Dependence

Dynamic Bottleneck for Robust Self-Supervised Exploration

Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning

Partition and Code: learning how to compress graphs

An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence

Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time

Bayesian Optimization with High-Dimensional Outputs

Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks

Compressive Visual Representations

Multi-Armed Bandits with Bounded Arm-Memory: Near-Optimal Guarantees for Best-Arm Identification and Regret Minimization

Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations

Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints

Human-Adversarial Visual Question Answering

Skipping the Frame-Level: Event-Based Piano Transcription With Neural Semi-CRFs

Dueling Bandits with Team Comparisons

SILG: The Multi-domain Symbolic Interactive Language Grounding Benchmark

EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization

NORESQA: A Framework for Speech Quality Assessment using Non-Matching References

Recurrent Submodular Welfare and Matroid Blocking Semi-Bandits

Estimating Multi-cause Treatment Effects via Single-cause Perturbation

An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints

Residual2Vec: Debiasing graph embedding with random graphs

Memory Efficient Meta-Learning with Large Images

Active Offline Policy Selection

Dynamics-regulated kinematic policy for egocentric pose estimation

Graph Neural Networks with Local Graph Parameters

Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature

The effectiveness of feature attribution methods and its correlation with automatic evaluation scores

Automated Discovery of Adaptive Attacks on Adversarial Defenses

Interpretable agent communication from scratch (with a generic visual processor emerging on the side)

MAU: A Motion-Aware Unit for Video Prediction and Beyond

BARTScore: Evaluating Generated Text as Text Generation

Unsupervised Part Discovery from Contrastive Reconstruction

End-to-end Multi-modal Video Temporal Grounding

A Universal Law of Robustness via Isoperimetry

Deep Reinforcement Learning at the Edge of the Statistical Precipice

Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation

NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild

Learning One Representation to Optimize All Rewards

Matrix factorisation and the interpretation of geodesic distance

Counterfactual Explanations Can Be Manipulated

Backward-Compatible Prediction Updates: A Probabilistic Approach

ReAct: Out-of-distribution Detection With Rectified Activations

Fast Training of Neural Lumigraph Representations using Meta Learning

Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems

Approximating the Permanent with Deep Rejection Sampling

Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods

Meta-Learning Reliable Priors in the Function Space

Predicting What You Already Know Helps: Provable Self-Supervised Learning

Scalable Inference in SDEs by Direct Matching of the Fokker–Planck–Kolmogorov Equation

Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound

Numerical influence of ReLU’(0) on backpropagation

Class-agnostic Reconstruction of Dynamic Objects from Videos

Unique sparse decomposition of low rank matrices

Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness

A Winning Hand: Compressing Deep Networks Can Improve Out-of-Distribution Robustness

Mirror Langevin Monte Carlo: the Case Under Isoperimetry

Arbitrary Conditional Distributions with Energy

Self-Consistent Models and Values

Iterative Connecting Probability Estimation for Networks

Learning to Adapt via Latent Domains for Adaptive Semantic Segmentation

Shapeshifter: a Parameter-efficient Transformer using Factorized Reshaped Matrices

Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization

Scalable Intervention Target Estimation in Linear Models

Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation

Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence

You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership

Wisdom of the Crowd Voting: Truthful Aggregation of Voter Information and Preferences

Online Multi-Armed Bandits with Adaptive Inference

Discrete-Valued Neural Communication

Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability

Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement

On Calibration and Out-of-Domain Generalization

Reinforcement Learning in Reward-Mixing MDPs

Explaining Hyperparameter Optimization via Partial Dependence Plots

Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time

Self-Interpretable Model with Transformation Equivariant Interpretation

Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation

ReSSL: Relational Self-Supervised Learning with Weak Augmentation

Test-Time Personalization with a Transformer for Human Pose Estimation

Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models

Weisfeiler and Lehman Go Cellular: CW Networks

Hybrid Regret Bounds for Combinatorial Semi-Bandits and Adversarial Linear Bandits

On Component Interactions in Two-Stage Recommender Systems

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

Misspecified Gaussian Process Bandit Optimization

On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning

Can Information Flows Suggest Targets for Interventions in Neural Circuits?

Dangers of Bayesian Model Averaging under Covariate Shift

Learning Equilibria in Matching Markets from Bandit Feedback

Pooling by Sliced-Wasserstein Embedding

BayesIMP: Uncertainty Quantification for Causal Data Fusion

Neural Auto-Curricula in Two-Player Zero-Sum Games

From global to local MDI variable importances for random forests and when they are Shapley values

Adversarial Robustness of Streaming Algorithms through Importance Sampling

Tractable Regularization of Probabilistic Circuits

Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data

Removing Inter-Experimental Variability from Functional Data in Systems Neuroscience

A No-go Theorem for Robust Acceleration in the Hyperbolic Plane

Rebounding Bandits for Modeling Satiation Effects

Towards Instance-Optimal Offline Reinforcement Learning with Pessimism

Environment Generation for Zero-Shot Compositional Reinforcement Learning

A Critical Look at the Consistency of Causal Estimation with Deep Latent Variable Models

Efficient Bayesian network structure learning via local Markov boundary search

Recursive Bayesian Networks: Generalising and Unifying Probabilistic Context-Free Grammars and Dynamic Bayesian Networks

Instance-dependent Label-noise Learning under a Structural Causal Model

Automatic Unsupervised Outlier Model Selection

Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training

Volume Rendering of Neural Implicit Surfaces

MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers

Medical Dead-ends and Learning to Identify High-Risk States and Treatments

Overcoming the Convex Barrier for Simplex Inputs

Coupled Segmentation and Edge Learning via Dynamic Graph Propagation

Offline RL Without Off-Policy Evaluation

Continuous vs. Discrete Optimization of Deep Neural Networks

CrypTen: Secure Multi-Party Computation Meets Machine Learning

SketchGen: Generating Constrained CAD Sketches

Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems

Analysis of one-hidden-layer neural networks via the resolvent method

Grounding Spatio-Temporal Language with Transformers

Domain Invariant Representation Learning with Domain Density Transformations

Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation

Equilibrium and non-Equilibrium regimes in the learning of Restricted Boltzmann Machines

Accurate Point Cloud Registration with Robust Optimal Transport

Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks

MarioNette: Self-Supervised Sprite Learning

Center Smoothing: Certified Robustness for Networks with Structured Outputs

Scalable Thompson Sampling using Sparse Gaussian Process Models

Shape Registration in the Time of Transformers

Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data

Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets

Hyperbolic Procrustes Analysis Using Riemannian Geometry

Bubblewrap: Online tiling and real-time flow prediction on neural manifolds

The Semi-Random Satisfaction of Voting Axioms

A first-order primal-dual method with adaptivity to local smoothness

Adversarial Robustness with Semi-Infinite Constrained Learning

Collaborative Uncertainty in Multi-Agent Trajectory Forecasting

Scaling Gaussian Processes with Derivative Information Using Variational Inference

Cardinality constrained submodular maximization for random streams

A variational approximate posterior for the deep Wishart process

Neural Pseudo-Label Optimism for the Bank Loan Problem

Multi-modal Dependency Tree for Video Captioning

Teachable Reinforcement Learning via Advice Distillation

On the Universality of Graph Neural Networks on Large Random Graphs

Adversarial Attacks on Graph Classifiers via Bayesian Optimisation

Do Wider Neural Networks Really Help Adversarial Robustness?

BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery

Sharp Impossibility Results for Hyper-graph Testing

Indexed Minimum Empirical Divergence for Unimodal Bandits

Regret Bounds for Gaussian-Process Optimization in Large Domains

Directed Spectrum Measures Improve Latent Network Models Of Neural Populations

Statistical Inference with M-Estimators on Adaptively Collected Data

One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval

Near-Optimal Offline Reinforcement Learning via Double Variance Reduction

Cortico-cerebellar networks as decoupling neural interfaces

One More Step Towards Reality: Cooperative Bandits with Imperfect Communication

Neural Ensemble Search for Uncertainty Estimation and Dataset Shift

Finding Bipartite Components in Hypergraphs

Relational Self-Attention: What's Missing in Attention for Video Understanding

Towards Enabling Meta-Learning from Target Models

An Exact Characterization of the Generalization Error for the Gibbs Algorithm

Panoptic 3D Scene Reconstruction From a Single RGB Image

Measuring Generalization with Optimal Transport

On the Suboptimality of Thompson Sampling in High Dimensions

Implicit SVD for Graph Representation Learning

Offline Model-based Adaptable Policy Learning

Multilingual Pre-training with Universal Dependency Learning

AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks

Scaling Vision with Sparse Mixture of Experts

Synthetic Design: An Optimization Approach to Experimental Design with Synthetic Controls

Ranking Policy Decisions

Searching the Search Space of Vision Transformer

Relative stability toward diffeomorphisms indicates performance in deep nets

The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxation

Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Making by Reinforcement Learning

Cooperative Stochastic Bandits with Asynchronous Agents and Constrained Feedback

Refining Language Models with Compositional Explanations

Consistent Non-Parametric Methods for Maximizing Robustness

An Image is Worth More Than a Thousand Words: Towards Disentanglement in The Wild

Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models

Inverse Optimal Control Adapted to the Noise Characteristics of the Human Sensorimotor System

Deep Neural Networks as Point Estimates for Deep Gaussian Processes

3DP3: 3D Scene Perception via Probabilistic Programming

A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks

Calibration and Consistency of Adversarial Surrogate Losses

Can fMRI reveal the representation of syntactic structure in the brain?

A Kernel-based Test of Independence for Cluster-correlated Data

Efficient methods for Gaussian Markov random fields under sparse linear constraints

Neural Hybrid Automata: Learning Dynamics With Multiple Modes and Stochastic Transitions

Credit Assignment Through Broadcasting a Global Error Vector

An Online Method for A Class of Distributionally Robust Optimization with Non-convex Objectives

Recursive Causal Structure Learning in the Presence of Latent Variables and Selection Bias

Spectral embedding for dynamic networks with stability guarantees

Distributed Zero-Order Optimization under Adversarial Noise

Non-Gaussian Gaussian Processes for Few-Shot Regression

Online learning in MDPs with linear function approximation and bandit feedback.

Kernel Identification Through Transformers

Parallelizing Thompson Sampling

The Causal-Neural Connection: Expressiveness, Learnability, and Inference

A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks

Deep Learning Through the Lens of Example Difficulty

R-Drop: Regularized Dropout for Neural Networks

Bootstrap Your Object Detector via Mixed Training

One Explanation is Not Enough: Structured Attention Graphs for Image Classification

Submodular + Concave

Pure Exploration in Kernel and Neural Bandits

Impression learning: Online representation learning with synaptic plasticity

Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation

Detecting Moments and Highlights in Videos via Natural Language Queries

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

Residual Relaxation for Multi-view Representation Learning

Do Vision Transformers See Like Convolutional Neural Networks?

Object-aware Contrastive Learning for Debiased Scene Representation

Answering Complex Causal Queries With the Maximum Causal Set Effect

Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?

Collaborative Causal Discovery with Atomic Interventions

Score-based Generative Neural Networks for Large-Scale Optimal Transport

Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks

CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator

Stochastic Solutions for Linear Inverse Problems using the Prior Implicit in a Denoiser

Structured Reordering for Modeling Latent Alignments in Sequence Transduction

A universal probabilistic spike count model reveals ongoing modulation of neural variability

Reverse-Complement Equivariant Networks for DNA Sequences

Nonsmooth Implicit Differentiation for Machine-Learning and Optimization

Marginalised Gaussian Processes with Nested Sampling

A Continuous Mapping For Augmentation Design

GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles

Compositional Modeling of Nonlinear Dynamical Systems with ODE-based Random Features

Learning Treatment Effects in Panels with General Intervention Patterns

From Optimality to Robustness: Adaptive Re-Sampling Strategies in Stochastic Bandits

Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics

Meta Learning Backpropagation And Improving It

Optimizing Reusable Knowledge for Continual Learning via Metalearning

A sampling-based circuit for optimal decision making

Compressed Video Contrastive Learning

Attention Bottlenecks for Multimodal Fusion

Spot the Difference: Detection of Topological Changes via Geometric Alignment

SE(3)-equivariant prediction of molecular wavefunctions and electronic densities

S$^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks

Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark

Sequential Causal Imitation Learning with Unobserved Confounders

Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling

DOBF: A Deobfuscation Pre-Training Objective for Programming Languages

Learning-to-learn non-convex piecewise-Lipschitz functions

Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems

Attention Approximates Sparse Distributed Memory

Finding Regions of Heterogeneity in Decision-Making via Expected Conditional Covariance

Identifying and Benchmarking Natural Out-of-Context Prediction Problems

Overinterpretation reveals image classification model pathologies

Neural Circuit Synthesis from Specification Patterns

Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction

Adversarial Examples for k-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams

Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions

Neural Population Geometry Reveals the Role of Stochasticity in Robust Perception

Iterative Amortized Policy Optimization

Revisiting the Calibration of Modern Neural Networks

Nested Graph Neural Networks

A flow-based latent state generative model of neural population responses to natural images

On Inductive Biases for Heterogeneous Treatment Effect Estimation

Adversarial Graph Augmentation to Improve Graph Contrastive Learning

Probabilistic Tensor Decomposition of Neural Population Spiking Activity

Safe Pontryagin Differentiable Programming

Multi-armed Bandit Requiring Monotone Arm Sequences

Generalizable Imitation Learning from Observation via Inferring Goal Proximity

Deformable Butterfly: A Highly Structured and Sparse Linear Transform

Counterfactual Invariance to Spurious Correlations in Text Classification

Neural optimal feedback control with local learning rules

Noether Networks: meta-learning useful conserved quantities

Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style

Multimodal Virtual Point 3D Detection

Learning with Algorithmic Supervision via Continuous Relaxations

Higher Order Kernel Mean Embeddings to Capture Filtrations of Stochastic Processes

Information Directed Sampling for Sparse Linear Bandits

Recovering Latent Causal Factor for Generalization to Distributional Shifts

Dynamic population-based meta-learning for multi-agent communication with natural language

Statistical Regeneration Guarantees of the Wasserstein Autoencoder with Latent Space Consistency

Leveraging the Inductive Bias of Large Language Models for Abstract Textual Reasoning

Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Independent Projected Kernels

Provably Strict Generalisation Benefit for Invariance in Kernel Methods

Causal Inference for Event Pairs in Multivariate Point Processes

Evaluating model performance under worst-case subpopulations

Projected GANs Converge Faster

Large-Scale Learning with Fourier Features and Tensor Decompositions

TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness

Moser Flow: Divergence-based Generative Modeling on Manifolds

Long-Short Transformer: Efficient Transformers for Language and Vision

Deconditional Downscaling with Gaussian Processes

The Pareto Frontier of model selection for general Contextual Bandits

Supervising the Transfer of Reasoning Patterns in VQA

Fast Certified Robust Training with Short Warmup

Behavior From the Void: Unsupervised Active Pre-Training

Autonomous Reinforcement Learning via Subgoal Curricula

Statistically and Computationally Efficient Linear Meta-representation Learning

Decentralized Learning in Online Queuing Systems

BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining

Fitting summary statistics of neural data with a differentiable spiking network simulator

PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators

Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits

Monte Carlo Tree Search With Iteratively Refining State Abstractions

Learning Models for Actionable Recourse

Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms

Bandit Phase Retrieval

Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination

Revisiting Deep Learning Models for Tabular Data

Neural Program Generation Modulo Static Analysis

Tighter Expected Generalization Error Bounds via Wasserstein Distance

Adversarial Robustness with Non-uniform Perturbations

Leveraging Distribution Alignment via Stein Path for Cross-Domain Cold-Start Recommendation

Separation Results between Fixed-Kernel and Feature-Learning Probability Metrics

Scalable Diverse Model Selection for Accessible Transfer Learning

Differentiable Annealed Importance Sampling and the Perils of Gradient Noise

Exploiting a Zoo of Checkpoints for Unseen Tasks

Grounding inductive biases in natural images: invariance stems from variations in data

Matching a Desired Causal State via Shift Interventions

Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport

Optimality of variational inference for stochasticblock model with missing links

Row-clustering of a Point Process-valued Matrix

SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition

Reliable Causal Discovery with Improved Exact Search and Weaker Assumptions

Across-animal odor decoding by probabilistic manifold alignment

Differentiable rendering with perturbed optimizers

Nested Variational Inference

On sensitivity of meta-learning to support data

Private learning implies quantum stability

BNS: Building Network Structures Dynamically for Continual Learning

Object DGCNN: 3D Object Detection using Dynamic Graphs

The balancing principle for parameter choice in distance-regularized domain adaptation

Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks

MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge

TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation

Learning Graph Cellular Automata

Provably Efficient Causal Reinforcement Learning with Confounded Observational Data

Optimal Order Simple Regret for Gaussian Process Bandits

PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition

Multi-Objective Meta Learning

Mini-Batch Consistent Slot Set Encoder for Scalable Set Encoding

Online Matching in Sparse Random Graphs: Non-Asymptotic Performances of Greedy Algorithm

When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?

Perceptual Score: What Data Modalities Does Your Model Perceive?

Variational Diffusion Models

Stateful ODE-Nets using Basis Function Expansions

TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?

Double Machine Learning Density Estimation for Local Treatment Effects with Instruments

SOLQ: Segmenting Objects by Learning Queries

Asymptotically Best Causal Effect Identification with Multi-Armed Bandits

Learning rule influences recurrent network representations but not attractor structure in decision-making tasks

Fair Exploration via Axiomatic Bargaining

Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning

On the Bias-Variance-Cost Tradeoff of Stochastic Optimization

Comprehensive Knowledge Distillation with Causal Intervention

Biological learning in key-value memory networks

Correlated Stochastic Block Models: Exact Graph Matching with Applications to Recovering Communities

Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration

Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization

Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning

Learning Disentangled Behavior Embeddings

Revisiting ResNets: Improved Training and Scaling Strategies

On the Rate of Convergence of Regularized Learning in Games: From Bandits and Uncertainty to Optimism and Beyond

Aligning Pretraining for Detection via Object-Level Contrastive Learning

Design of Experiments for Stochastic Contextual Linear Bandits

Identification of Partially Observed Linear Causal Models: Graphical Conditions for the Non-Gaussian and Heterogeneous Cases

Adversarially Robust Change Point Detection

Optimal Policies Tend To Seek Power

COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining

Bandits with Knapsacks beyond the Worst Case

The Difficulty of Passive Learning in Deep Reinforcement Learning

Editing a classifier by rewriting its prediction rules

Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing

Black Box Probabilistic Numerics

Interpolation can hurt robust generalization even when there is no noise

Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training

Fast rates for prediction with limited expert advice

Spatio-Temporal Variational Gaussian Processes

Adaptive Risk Minimization: Learning to Adapt to Domain Shift

Off-Policy Risk Assessment in Contextual Bandits

Bias and variance of the Bayesian-mean decoder

Partial success in closing the gap between human and machine vision

Snowflake: Scaling GNNs to high-dimensional continuous control via parameter freezing

DiBS: Differentiable Bayesian Structure Learning

Nonparametric estimation of continuous DPPs with kernel methods

Training Neural Networks with Fixed Sparse Masks

VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text

Fast and accurate randomized algorithms for low-rank tensor decompositions

Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridge

Understanding Adaptive, Multiscale Temporal Integration In Deep Speech Recognition Systems

VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer

On Episodes, Prototypical Networks, and Few-Shot Learning

Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering

Domain Adaptation with Invariant Representation Learning: What Transformations to Learn?

Piper: Multidimensional Planner for DNN Parallelization

Causal Effect Inference for Structured Treatments

A Causal Lens for Controllable Text Generation

Counterfactual Maximum Likelihood Estimation for Training Deep Networks

Learning Debiased Representation via Disentangled Feature Augmentation

Scallop: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning

Learning the optimal Tikhonov regularizer for inverse problems

On Margin-Based Cluster Recovery with Oracle Queries

Dense Unsupervised Learning for Video Segmentation

Charting and Navigating the Space of Solutions for Recurrent Neural Networks

Reusing Combinatorial Structure: Faster Iterative Projections over Submodular Base Polytopes

Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification

Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability

Reformulating Zero-shot Action Recognition for Multi-label Actions

Optimal Best-Arm Identification Methods for Tail-Risk Measures

A Theory of the Distortion-Perception Tradeoff in Wasserstein Space

Implicit Task-Driven Probability Discrepancy Measure for Unsupervised Domain Adaptation

Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis

Fast Algorithms for $L_\infty$-constrained S-rectangular Robust MDPs

PatchGame: Learning to Signal Mid-level Patches in Referential Games

Tensor Normal Training for Deep Learning Models

Morié Attack (MA): A New Potential Risk of Screen Photos

Certifying Robustness to Programmable Data Bias in Decision Trees

Bayesian decision-making under misspecified priors with applications to meta-learning

Identification and Estimation of Joint Probabilities of Potential Outcomes in Observational Studies with Covariate Information

On the Algorithmic Stability of Adversarial Training

SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data

Optimal Rates for Nonparametric Density Estimation under Communication Constraints

Learning Generalized Gumbel-max Causal Mechanisms

Streaming Belief Propagation for Community Detection

Passive attention in artificial neural networks predicts human visual selectivity

Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies

An analysis of Ermakov-Zolotukhin quadrature using kernels

Unsupervised Object-Based Transition Models For 3D Partially Observable Environments

Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning

Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation

Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks

Online and Offline Reinforcement Learning by Planning with a Learned Model

Identifiable Generative models for Missing Not at Random Data Imputation

Dueling Bandits with Adversarial Sleeping

Beware of the Simulated DAG! Causal Discovery Benchmarks May Be Easy to Game

Robustness between the worst and average case

Online Learning and Control of Complex Dynamical Systems from Sensory Input

On Memorization in Probabilistic Deep Generative Models

Dynamical Wasserstein Barycenters for Time-series Modeling

Encoding Robustness to Image Style via Adversarial Feature Perturbations

An Empirical Investigation of Domain Generalization with Empirical Risk Minimizers

Towards Sample-efficient Overparameterized Meta-learning

Towards mental time travel: a hierarchical memory for reinforcement learning agents

Beyond Tikhonov: faster learning with self-concordant losses, via iterative regularization

Robustness via Uncertainty-aware Cycle Consistency

Post-Contextual-Bandit Inference

Online Convex Optimization with Continuous Switching Constraint

Adversarially robust learning for security-constrained optimal power flow

Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

Your head is there to move you around: Goal-driven models of the primate dorsal pathway

Achieving Rotational Invariance with Bessel-Convolutional Neural Networks

A Domain-Shrinking based Bayesian Optimization Algorithm with Order-Optimal Regret Performance

Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

Learning Robust Hierarchical Patterns of Human Brain across Many fMRI Studies

Bandit Quickest Changepoint Detection

Optimal Gradient-based Algorithms for Non-concave Bandit Optimization

Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time

How Does it Sound?

Stabilizing Dynamical Systems via Policy Gradient Methods

Language models enable zero-shot prediction of the effects of mutations on protein function

Mind the Gap: Assessing Temporal Generalization in Neural Language Models

Targeted Neural Dynamical Modeling

On the Role of Optimization in Double Descent: A Least Squares Study

PCA Initialization for Approximate Message Passing in Rotationally Invariant Models

Distributional Gradient Matching for Learning Uncertain Neural Dynamics Models

Near-Optimal Lower Bounds For Convex Optimization For All Orders of Smoothness

Data Augmentation Can Improve Robustness

Delayed Gradient Averaging: Tolerate the Communication Latency for Federated Learning

Optimal Algorithms for Stochastic Contextual Preference Bandits

Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize

MICo: Improved representations via sampling-based state similarity for Markov decision processes

Counterfactual Explanations in Sequential Decision Making Under Uncertainty

SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness

Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks

Structural Credit Assignment in Neural Networks using Reinforcement Learning

Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels

Adversarial Examples Make Strong Poisons

Early Convolutions Help Transformers See Better

InfoGCL: Information-Aware Graph Contrastive Learning

Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data

(ends 10:00 AM)

10 a.m.

Competition:

Competition Track Day 1: Overviews + Breakout Sessions

(ends 3:04 PM)

Affinity Workshop:

LatinX in AI (LXAI) Research @ NeurIPS 2021

(ends 3:00 PM)

11 a.m.

Affinity Workshop:

New in ML 2

(ends 2:33 PM)

3 p.m.

Invited Talk:

The Banality of Scale: A Theory on the Limits of Modeling Bias and Fairness Frameworks for Social Justice (and other lessons from the Pandemic)

Mary L. Gray

(ends 4:30 PM)

4:30 p.m.

Poster Session 2 [4:30-6:00]

UniDoc: Unified Pretraining Framework for Document Understanding

AugMax: Adversarial Composition of Random Augmentations for Robust Training

Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization

Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks

Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning

Multi-Person 3D Motion Prediction with Multi-Range Transformers

Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations

When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work

Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning

Pareto-Optimal Learning-Augmented Algorithms for Online Conversion Problems

Conservative Data Sharing for Multi-Task Offline Reinforcement Learning

Accommodating Picky Customers: Regret Bound and Exploration Complexity for Multi-Objective Reinforcement Learning

The Emergence of Objectness: Learning Zero-shot Segmentation from Videos

Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints

Self-Supervised Multi-Object Tracking with Cross-input Consistency

Exponential Graph is Provably Efficient for Decentralized Deep Training

Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training

Weighted model estimation for offline model-based reinforcement learning

Improved Transformer for High-Resolution GANs

Understanding the Effect of Stochasticity in Policy Optimization

Excess Capacity and Backdoor Poisoning

Amortized Variational Inference for Simple Hierarchical Models

Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data

Predicting Event Memorability from Contextual Visual Semantics

Representer Point Selection via Local Jacobian Expansion for Post-hoc Classifier Explanation of Deep Neural Networks and Ensemble Models

Densely connected normalizing flows

CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation

Symbolic Regression via Deep Reinforcement Learning Enhanced Genetic Programming Seeding

Choose a Transformer: Fourier or Galerkin

Fine-grained Generalization Analysis of Inductive Matrix Completion

MagNet: A Neural Network for Directed Graphs

Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation

AC-GC: Lossy Activation Compression with Guaranteed Convergence

Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Do Transformers Really Perform Badly for Graph Representation?

Learning Space Partitions for Path Planning

TopicNet: Semantic Graph-Guided Topic Discovery

Subgroup Generalization and Fairness of Graph Neural Networks

Reconstruction for Powerful Graph Representations

Efficient Truncated Linear Regression with Unknown Noise Variance

Inverse-Weighted Survival Games

Representation Learning on Spatial Networks

Iteratively Reweighted Least Squares for Basis Pursuit with Global Linear Convergence Rate

Low-Rank Constraints for Fast Inference in Structured Models

Accumulative Poisoning Attacks on Real-time Data

An Improved Analysis and Rates for Variance Reduction under Without-replacement Sampling Orders

Exploring Forensic Dental Identification with Deep Learning

Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)

On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness

QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning

Exploiting Local Convergence of Quasi-Newton Methods Globally: Adaptive Sample Size Approach

SSMF: Shifting Seasonal Matrix Factorization

Sample Complexity of Tree Search Configuration: Cutting Planes and Beyond

Understanding the Generalization Benefit of Model Invariance from a Data Perspective

Robust Regression Revisited: Acceleration and Improved Estimation Rates

Regime Switching Bandits

Towards Robust Bisimulation Metric Learning

Limiting fluctuation and trajectorial stability of multilayer neural networks with mean field training

Learning where to learn: Gradient sparsity in meta and continual learning

Simple steps are all you need: Frank-Wolfe and generalized self-concordant functions

Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks

Machine learning structure preserving brackets for forecasting irreversible processes

On the Variance of the Fisher Information for Deep Learning

ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE

A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning

Visualizing the Emergence of Intermediate Visual Patterns in DNNs

Functional Neural Networks for Parametric Image Restoration Problems

Does Knowledge Distillation Really Work?

argmax centroid

On the Value of Infinite Gradients in Variational Autoencoder Models

Meta-learning with an Adaptive Task Scheduler

Joint Modeling of Visual Objects and Relations for Scene Graph Generation

Open-set Label Noise Can Improve Robustness Against Inherent Label Noise

Learning to Elect

How Data Augmentation affects Optimization for Linear Regression

Gradual Domain Adaptation without Indexed Intermediate Domains

K-level Reasoning for Zero-Shot Coordination in Hanabi

Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems

L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization

Pay Attention to MLPs

A Highly-Efficient Group Elastic Net Algorithm with an Application to Function-On-Scalar Regression

Evaluating State-of-the-Art Classification Models Against Bayes Optimality

Novel Upper Bounds for the Constrained Most Probable Explanation Task

MADE: Exploration via Maximizing Deviation from Explored Regions

Variational Model Inversion Attacks

Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others

List-Decodable Mean Estimation in Nearly-PCA Time

Escaping Saddle Points with Compressed SGD

Faster Matchings via Learned Duals

Equivariant Manifold Flows

Few-Shot Data-Driven Algorithms for Low Rank Approximation

Information is Power: Intrinsic Control via Information Capture

SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning

Quantifying and Improving Transferability in Domain Generalization

Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling

Dynamic Normalization and Relay for Video Action Recognition

An Improved Analysis of Gradient Tracking for Decentralized Machine Learning

DeepGEM: Generalized Expectation-Maximization for Blind Inversion

Generalized Proximal Policy Optimization with Sample Reuse

Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems

Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality

Out-of-Distribution Generalization in Kernel Regression

A Multi-Implicit Neural Representation for Fonts

Direct Multi-view Multi-person 3D Pose Estimation

Curriculum Learning for Vision-and-Language Navigation

Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms

Temporal-attentive Covariance Pooling Networks for Video Recognition

Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction

Prior-independent Dynamic Auctions for a Value-maximizing Buyer

Overparameterization Improves Robustness to Covariate Shift in High Dimensions

Towards Biologically Plausible Convolutional Networks

CLIP-It! Language-Guided Video Summarization

Lossy Compression for Lossless Prediction

Generalized DataWeighting via Class-Level Gradient Manipulation

Unsupervised Foreground Extraction via Deep Region Competition

Modified Frank Wolfe in Probability Space

Profiling Pareto Front With Multi-Objective Stein Variational Gradient Descent

TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up

Automorphic Equivalence-aware Graph Neural Network

Unadversarial Examples: Designing Objects for Robust Vision

Deep Jump Learning for Off-Policy Evaluation in Continuous Treatment Settings

Augmented Shortcuts for Vision Transformers

Leveraging SE(3) Equivariance for Self-supervised Category-Level Object Pose Estimation from Point Clouds

Self-Supervised Learning with Kernel Dependence Maximization

Dimensionality Reduction for Wasserstein Barycenter

Nearly Horizon-Free Offline Reinforcement Learning

Rethinking Neural Operations for Diverse Tasks

Motif-based Graph Self-Supervised Learning for Molecular Property Prediction

Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations

Diffusion Normalizing Flow

Learned Robust PCA: A Scalable Deep Unfolding Approach for High-Dimensional Outlier Detection

An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning

Relaxing Local Robustness

Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer

Differentiable Simulation of Soft Multi-body Systems

A Prototype-Oriented Framework for Unsupervised Domain Adaptation

Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation

Robust Auction Design in the Auto-bidding World

MOMA: Multi-Object Multi-Actor Activity Parsing

No-Press Diplomacy from Scratch

Remember What You Want to Forget: Algorithms for Machine Unlearning

Understanding the Under-Coverage Bias in Uncertainty Estimation

Heavy Ball Neural Ordinary Differential Equations

Taxonomizing local versus global structure in neural network loss landscapes

EIGNN: Efficient Infinite-Depth Graph Neural Networks

Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance

Amortized Synthesis of Constrained Configurations Using a Differentiable Surrogate

Scheduling jobs with stochastic holding costs

Rethinking conditional GAN training: An approach using geometrically structured latent manifolds

Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning

Provably efficient multi-task reinforcement learning with model transfer

Reverse engineering learned optimizers reveals known and novel mechanisms

Model-Based Domain Generalization

Differentiable Spline Approximations

Deep Residual Learning in Spiking Neural Networks

Learning and Generalization in RNNs

Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers

Rethinking Graph Transformers with Spectral Attention

PiRank: Scalable Learning To Rank via Differentiable Sorting

Iterative Teaching by Label Synthesis

Unifying lower bounds on prediction dimension of convex surrogates

Reinforcement Learning with Latent Flow

Understanding How Encoder-Decoder Architectures Attend

Testing Probabilistic Circuits

Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting

Analysis of Sensing Spectral for Signal Recovery under a Generalized Linear Model

Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds

Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses

NN-Baker: A Neural-network Infused Algorithmic Framework for Optimization Problems on Geometric Intersection Graphs

PLUR: A Unifying, Graph-Based View of Program Learning, Understanding, and Repair

XDO: A Double Oracle Algorithm for Extensive-Form Games

A mechanistic multi-area recurrent network model of decision-making

Differentiable Spike: Rethinking Gradient-Descent for Training Spiking Neural Networks

Towards a Theoretical Framework of Out-of-Distribution Generalization

Learning State Representations from Random Deep Action-conditional Predictions

Adaptive Denoising via GainTuning

Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration

Particle Cloud Generation with Message Passing Generative Adversarial Networks

Dual Adaptivity: A Universal Algorithm for Minimizing the Adaptive Regret of Convex Functions

NovelD: A Simple yet Effective Exploration Criterion

Machine versus Human Attention in Deep Reinforcement Learning Tasks

Absolute Neighbour Difference based Correlation Test for Detecting Heteroscedastic Relationships

Learning Frequency Domain Approximation for Binary Neural Networks

A Faster Decentralized Algorithm for Nonconvex Minimax Problems

Revisiting 3D Object Detection From an Egocentric Perspective

Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering

The Elastic Lottery Ticket Hypothesis

Bandit Learning with Delayed Impact of Actions

Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries Paradigm

The Role of Global Labels in Few-Shot Classification and How to Infer Them

Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval

On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sources

You Are the Best Reviewer of Your Own Papers: An Owner-Assisted Scoring Mechanism

CBP: backpropagation with constraint on weight precision using a pseudo-Lagrange multiplier method

Stateful Strategic Regression

Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning

Unsupervised Object-Level Representation Learning from Scene Images

Differentiable Optimization of Generalized Nondecomposable Functions using Linear Programs

Learning with Noisy Correspondence for Cross-modal Matching

Parameter Prediction for Unseen Deep Architectures

FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention

ELLA: Exploration through Learned Language Abstraction

On the Cryptographic Hardness of Learning Single Periodic Neurons

Automatic and Harmless Regularization with Constrained and Lexicographic Optimization: A Dynamic Barrier Approach

Discovery of Options via Meta-Learned Subgoals

Residual Pathway Priors for Soft Equivariance Constraints

Learning Large Neighborhood Search Policy for Integer Programming

Validating the Lottery Ticket Hypothesis with Inertial Manifold Theory

(ends 6:00 PM)

6 p.m.

8 p.m.

11 p.m.

Invited Talk (Breiman Lecture):

Do We Know How to Estimate the Mean?

Gabor Lugosi

(ends 12:30 AM)

WED 8 DEC

midnight

Datasets and Benchmarks:

Dataset and Benchmark Poster Session 2

(ends 2:00 AM)

12:30 a.m.

Poster Session 3 [12:30-2:00]

Neighborhood Reconstructing Autoencoders

Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples

Compacter: Efficient Low-Rank Hypercomplex Adapter Layers

Distilling Image Classifiers in Object Detectors

Learning on Random Balls is Sufficient for Estimating (Some) Graph Parameters

Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond

Learning Conjoint Attentions for Graph Neural Nets

Convex-Concave Min-Max Stackelberg Games

3D Pose Transfer with Correspondence Learning and Mesh Refinement

Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training

Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness

IQ-Learn: Inverse soft-Q Learning for Imitation

Invertible Tabular GANs: Killing Two Birds with One Stone for Tabular Data Synthesis

Pruning Randomly Initialized Neural Networks with Iterative Randomization

MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps

Credit Assignment in Neural Networks through Deep Feedback Control

Accurately Solving Rod Dynamics with Graph Learning

Distilling Object Detectors with Feature Richness

Learning Causal Semantic Representation for Out-of-Distribution Prediction

Ising Model Selection Using $\ell_{1}$-Regularized Linear Regression: A Statistical Mechanics Analysis

Learnability of Linear Thresholds from Label Proportions

Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders

SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization

Interpreting Representation Quality of DNNs for 3D Point Cloud Processing

Differentiable Learning Under Triage

Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime

Learning Collaborative Policies to Solve NP-hard Routing Problems

Modality-Agnostic Topology Aware Localization

Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer

Differentiable Synthesis of Program Architectures

Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression

Learning to dehaze with polarization

Coarse-to-fine Animal Pose and Shape Estimation

Video Instance Segmentation using Inter-Frame Communication Transformers

RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning

Hard-Attention for Scalable Image Classification

Neural Relightable Participating Media Rendering

Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction

Few-Shot Object Detection via Association and DIscrimination

Linear Convergence of Gradient Methods for Estimating Structured Transition Matrices in High-dimensional Vector Autoregressive Models

PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning

Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons

Vector-valued Distance and Gyrocalculus on the Space of Symmetric Positive Definite Matrices

FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling

The Image Local Autoregressive Transformer

All Tokens Matter: Token Labeling for Training Better Vision Transformers

Policy Learning Using Weak Supervision

Uncertainty Quantification and Deep Ensembles

BCORLE($\lambda$): An Offline Reinforcement Learning and Evaluation Framework for Coupons Allocation in E-commerce Market

TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks

Exploiting Domain-Specific Features to Enhance Domain Generalization

Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs

VAST: Value Function Factorization with Variable Agent Sub-Teams

A Framework to Learn with Interpretation

Using Random Effects to Account for High-Cardinality Categorical Features and Repeated Measures in Deep Neural Networks

Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch

Learning from Inside: Self-driven Siamese Sampling and Reasoning for Video Question Answering

Fast Abductive Learning by Similarity-based Consistency Optimization

Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects

Action-guided 3D Human Motion Prediction

Scalable Rule-Based Representation Learning for Interpretable Classification

Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection

Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution

BAST: Bayesian Additive Regression Spanning Trees for Complex Constrained Domain

VoiceMixer: Adversarial Voice Style Mixup

CentripetalText: An Efficient Text Instance Representation for Scene Text Detection

Landmark-RxR: Solving Vision-and-Language Navigation with Fine-Grained Alignment Supervision

Improving black-box optimization in VAE latent space using decoder uncertainty

Alias-Free Generative Adversarial Networks

Global Filter Networks for Image Classification

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation

Generalization Bounds for Graph Embedding Using Negative Sampling: Linear vs Hyperbolic

Regularized Softmax Deep Multi-Agent Q-Learning

Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling

Smooth Bilevel Programming for Sparse Regularization

Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics

Do Input Gradients Highlight Discriminative Features?

Word2Fun: Modelling Words as Functions for Diachronic Word Representation

Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning

Contextual Similarity Aggregation with Self-attention for Visual Re-ranking

Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space

Control Variates for Slate Off-Policy Evaluation

Debiased Visual Question Answering from Feature and Sample Perspectives

Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity

Celebrating Diversity in Shared Multi-Agent Reinforcement Learning

Optimizing Conditional Value-At-Risk of Black-Box Functions

Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning

How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?

Faster Directional Convergence of Linear Neural Networks under Spherically Symmetric Data

Neural Additive Models: Interpretable Machine Learning with Neural Nets

Batch Normalization Orthogonalizes Representations in Deep Random Networks

Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss

Convex Polytope Trees

Capturing implicit hierarchical structure in 3D biomedical images with self-supervised hyperbolic representations

When Is Unsupervised Disentanglement Possible?

SPANN: Highly-efficient Billion-scale Approximate Nearest Neighborhood Search

Efficient Equivariant Network

Even your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed by Self-Distillation

A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration

Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction

Contrastive Laplacian Eigenmaps

Dynamic Grained Encoder for Vision Transformers

A 3D Generative Model for Structure-Based Drug Design

Robust Pose Estimation in Crowded Scenes with Direct Pose-Level Inference

Contrastive Graph Poisson Networks: Semi-Supervised Learning with Extremely Limited Labels

Generalized and Discriminative Few-Shot Object Detection via SVD-Dictionary Enhancement

Self-Instantiated Recurrent Units with Dynamic Soft Recursion

Greedy and Random Quasi-Newton Methods with Faster Explicit Superlinear Convergence

Loss function based second-order Jensen inequality and its application to particle variational inference

An Empirical Study of Adder Neural Networks for Object Detection

ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning

Discovering Dynamic Salient Regions for Spatio-Temporal Graph Neural Networks

Weak-shot Fine-grained Classification via Similarity Transfer

On Optimal Robustness to Adversarial Corruption in Online Decision Problems

Learning Debiased and Disentangled Representations for Semantic Segmentation

On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry

Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning

Adversarial Examples in Multi-Layer Random ReLU Networks

TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning

Data-Efficient Instance Generation from Instance Discrimination

Differentiable Equilibrium Computation with Decision Diagrams for Stackelberg Models of Combinatorial Congestion Games

Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification

Conic Blackwell Algorithm: Parameter-Free Convex-Concave Saddle-Point Solving

Align before Fuse: Vision and Language Representation Learning with Momentum Distillation

A single gradient step finds adversarial examples on random two-layers neural networks

Reliable Estimation of KL Divergence using a Discriminator in Reproducing Kernel Hilbert Space

Mitigating Forgetting in Online Continual Learning with Neuron Calibration

K-Net: Towards Unified Image Segmentation

Learning to Simulate Self-driven Particles System with Coordinated Policy Optimization

Bridging Explicit and Implicit Deep Generative Models via Neural Stein Estimators

Meta-Learning Sparse Implicit Neural Representations

Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition

Multi-View Representation Learning via Total Correlation Objective

Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning

OctField: Hierarchical Implicit Functions for 3D Modeling

Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect

Non-asymptotic convergence bounds for Wasserstein approximation using point clouds

Pareto Domain Adaptation

Self-Supervised GANs with Label Augmentation

Sifting through the noise: Universal first-order methods for stochastic variational inequalities

Towards Stable and Robust AdderNets

Alignment Attention by Matching Key and Query Distributions

Neural Routing by Memory

Safe Reinforcement Learning by Imagining the Near Future

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Learning Transferable Adversarial Perturbations

Posterior Meta-Replay for Continual Learning

On the Convergence of Step Decay Step-Size for Stochastic Optimization

Rethinking and Reweighting the Univariate Losses for Multi-Label Ranking: Consistency and Generalization

Credal Self-Supervised Learning

A PAC-Bayes Analysis of Adversarial Robustness

Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions

Dynamic Sasvi: Strong Safe Screening for Norm-Regularized Least Squares

What Matters for Adversarial Imitation Learning?

MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agents

Graph Adversarial Self-Supervised Learning

Locally Most Powerful Bayesian Test for Out-of-Distribution Detection using Deep Generative Models

Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks

Structured Dropout Variational Inference for Bayesian Neural Networks

Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL

Multimodal and Multilingual Embeddings for Large-Scale Speech Mining

DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples

Transformer in Transformer

DualNet: Continual Learning, Fast and Slow

Learning Diverse Policies in MOBA Games via Macro-Goals

Determinantal point processes based on orthogonal polynomials for sampling minibatches in SGD

Deep Molecular Representation Learning via Fusing Physical and Chemical Information

GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training

Online Learning Of Neural Computations From Sparse Temporal Feedback

Instance-Conditional Knowledge Distillation for Object Detection

On Joint Learning for Solving Placement and Routing in Chip Design

Neural Dubber: Dubbing for Videos According to Scripts

Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space

Noisy Adaptation Generates Lévy Flights in Attractor Neural Networks

Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck

Mining the Benefits of Two-stage and One-stage HOI Detection

Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains

Relative Uncertainty Learning for Facial Expression Recognition

Image Generation using Continuous Filter Atoms

BooVAE: Boosting Approach for Continual Learning of VAE

Handling Long-tailed Feature Distribution in AdderNets

Training Neural Networks is ER-complete

Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence

Online Variational Filtering and Parameter Learning

Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning

Efficient and Accurate Gradients for Neural SDEs

Unfolding Taylor's Approximations for Image Restoration

Metropolis-Hastings Data Augmentation for Graph Neural Networks

Adaptive First-Order Methods Revisited: Convex Minimization without Lipschitz Requirements

Adversarial Teacher-Student Representation Learning for Domain Generalization

Fast Axiomatic Attribution for Neural Networks

OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression

Only Train Once: A One-Shot Neural Network Training And Pruning Framework

Predicting Molecular Conformation via Dynamic Graph Score Matching

Rate-Optimal Subspace Estimation on Random Graphs

Node Dependent Local Smoothing for Scalable Graph Learning

Variational Inference for Continuous-Time Switching Dynamical Systems

Generative Occupancy Fields for 3D Surface-Aware Image Synthesis

Gaussian Kernel Mixture Network for Single Image Defocus Deblurring

Duplex Sequence-to-Sequence Learning for Reversible Machine Translation

DeepReduce: A Sparse-tensor Communication Framework for Federated Deep Learning

A self consistent theory of Gaussian Processes captures feature learning effects in finite CNNs

Learning Transferable Features for Point Cloud Detection via 3D Contrastive Co-training

Generative vs. Discriminative: Rethinking The Meta-Continual Learning

FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition

On Robust Optimal Transport: Computational Complexity and Barycenter Computation

Searching Parameterized AP Loss for Object Detection

Two steps to risk sensitivity

Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks

AFEC: Active Forgetting of Negative Transfer in Continual Learning

Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding

LADA: Look-Ahead Data Acquisition via Augmentation for Deep Active Learning

Probabilistic Margins for Instance Reweighting in Adversarial Training

Unbalanced Optimal Transport through Non-negative Penalized Linear Regression

A Hierarchical Reinforcement Learning Based Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems

Tracking People with 3D Representations

Learning Riemannian metric for disease progression modeling

Efficient Training of Visual Transformers with Small Datasets

CoFiNet: Reliable Coarse-to-fine Correspondences for Robust PointCloud Registration

Learning Nonparametric Volterra Kernels with Gaussian Processes

FINE Samples for Learning with Noisy Labels

Instance-Dependent Bounds for Zeroth-order Lipschitz Optimization with Error Certificates

MLP-Mixer: An all-MLP Architecture for Vision

AutoGEL: An Automated Graph Neural Network with Explicit Link Information

Recognizing Vector Graphics without Rasterization

Unsupervised Representation Transfer for Small Networks: I Believe I Can Distill On-the-Fly

Information-theoretic generalization bounds for black-box learning algorithms

Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)

A/B/n Testing with Control in the Presence of Subpopulations

Sparse Quadratic Optimisation over the Stiefel Manifold with Application to Permutation Synchronisation

Dual-stream Network for Visual Recognition

Mastering Atari Games with Limited Data

Set Prediction in the Latent Space

Neural Production Systems

Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods

Non-approximate Inference for Collective Graphical Models on Path Graphs via Discrete Difference of Convex Algorithm

SBO-RNN: Reformulating Recurrent Neural Networks via Stochastic Bilevel Optimization

Navigating to the Best Policy in Markov Decision Processes

A Mathematical Framework for Quantifying Transferability in Multi-source Transfer Learning

You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection

Low-Rank Extragradient Method for Nonsmooth and Low-Rank Matrix Optimization Problems

Coordinated Proximal Policy Optimization

Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model

The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle

Universal Semi-Supervised Learning

Improving Deep Learning Interpretability by Saliency Guided Training

Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery

PolarStream: Streaming Object Detection and Segmentation with Polar Pillars

Distilling Meta Knowledge on Heterogeneous Graph for Illicit Drug Trafficker Detection on Social Media

Instance-Dependent Partial Label Learning

UFC-BERT: Unifying Multi-Modal Controls for Conditional Image Synthesis

General Low-rank Matrix Optimization: Geometric Analysis and Sharper Bounds

A Non-commutative Extension of Lee-Seung's Algorithm for Positive Semidefinite Factorizations

Garment4D: Garment Reconstruction from Point Cloud Sequences

RIM: Reliable Influence-based Active Learning on Graphs

RelaySum for Decentralized Deep Learning on Heterogeneous Data

Continuized Accelerations of Deterministic and Stochastic Gradient Descents, and of Gossip Algorithms

Natural continual learning: success is a journey, not (just) a destination

Post-Training Quantization for Vision Transformer

Variational Bayesian Reinforcement Learning with Regret Bounds

Implicit Sparse Regularization: The Impact of Depth and Early Stopping

No-regret Online Learning over Riemannian Manifolds

Parametrized Quantum Policies for Reinforcement Learning

Adaptive Online Packing-guided Search for POMDPs

Continual World: A Robotic Benchmark For Continual Reinforcement Learning

GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph

Balanced Chamfer Distance as a Comprehensive Metric for Point Cloud Completion

On Optimal Interpolation in Linear Regression

Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization

STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data

Iterative Teacher-Aware Learning

Offline Reinforcement Learning with Reverse Model-based Imagination

Neural Architecture Dilation for Adversarial Robustness

BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation

Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning

Topology-Imbalance Learning for Semi-Supervised Node Classification

(ends 2:00 AM)

2 a.m.

Competition:

Competition Track Day 2: Overviews + Breakout Sessions

(ends 6:44 AM)

3 a.m.

7 a.m.

Panel:

The Role of Benchmarks in the Scientific Progress of Machine Learning

(ends 8:00 AM)

8 a.m.

Datasets and Benchmarks:

Dataset and Benchmark Track 2

(ends 9:00 AM)

Oral Session 3: Deep Learning [8:00-9:00]

Oral s 8:00-8:15

[8:00] Unsupervised Speech Recognition

Q&A s 8:15-8:20

[8:15] Q&A

Oral s 8:20-8:35

[8:20] Deep Reinforcement Learning at the Edge of the Statistical Precipice

Q&A s 8:35-8:40

[8:35] Q&A

Oral s 8:40-8:55

[8:40] Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss

Q&A s 8:55-9:00

[8:55] Q&A

(ends 9:00 AM)

Oral Session 3: Optimization [8:00-9:00]

Oral s 8:00-8:15

[8:00] Continuized Accelerations of Deterministic and Stochastic Gradient Descents, and of Gossip Algorithms

Q&A s 8:15-8:20

[8:15] Q&A

Oral s 8:20-8:35

[8:20] Oracle Complexity in Nonsmooth Nonconvex Optimization

Q&A s 8:35-8:40

[8:35] Q&A

Oral s 8:40-8:55

[8:40] Faster Matchings via Learned Duals

Q&A s 8:55-9:00

[8:55] Q&A

(ends 9:00 AM)

Oral Session 3: Theory [8:00-9:00]

Oral s 8:00-8:15

[8:00] Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination

Q&A s 8:15-8:20

[8:15] Q&A

Oral s 8:20-8:35

[8:20] Bellman-consistent Pessimism for Offline Reinforcement Learning

Q&A s 8:35-8:40

[8:35] Q&A

Oral s 8:40-8:55

[8:40] A Compositional Atlas of Tractable Circuit Operations for Probabilistic Inference

Q&A s 8:55-9:00

[8:55] Q&A

(ends 9:00 AM)

Oral Session 3: Vision Applications [8:00-9:00]

Oral s 8:00-8:15

[8:00] Partial success in closing the gap between human and machine vision

Q&A s 8:15-8:20

[8:15] Q&A

Oral s 8:20-8:35

[8:20] Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers

Q&A s 8:35-8:40

[8:35] Q&A

Oral s 8:40-8:55

[8:40] Volume Rendering of Neural Implicit Surfaces

Q&A s 8:55-9:00

[8:55] Q&A

(ends 9:00 AM)

8:30 a.m.

Demonstration:

Demonstrations 2

(ends 9:50 AM)

9 a.m.

Town Hall:

Town Hall

(ends 10:00 AM)

10 a.m.

10:30 a.m.

Affinity Workshop:

Queer in AI Workshop 2

(ends 1:30 PM)

11 a.m.

Affinity Workshop:

Indigenous in AI Workshop

(ends 2:30 PM)

noon

3 p.m.

Invited Talk (Posner Lecture):

Benign Overfitting

Peter Bartlett

(ends 4:30 PM)

4:30 p.m.

Poster Session 4 [4:30-6:00]

Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee

Scaling Neural Tangent Kernels via Sketching and Random Features

On the Value of Interaction and Function Approximation in Imitation Learning

A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning

TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification

Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection

ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees

Posterior Collapse and Latent Variable Non-identifiability

Neural Active Learning with Performance Guarantees

Variance-Aware Off-Policy Evaluation with Linear Function Approximation

SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL

Multiple Descent: Design Your Own Generalization Curve

Graph Neural Networks with Adaptive Residual

Differentiable Quality Diversity

Efficient Mirror Descent Ascent Methods for Nonsmooth Minimax Problems

CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum

Diversity Enhanced Active Learning with Strictly Proper Scoring Rules

Lifelong Domain Adaptation via Consolidated Internal Distribution

Counterbalancing Learning and Strategic Incentives in Allocation Markets

Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism

Towards Efficient and Effective Adversarial Training

Evaluating Efficient Performance Estimators of Neural Architectures

SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency

Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State

TNASP: A Transformer-based NAS Predictor with a Self-evolution Framework

Adversarial Attack Generation Empowered by Min-Max Optimization

Class-Disentanglement and Applications in Adversarial Detection and Defense

Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection

Topological Detection of Trojaned Neural Networks

A Law of Iterated Logarithm for Multi-Agent Reinforcement Learning

Particle Dual Averaging: Optimization of Mean Field Neural Network with Global Convergence Rate Analysis

Three Operator Splitting with Subgradients, Stochastic Gradients, and Adaptive Learning Rates

A Convergence Analysis of Gradient Descent on Graph Neural Networks

NAS-Bench-x11 and the Power of Learning Curves

How Modular should Neural Module Networks Be for Systematic Generalization?

On the Stochastic Stability of Deep Markov Models

CHIP: CHannel Independence-based Pruning for Compact Neural Networks

Federated Split Task-Agnostic Vision Transformer for COVID-19 CXR Diagnosis

Robust Optimization for Multilingual Translation with Imbalanced Data

Best of Both Worlds: Practical and Theoretically Optimal Submodular Maximization in Parallel

Permuton-induced Chinese Restaurant Process

Open Rule Induction

Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction

Revisiting Model Stitching to Compare Neural Representations

Sageflow: Robust Federated Learning against Both Stragglers and Adversaries

Bayesian Adaptation for Covariate Shift

Finite Sample Analysis of Average-Reward TD Learning and $Q$-Learning

Offline Reinforcement Learning as One Big Sequence Modeling Problem

Maximum Likelihood Training of Score-Based Diffusion Models

Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation

Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systems

USCO-Solver: Solving Undetermined Stochastic Combinatorial Optimization Problems

Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization

Breaking the Dilemma of Medical Image-to-image Translation

Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method

On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method

Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GAN

Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity

The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective

Exact marginal prior distributions of finite Bayesian neural networks

Spatiotemporal Joint Filter Decomposition in 3D Convolutional Neural Networks

On Effective Scheduling of Model-based Reinforcement Learning

Adaptable Agent Populations via a Generative Model of Policies

Deep Self-Dissimilarities as Powerful Visual Fingerprints

Sample Complexity Bounds for Active Ranking from Multi-wise Comparisons

Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention

RoMA: Robust Model Adaptation for Offline Model-based Optimization

Flexible Option Learning

Diverse Message Passing for Attribute with Heterophily

Greedy Approximation Algorithms for Active Sequential Hypothesis Testing

Stability and Deviation Optimal Risk Bounds with Convergence Rate $O(1/n)$

Blending Anti-Aliasing into Vision Transformer

Neural Regression, Representational Similarity, Model Zoology & Neural Taskonomy at Scale in Rodent Visual Cortex

A Topological Perspective on Causal Inference

Preconditioned Gradient Descent for Over-Parameterized Nonconvex Matrix Factorization

Provably efficient, succinct, and precise explanations

Bootstrapping the Error of Oja's Algorithm

Sub-Linear Memory: How to Make Performers SLiM

Nested Counterfactual Identification from Arbitrary Surrogate Experiments

HRFormer: High-Resolution Vision Transformer for Dense Predict

Forster Decomposition and Learning Halfspaces with Noise

Proper Value Equivalence

When Is Generalizable Reinforcement Learning Tractable?

Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spaces

Low-dimensional Structure in the Space of Language Representations is Reflected in Brain Responses

Locally Valid and Discriminative Prediction Intervals for Deep Learning Models

Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel

Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler

Diffusion Models Beat GANs on Image Synthesis

On Empirical Risk Minimization with Dependent and Heavy-Tailed Data

Gone Fishing: Neural Active Learning with Fisher Embeddings

Why Spectral Normalization Stabilizes GANs: Analysis and Improvements

Efficient Active Learning for Gaussian Process Classification by Error Reduction

Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation

How does a Neural Network's Architecture Impact its Robustness to Noisy Labels?

Parameterized Knowledge Transfer for Personalized Federated Learning

Online Learning in Periodic Zero-Sum Games

Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking

Generalization Bounds for (Wasserstein) Robust Optimization

Revenue maximization via machine learning with noisy data

Exploiting Data Sparsity in Secure Cross-Platform Social Recommendation

Emergent Discrete Communication in Semantic Spaces

Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path

Lower and Upper Bounds on the Pseudo-Dimension of Tensor Network Models

What Makes Multi-Modal Learning Better than Single (Provably)

Selective Sampling for Online Best-arm Identification

Multi-task Learning of Order-Consistent Causal Graphs

Optimal prediction of Markov chains with and without spectral gap

Continuous Doubly Constrained Batch Reinforcement Learning

Tensor decompositions of higher-order correlations by nonlinear Hebbian plasticity

Shifted Chunk Transformer for Spatio-Temporal Representational Learning

Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification

Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models

Coresets for Classification – Simplified and Strengthened

Hyperparameter Tuning is All You Need for LISTA

A Geometric Structure of Acceleration and Its Role in Making Gradients Small Fast

Fast Federated Learning in the Presence of Arbitrary Device Unavailability

SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning

FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective

Pretraining Representations for Data-Efficient Reinforcement Learning

Universal Approximation Using Well-Conditioned Normalizing Flows

Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias

MST: Masked Self-Supervised Transformer for Visual Representation

Demystifying and Generalizing BinaryConnect

Representing Long-Range Context for Graph Neural Networks with Global Attention

Learning Student-Friendly Teacher Networks for Knowledge Distillation

Channel Permutations for N:M Sparsity

Progressive Coordinate Transforms for Monocular 3D Object Detection

For high-dimensional hierarchical models, consider exchangeability of effects across covariates instead of across datasets

Provably Faster Algorithms for Bilevel Optimization

Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimation

Class-Incremental Learning via Dual Augmentation

Bayesian Optimization of Function Networks

Look at What I’m Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos

Controlled Text Generation as Continuous Optimization with Multiple Constraints

Topic Modeling Revisited: A Document Graph-based Neural Network Perspective

Robust Compressed Sensing MRI with Deep Generative Priors

Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles

Uncertain Decisions Facilitate Better Preference Learning

Probability Paths and the Structure of Predictions over Time

Deep Extended Hazard Models for Survival Analysis

A nonparametric method for gradual change problems with statistical guarantees

Active 3D Shape Reconstruction from Vision and Touch

Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning

An Axiomatic Theory of Provably-Fair Welfare-Centric Machine Learning

Neural Symplectic Form: Learning Hamiltonian Equations on General Coordinate Systems

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting

On the Representation Power of Set Pooling Networks

Formalizing the Generalization-Forgetting Trade-off in Continual Learning

Sliced Mutual Information: A Scalable Measure of Statistical Dependence

Emergent Communication under Varying Sizes and Connectivities

Regret Minimization Experience Replay in Off-Policy Reinforcement Learning

Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning

Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers

Deep Markov Factor Analysis: Towards Concurrent Temporal and Spatial Analysis of fMRI Data

Teaching an Active Learner with Contrastive Examples

Manipulating SGD with Data Ordering Attacks

Structure learning in polynomial time: Greedy algorithms, Bregman information, and exponential families

Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning

Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations

ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs

Fine-Grained Zero-Shot Learning with DNA as Side Information

Referring Transformer: A One-step Approach to Multi-task Visual Grounding

Chasing Sparsity in Vision Transformers: An End-to-End Exploration

Multi-Step Budgeted Bayesian Optimization with Unknown Evaluation Costs

Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective

Improved Learning Rates of a Functional Lasso-type SVM with Sparse Multi-Kernel Representation

A Surrogate Objective Framework for Prediction+Programming with Soft Constraints

Ultrahyperbolic Neural Networks

Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration

Pseudo-Spherical Contrastive Divergence

A Variational Perspective on Diffusion-Based Generative Models and Score Matching

Does Preprocessing Help Training Over-parameterized Neural Networks?

Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model

Change Point Detection via Multivariate Singular Spectrum Analysis

Optimal Sketching for Trace Estimation

Coupled Gradient Estimators for Discrete Latent Variables

Second-Order Neural ODE Optimizer

Estimating High Order Gradients of the Data Distribution by Denoising

Collapsed Variational Bounds for Bayesian Neural Networks

Batch Multi-Fidelity Bayesian Optimization with Deep Auto-Regressive Networks

Learning with Holographic Reduced Representations

On the Second-order Convergence Properties of Random Search Methods

A Max-Min Entropy Framework for Reinforcement Learning

Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games

Sequence-to-Sequence Learning with Latent Neural Grammars

Towards a Unified Information-Theoretic Framework for Generalization

Pragmatic Image Compression for Human-in-the-Loop Decision-Making

Characterizing possible failure modes in physics-informed neural networks

A Stochastic Newton Algorithm for Distributed Convex Optimization

The staircase property: How hierarchical structure can guide deep learning

Scaling Up Exact Neural Network Compression by ReLU Stability

Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture

Localization with Sampling-Argmax

Gauge Equivariant Transformer

DeepSITH: Efficient Learning via Decomposition of What and When Across Time Scales

A generative nonparametric Bayesian model for whole genomes

Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis

Efficient constrained sampling via the mirror-Langevin algorithm

ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias

Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme

MobILE: Model-Based Imitation Learning From Observation Alone

On the Expected Complexity of Maxout Networks

Gradient-based Editing of Memory Examples for Online Task-free Continual Learning

Learning Distilled Collaboration Graph for Multi-Agent Perception

Corruption Robust Active Learning

Program Synthesis Guided Reinforcement Learning for Partially Observed Environments

Soft Calibration Objectives for Neural Networks

A Geometric Analysis of Neural Collapse with Unconstrained Features

Autobahn: Automorphism-based Graph Neural Nets

Focal Attention for Long-Range Interactions in Vision Transformers

Rectangular Flows for Manifold Learning

Continual Learning via Local Module Composition

Local plasticity rules can learn deep representations using self-supervised contrastive predictions

MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction

(ends 6:00 PM)

6 p.m.

Affinity Workshop:

WiML Workshop 1

(ends 11:00 PM)

6:30 p.m.

11 p.m.

Invited Talk:

Optimal Transport: Past, Present, and Future

Alessio Figalli

(ends 12:30 AM)

THU 9 DEC

12:30 a.m.

Poster Session 5 [12:30-2:00]

From Canonical Correlation Analysis to Self-supervised Graph Neural Networks

Fast Tucker Rank Reduction for Non-Negative Tensors Using Mean-Field Approximation

ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis

See More for Scene: Pairwise Consistency Learning for Scene Classification

PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning

Faster Non-asymptotic Convergence for Double Q-learning

Manifold Topology Divergence: a Framework for Comparing Data Manifolds.

Diversity Matters When Learning From Ensembles

What can linearized neural networks actually say about generalization?

Integrating Tree Path in Transformer for Code Representation

Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems

Scalable Quasi-Bayesian Inference for Instrumental Variable Regression

Learning interaction rules from multi-animal trajectories via augmented behavioral models

Overlapping Spaces for Compact Graph Representations

Tactical Optimism and Pessimism for Deep Reinforcement Learning

CANITA: Faster Rates for Distributed Convex Optimization with Communication Compression

Co-evolution Transformer for Protein Contact Prediction

Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning

Adversarial Reweighting for Partial Domain Adaptation

Anti-Backdoor Learning: Training Clean Models on Poisoned Data

Necessary and sufficient graphical conditions for optimal adjustment sets in causal graphical models with hidden variables

Uncertainty-Driven Loss for Single Image Super-Resolution

NEO: Non Equilibrium Sampling on the Orbits of a Deterministic Transform

Deep Contextual Video Compression

Graphical Models in Heavy-Tailed Markets

Hessian Eigenspectra of More Realistic Nonlinear Models

Counterexample Guided RL Policy Refinement Using Bayesian Optimization

LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes

Intermediate Layers Matter in Momentum Contrastive Self Supervised Learning

Analyzing the Generalization Capability of SGLD Using Properties of Gaussian Channels

One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective

Width-based Lookaheads with Learnt Base Policies and Heuristics Over the Atari-2600 Benchmark

Universal Off-Policy Evaluation

Learning Interpretable Decision Rule Sets: A Submodular Optimization Approach

Transformers Generalize DeepSets and Can be Extended to Graphs & Hypergraphs

CorticalFlow: A Diffeomorphic Mesh Transformer Network for Cortical Surface Reconstruction

Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learning

Gradient Inversion with Generative Image Prior

Truncated Marginal Neural Ratio Estimation

Habitat 2.0: Training Home Assistants to Rearrange their Habitat

Oracle Complexity in Nonsmooth Nonconvex Optimization

The Complexity of Bayesian Network Learning: Revisiting the Superstructure

Subgoal Search For Complex Reasoning Tasks

Do Different Tracking Tasks Require Different Appearance Models?

Near-Optimal Multi-Perturbation Experimental Design for Causal Structure Learning

Continuous Mean-Covariance Bandits

Solving Soft Clustering Ensemble via $k$-Sparse Discrete Wasserstein Barycenter

The Adaptive Doubly Robust Estimator and a Paradox Concerning Logging Policy

Adaptive Data Augmentation on Temporal Graphs

Distributional Reinforcement Learning for Multi-Dimensional Reward Functions

KS-GNN: Keywords Search over Incomplete Graphs via Graphs Neural Network

There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning

TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification

INDIGO: GNN-Based Inductive Knowledge Graph Completion Using Pair-Wise Encoding

Robustifying Algorithms of Learning Latent Trees with Vector Variables

Preserved central model for faster bidirectional compression in distributed settings

Iterative Causal Discovery in the Possible Presence of Latent Confounders and Selection Bias

A Bayesian-Symbolic Approach to Reasoning and Learning in Intuitive Physics

Associating Objects with Transformers for Video Object Segmentation

Lip to Speech Synthesis with Visual Context Attentional GAN

Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis

Dual Progressive Prototype Network for Generalized Zero-Shot Learning

Partition-Based Formulations for Mixed-Integer Optimization of Trained ReLU Neural Networks

A Constant Approximation Algorithm for Sequential Random-Order No-Substitution k-Median Clustering

Repulsive Deep Ensembles are Bayesian

Hypergraph Propagation and Community Selection for Objects Retrieval

Information Directed Reward Learning for Reinforcement Learning

How Tight Can PAC-Bayes be in the Small Data Regime?

Understanding Partial Multi-Label Learning via Mutual Information

E(n) Equivariant Normalizing Flows

An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias

Learning to Learn Graph Topologies

Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP

EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback

Kernel Functional Optimisation

Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning

CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation

Automatic Data Augmentation for Generalization in Reinforcement Learning

Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems

A$^2$-Net: Learning Attribute-Aware Hash Codes for Large-Scale Fine-Grained Image Retrieval

Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning

iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder

History Aware Multimodal Transformer for Vision-and-Language Navigation

No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data

Learning to Combine Per-Example Solutions for Neural Program Synthesis

Refined Learning Bounds for Kernel and Approximate $k$-Means

Conformal Time-series Forecasting

Conformal Prediction using Conditional Histograms

Network-to-Network Regularization: Enforcing Occam's Razor to Improve Generalization

Spherical Motion Dynamics: Learning Dynamics of Normalized Neural Network using SGD and Weight Decay

Efficient Learning of Discrete-Continuous Computation Graphs

Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima

Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks

Asynchronous Decentralized SGD with Quantized and Local Updates

Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret

Sim and Real: Better Together

Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions

Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases

BooVI: Provably Efficient Bootstrapped Value Iteration

Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective

Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networks

An Even More Optimal Stochastic Optimization Algorithm: Minibatching and Interpolation Learning

A Gradient Method for Multilevel Optimization

A Provably Efficient Sample Collection Strategy for Reinforcement Learning

Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization

The Complexity of Sparse Tensor PCA

Rethinking gradient sparsification as total error minimization

Personalized Federated Learning With Gaussian Processes

Parameter-free HE-friendly Logistic Regression

Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond

Going Beyond Linear RL: Sample Efficient Neural Function Approximation

CATs: Cost Aggregation Transformers for Visual Correspondence

Generalizable Multi-linear Attention Network

Denoising Normalizing Flow

ROI Maximization in Stochastic Online Decision-Making

Twins: Revisiting the Design of Spatial Attention in Vision Transformers

Causal Identification with Matrix Equations

Model-Based Reinforcement Learning via Imagination with Derived Memory

Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment

Low-Fidelity Video Encoder Optimization for Temporal Action Localization

Compositional Reinforcement Learning from Logical Specifications

Latent Matters: Learning Deep State-Space Models

On the Estimation Bias in Double Q-Learning

Scalable Bayesian GPFA with automatic relevance determination and discrete noise models

Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation

Making the most of your day: online learning for optimal allocation of time

Subquadratic Overparameterization for Shallow Neural Networks

Deep Conditional Gaussian Mixture Model for Constrained Clustering

What’s a good imputation to predict with missing values?

Numerical Composition of Differential Privacy

Sparse Spiking Gradient Descent

Rethinking Calibration of Deep Neural Networks: Do Not Be Afraid of Overconfidence

Learning Stable Deep Dynamics Models for Partially Observed or Delayed Dynamical Systems

Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data

Beyond Smoothness: Incorporating Low-Rank Analysis into Nonparametric Density Estimation

Identifiability in inverse reinforcement learning

A Probabilistic State Space Model for Joint Inference from Differential Equations and Data

Global Convergence of Online Optimization for Nonlinear Model Predictive Control

Variational Bayesian Optimistic Sampling

Cross-modal Domain Adaptation for Cost-Efficient Visual Reinforcement Learning

Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote

Proportional Participatory Budgeting with Additive Utilities

MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data

Rectifying the Shortcut Learning of Background for Few-Shot Learning

Uncertainty Calibration for Ensemble-Based Debiasing Methods

ToAlign: Task-Oriented Alignment for Unsupervised Domain Adaptation

PortaSpeech: Portable and High-Quality Generative Text-to-Speech

BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation

Rethinking the Variational Interpretation of Accelerated Optimization Methods

On the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms

Fast Routing under Uncertainty: Adaptive Learning in Congestion Games via Exponential Weights

Online Meta-Learning via Learning with Layer-Distributed Memory

Actively Identifying Causal Effects with Latent Variables Given Only Response Variable Observable

Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models

Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs

Doubly Robust Thompson Sampling with Linear Payoffs

Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework

Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic

Gradient Driven Rewards to Guarantee Fairness in Collaborative Machine Learning

Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation

Global-aware Beam Search for Neural Abstractive Summarization

HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning

Low-Rank Subspaces in GANs

Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels

Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent

Graph Differentiable Architecture Search with Structure Learning

Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation

Discerning Decision-Making Process of Deep Neural Networks with Hierarchical Voting Transformation

De-randomizing MCMC dynamics with the diffusion Stein operator

Deep Bandits Show-Off: Simple and Efficient Exploration with Deep Networks

Towards Sample-Optimal Compressive Phase Retrieval with Sparse and Generative Priors

Structure-Aware Random Fourier Kernel for Graphs

Post-Training Sparsity-Aware Quantization

The Implicit Bias of Minima Stability: A View from Function Space

Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification

Learning curves of generic features maps for realistic datasets with a teacher-student model

It Has Potential: Gradient-Driven Denoisers for Convergent Solutions to Inverse Problems

IRM—when it works and when it doesn't: A test case of natural language inference

Self-Supervised Learning Disentangled Group Representation as Feature

Decentralized Q-learning in Zero-sum Markov Games

Agent Modelling under Partial Observability for Deep Reinforcement Learning

PSD Representations for Effective Probability Models

Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach

Stochastic bandits with groups of similar arms.

Boost Neural Networks by Checkpoints

Model Selection for Bayesian Autoencoders

Knowledge-Adaptation Priors

Time-independent Generalization Bounds for SGLD in Non-convex Settings

On learning sparse vectors from mixture of responses

Adder Attention for Vision Transformer

Asynchronous Decentralized Online Learning

On the Provable Generalization of Recurrent Neural Networks

STORM+: Fully Adaptive SGD with Recursive Momentum for Nonconvex Optimization

Meta Internal Learning

Precise characterization of the prior predictive distribution of deep ReLU networks

Variational Multi-Task Learning with Gumbel-Softmax Priors

Generalization Guarantee of SGD for Pairwise Learning

Task-Adaptive Neural Network Search with Meta-Contrastive Learning

Efficient and Local Parallel Random Walks

Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model

Integrated Latent Heterogeneity and Invariance Learning in Kernel Space

Beyond the Signs: Nonparametric Tensor Completion via Sign Series

Disentangled Contrastive Learning on Graphs

DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks

Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs

SWAD: Domain Generalization by Seeking Flat Minima

Bandits with many optimal arms

Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution

SSAL: Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection

Coresets for Time Series Clustering

Cycle Self-Training for Domain Adaptation

Stochastic Anderson Mixing for Nonconvex Stochastic Optimization

A Note on Sparse Generalized Eigenvalue Problem

RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents

Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication

Active Assessment of Prediction Services as Accuracy Surface Over Attribute Combinations

PartialFed: Cross-Domain Personalized Federated Learning via Partial Initialization

Multi-Label Learning with Pairwise Relevance Ordering

MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanisms

Efficient Combination of Rematerialization and Offloading for Training DNNs

Well-tuned Simple Nets Excel on Tabular Datasets

POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples

Combinatorial Pure Exploration with Bottleneck Reward Function

Variational Continual Bayesian Meta-Learning

Understanding Bandits with Graph Feedback

Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation

Modular Gaussian Processes for Transfer Learning

Causal Bandits with Unknown Graph Structure

IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers

Differentially Private Multi-Armed Bandits in the Shuffle Model

Not All Low-Pass Filters are Robust in Graph Convolutional Networks

Constrained Optimization to Train Neural Networks on Critical and Under-Represented Classes

Offline Constrained Multi-Objective Reinforcement Learning via Pessimistic Dual Value Iteration

Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations

Identification of the Generalized Condorcet Winner in Multi-dueling Bandits

Re-ranking for image retrieval and transductive few-shot classification

Instance-optimal Mean Estimation Under Differential Privacy

Optimizing Information-theoretical Generalization Bound via Anisotropic Noise of SGLD

Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning

Effective Meta-Regularization by Kernelized Proximal Regularization

Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation

Artistic Style Transfer with Internal-external Learning and Contrastive Learning

Curriculum Disentangled Recommendation with Noisy Multi-feedback

Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning

Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks

GRIN: Generative Relation and Intention Network for Multi-agent Trajectory Prediction

Semialgebraic Representation of Monotone Deep Equilibrium Models and Applications to Certification

Towards Understanding Why Lookahead Generalizes Better Than SGD and Beyond

Dynamic Resolution Network

Stochastic Multi-Armed Bandits with Control Variates

Faster Algorithms and Constant Lower Bounds for the Worst-Case Expected Error

ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers

Independent mechanism analysis, a new concept?

Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning

Stylized Dialogue Generation with Multi-Pass Dual Learning

Entropy-based adaptive Hamiltonian Monte Carlo

Few-Round Learning for Federated Learning

Learning a Single Neuron with Bias Using Gradient Descent

Powerpropagation: A sparsity inducing weight reparameterisation

DRONE: Data-aware Low-rank Compression for Large NLP Models

Activation Sharing with Asymmetric Paths Solves Weight Transport Problem without Bidirectional Connection

Robust Generalization despite Distribution Shift via Minimum Discriminating Information

Batched Thompson Sampling

Error Compensated Distributed SGD Can Be Accelerated

Meta-Learning for Relative Density-Ratio Estimation

Unlabeled Principal Component Analysis

(ends 2:00 AM)

5 a.m.

7 a.m.

Invited Talk (Interview):

A Conversation on Human and Machine Intelligence

Daniel Kahneman

(ends 8:30 AM)

8:30 a.m.

Demonstration:

Demonstrations 3

(ends 9:35 AM)

Datasets and Benchmarks:

Dataset and Benchmark Poster Session 3

(ends 10:00 AM)

Poster Session 6 [8:30-10:00]

DRIVE: One-bit Distributed Mean Estimation

Differentiable Unsupervised Feature Selection based on a Gated Laplacian

Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA

End-to-End Weak Supervision

Probabilistic Attention for Interactive Segmentation

Noisy Recurrent Neural Networks

Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning

Fast Pure Exploration via Frank-Wolfe

Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition

Group Equivariant Subsampling

Curriculum Offline Imitating Learning

Roto-translated Local Coordinate Frames For Interacting Dynamical Systems

A/B Testing for Recommender Systems in a Two-sided Marketplace

Retiring Adult: New Datasets for Fair Machine Learning

Scalable Inference of Sparsely-changing Gaussian Markov Random Fields

Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning

Fair Classification with Adversarial Perturbations

Distributed Saddle-Point Problems Under Data Similarity

Analyzing the Confidentiality of Undistillable Teachers in Knowledge Distillation

Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions

Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition

TokenLearner: Adaptive Space-Time Tokenization for Videos

Shape As Points: A Differentiable Poisson Solver

Outcome-Driven Reinforcement Learning via Variational Inference

Exact Privacy Guarantees for Markov Chain Implementations of the Exponential Mechanism with Artificial Atoms

Settling the Variance of Multi-Agent Policy Gradients

Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation

A Central Limit Theorem for Differentially Private Query Answering

Federated Multi-Task Learning under a Mixture of Distributions

Recurrent Bayesian Classifier Chains for Exact Multi-Label Classification

Good Classification Measures and How to Find Them

Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs

Risk-Aware Transfer in Reinforcement Learning using Successor Features

Conformal Bayesian Computation

When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting

XCiT: Cross-Covariance Image Transformers

Directed Probabilistic Watershed

Local policy search with Bayesian optimization

On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay

Boosted CVaR Classification

Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation

Robust and Decomposable Average Precision for Image Retrieval

Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess

Efficient hierarchical Bayesian inference for spatio-temporal regression models in neuroimaging

Topological Attention for Time Series Forecasting

Learning to Synthesize Programs as Interpretable and Generalizable Policies

Lattice partition recovery with dyadic CART

Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality

Neural Trees for Learning on Graphs

Joint Inference for Neural Network Depth and Dropout Regularization

Least Square Calibration for Peer Reviews

Faster Neural Network Training with Approximate Tensor Operations

Breaking the centralized barrier for cross-device federated learning

TAAC: Temporally Abstract Actor-Critic for Continuous Control

Hyperbolic Busemann Learning with Ideal Prototypes

Multimodal Few-Shot Learning with Frozen Language Models

(Almost) Free Incentivized Exploration from Decentralized Learning Agents

MCMC Variational Inference via Uncorrected Hamiltonian Annealing

On the Importance of Gradients for Detecting Distributional Shifts in the Wild

Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods

Understanding End-to-End Model-Based Reinforcement Learning Methods as Implicit Parameterization

Towards robust vision by multi-task learning on monkey visual cortex

Perturb-and-max-product: Sampling and learning in discrete energy-based models

Mitigating Covariate Shift in Imitation Learning via Offline Data With Partial Coverage

CAFE: Catastrophic Data Leakage in Vertical Federated Learning

Risk-Averse Bayes-Adaptive Reinforcement Learning

Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection

Gradient Starvation: A Learning Proclivity in Neural Networks

Optimality and Stability in Federated Learning: A Game-theoretic Approach

Privately Learning Subspaces

Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs

Beltrami Flow and Neural Diffusion on Graphs

Adaptive Conformal Inference Under Distribution Shift

Periodic Activation Functions Induce Stationarity

NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM

Reliable Decisions with Threshold Calibration

Replay-Guided Adversarial Environment Design

Improving Conditional Coverage via Orthogonal Quantile Regression

Minimizing Polarization and Disagreement in Social Networks via Link Recommendation

Optimal Rates for Random Order Online Optimization

Circa: Stochastic ReLUs for Private Deep Learning

A Gang of Adversarial Bandits

Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent

Automatic Symmetry Discovery with Lie Algebra Convolutional Network

Learning to See by Looking at Noise

Explicit loss asymptotics in the gradient descent training of neural networks

Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling

Aligned Structured Sparsity Learning for Efficient Image Super-Resolution

Online Knapsack with Frequency Predictions

Distributed Principal Component Analysis with Limited Communication

Estimating the Long-Term Effects of Novel Treatments

G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators

Multiclass Boosting and the Cost of Weak Learning

Hyperparameter Optimization Is Deceiving Us, and How to Stop It

Framing RNN as a kernel method: A neural ODE approach

Statistical Query Lower Bounds for List-Decodable Linear Regression

Unsupervised Motion Representation Learning with Capsule Autoencoders

On the Theory of Reinforcement Learning with Once-per-Episode Feedback

Locally private online change point detection

Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation

Approximate Decomposable Submodular Function Minimization for Cardinality-Based Components

On the Out-of-distribution Generalization of Probabilistic Image Modelling

PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations

Privately Learning Mixtures of Axis-Aligned Gaussians

Efficient Training of Retrieval Models using Negative Cache

Mixture weights optimisation for Alpha-Divergence Variational Inference

Combining Human Predictions with Model Probabilities via Confusion Matrices and Calibration

Offline Meta Reinforcement Learning -- Identifiability Challenges and Effective Data Collection Strategies

Representation Learning for Event-based Visuomotor Policies

Representation Learning Beyond Linear Prediction Functions

Support vector machines and linear regression coincide with very high-dimensional features

The Skellam Mechanism for Differentially Private Federated Learning

Differentially Private n-gram Extraction

Parameter Inference with Bifurcation Diagrams

Similarity and Matching of Neural Network Representations

The Lazy Online Subgradient Algorithm is Universal on Strongly Convex Domains

Searching for Efficient Transformers for Language Modeling

Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets

Landscape analysis of an improved power method for tensor decomposition

Probabilistic Forecasting: A Level-Set Approach

Speech-T: Transducer for Text to Speech and Beyond

Neural Tangent Kernel Maximum Mean Discrepancy

Evaluating Gradient Inversion Attacks and Defenses in Federated Learning

Towards Tight Communication Lower Bounds for Distributed Optimisation

Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification

SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation

Distribution-free inference for regression: discrete, continuous, and in between

NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problem

LEADS: Learning Dynamical Systems that Generalize Across Environments

Storchastic: A Framework for General Stochastic Automatic Differentiation

Improved Regret Bounds for Tracking Experts with Memory

Grammar-Based Grounded Lexicon Learning

Covariance-Aware Private Mean Estimation Without Private Covariance Estimation

A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models

GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement

Learning Markov State Abstractions for Deep Reinforcement Learning

Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures

Exploring Social Posterior Collapse in Variational Autoencoder for Interaction Modeling

Ensembling Graph Predictions for AMR Parsing

On the interplay between data structure and loss function in classification problems

Mixture Proportion Estimation and PU Learning:A Modern Approach

Two-sided fairness in rankings via Lorenz dominance

Machine Learning for Variance Reduction in Online Experiments

Inverse Problems Leveraging Pre-trained Contrastive Representations

Equilibrium Refinement for the Age of Machines: The One-Sided Quasi-Perfect Equilibrium

Asynchronous Stochastic Optimization Robust to Arbitrary Delays

General Nonlinearities in SO(2)-Equivariant CNNs

Attention over Learned Object Embeddings Enables Complex Visual Reasoning

Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settings

Private and Non-private Uniformity Testing for Ranking Data

Compositional Transformers for Scene Generation

$(\textrm{Implicit})^2$: Implicit Layers for Implicit Representations

Local Differential Privacy for Regret Minimization in Reinforcement Learning

Asymptotics of the Bootstrap via Stability with Applications to Inference with Model Selection

Dynamic influence maximization

Object-Centric Representation Learning with Generative Spatial-Temporal Factorization

Stochastic Bias-Reduced Gradient Methods

Beyond Pinball Loss: Quantile Methods for Calibrated Uncertainty Quantification

Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications

Oracle-Efficient Regret Minimization in Factored MDPs with Unknown Structure

Federated Reconstruction: Partially Local Federated Learning

Score-based Generative Modeling in Latent Space

Online Adaptation to Label Distribution Shift

Faster proximal algorithms for matrix optimization using Jacobi-based eigenvalue methods

Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP

Exploring Cross-Video and Cross-Modality Signals for Weakly-Supervised Audio-Visual Video Parsing

Littlestone Classes are Privately Online Learnable

Learning to Generate Visual Questions with Noisy Supervision

Fixes That Fail: Self-Defeating Improvements in Machine-Learning Systems

Learning in two-player zero-sum partially observable Markov games with perfect recall

ATISS: Autoregressive Transformers for Indoor Scene Synthesis

On The Structure of Parametric Tournaments with Application to Ranking from Pairwise Comparisons

Explaining heterogeneity in medial entorhinal cortex with task-driven neural networks

FACMAC: Factored Multi-Agent Centralised Policy Gradients

Non-asymptotic Error Bounds for Bidirectional GANs

Causal Navigation by Continuous-time Neural Networks

Learning with User-Level Privacy

Don’t Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence

D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation

Continual Auxiliary Task Learning

Towards optimally abstaining from prediction with OOD test examples

FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout

Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings

Glance-and-Gaze Vision Transformer

Stochastic $L^\natural$-convex Function Minimization

Exploiting Opponents Under Utility Constraints in Sequential Games

Beyond Bandit Feedback in Online Multiclass Classification

Controllable and Compositional Generation with Latent-Space Energy-Based Models

Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning

Bayesian Bellman Operators

Tree in Tree: from Decision Trees to Decision Graphs

Test-time Collective Prediction

Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers

Safe Reinforcement Learning with Natural Language Constraints

Logarithmic Regret in Feature-based Dynamic Pricing

An Online Riemannian PCA for Stochastic Canonical Correlation Analysis

Last-iterate Convergence in Extensive-Form Games

Fair Clustering Under a Bounded Cost

Linear and Kernel Classification in the Streaming Model: Improved Bounds for Heavy Hitters

Collaborating with Humans without Human Data

Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients

Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent

Data driven semi-supervised learning

Characterizing the risk of fairwashing

PettingZoo: Gym for Multi-Agent Reinforcement Learning

Decision Transformer: Reinforcement Learning via Sequence Modeling

CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks

Who Leads and Who Follows in Strategic Classification?

Label Disentanglement in Partition-based Extreme Multilabel Classification

Neural Algorithmic Reasoners are Implicit Planners

Unsupervised Learning of Compositional Energy Concepts

FLEX: Unifying Evaluation for Few-Shot NLP

Online Control of Unknown Time-Varying Dynamical Systems

Contrastive Reinforcement Learning of Symbolic Reasoning Domains

Assessing Fairness in the Presence of Missing Data

Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi

Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations

Adaptive Machine Unlearning

EditGAN: High-Precision Semantic Image Editing

Differentiable Multiple Shooting Layers

Neural Bootstrapper

Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems

Learning-Augmented Dynamic Power Management with Multiple States via New Ski Rental Bounds

Adversarial Neuron Pruning Purifies Backdoored Deep Models

Scalable Online Planning via Reinforcement Learning Fine-Tuning

Adversarial Regression with Doubly Non-negative Weighting Matrices

Privately Publishable Per-instance Privacy

Boosting with Multiple Sources

Dense Keypoints via Multiview Supervision

Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficial

PreferenceNet: Encoding Human Preferences in Auction Design with Deep Learning

Distributed Machine Learning with Sparse Heterogeneous Data

Training Over-parameterized Models with Non-decomposable Objectives

Reinforcement learning for optimization of variational quantum circuit architectures

A Unified Approach to Fair Online Learning via Blackwell Approachability

Towards Multi-Grained Explainability for Graph Neural Networks

Neural Distance Embeddings for Biological Sequences

On the Sample Complexity of Learning under Geometric Stability

Federated Graph Classification over Non-IID Graphs

SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning

Label-Imbalanced and Group-Sensitive Classification under Overparameterization

Adapting to function difficulty and growth conditions in private optimization

Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity

Container: Context Aggregation Networks

Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing

Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning

Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering

ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction

How to transfer algorithmic reasoning knowledge to learn new algorithms?

Fast and Memory Efficient Differentially Private-SGD via JL Projections

Pipeline Combinators for Gradual AutoML

CogView: Mastering Text-to-Image Generation via Transformers

Nonuniform Negative Sampling and Log Odds Correction with Rare Events Data

User-Level Differentially Private Learning via Correlated Sampling

Practical Large-Scale Linear Programming using Primal-Dual Hybrid Gradient

On Large-Cohort Training for Federated Learning

Interesting Object, Curious Agent: Learning Task-Agnostic Exploration

Deep Learning on a Data Diet: Finding Important Examples Early in Training

Relaxed Marginal Consistency for Differentially Private Query Answering

Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks

Heavy Ball Momentum for Conditional Gradient

Disrupting Deep Uncertainty Estimation Without Harming Accuracy

An online passive-aggressive algorithm for difference-of-squares classification

Learning to Predict Trustworthiness with Steep Slope Loss

NeRV: Neural Representations for Videos

Surrogate Regret Bounds for Polyhedral Losses

Hierarchical Reinforcement Learning with Timed Subgoals

Fair Scheduling for Time-dependent Resources

Functional Variational Inference based on Stochastic Process Generators

Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models

Best-case lower bounds in online learning

Photonic Differential Privacy with Direct Feedback Alignment

NeuroMLR: Robust & Reliable Route Recommendation on Road Networks

DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks

Twice regularized MDPs and the equivalence between robustness and regularization

Contextual Recommendations and Low-Regret Cutting-Plane Algorithms

Reinforcement Learning Enhanced Explainer for Graph Neural Networks

Double/Debiased Machine Learning for Dynamic Treatment Effects

Local Disentanglement in Variational Auto-Encoders Using Jacobian $L_1$ Regularization

Average-Reward Learning and Planning with Options

Learning in Non-Cooperative Configurable Markov Decision Processes

Causal Influence Detection for Improving Efficiency in Reinforcement Learning

Multiclass versus Binary Differentially Private PAC Learning

Closing the loop in medical decision support by understanding clinical decision-making: A case study on organ transplantation

Fair Sparse Regression with Clustering: An Invex Relaxation for a Combinatorial Problem

The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization

Learning Semantic Representations to Verify Hardware Designs

Sampling with Trusthworthy Constraints: A Variational Gradient Framework

MERLOT: Multimodal Neural Script Knowledge Models

Fast Approximate Dynamic Programming for Infinite-Horizon Markov Decision Processes

Mixability made efficient: Fast online multiclass logistic regression

Analytic Insights into Structure and Rank of Neural Network Hessian Maps

Fair Algorithms for Multi-Agent Multi-Armed Bandits

Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation

Learning to Schedule Heuristics in Branch and Bound

Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates

RL for Latent MDPs: Regret Guarantees and a Lower Bound

Adaptive Sampling for Minimax Fair Classification

Planning from Pixels in Environments with Combinatorially Hard Search Spaces

Locally differentially private estimation of functionals of discrete distributions

Asymptotics of representation learning in finite Bayesian neural networks

Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback

Learning Hard Optimization Problems: A Data Generation Perspective

Canonical Capsules: Self-Supervised Capsules in Canonical Pose

Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning

Never Go Full Batch (in Stochastic Convex Optimization)

Multi-Scale Representation Learning on Proteins

Consistent Estimation for PCA and Sparse Regression with Oblivious Outliers

Fair Sortition Made Transparent

Post-processing for Individual Fairness

OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization

Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis

Implicit Generative Copulas

Towards Context-Agnostic Learning Using Synthetic Data

Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers

A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition

Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization

Online false discovery rate control for anomaly detection in time series

Improving Compositionality of Neural Networks by Decoding Representations to Inputs

Are Transformers more robust than CNNs?

Representation Costs of Linear Neural Networks: Analysis and Design

Deep Learning with Label Differential Privacy

NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction

Improved Guarantees for Offline Stochastic Matching via new Ordered Contention Resolution Schemes

Online Market Equilibrium with Application to Fair Division

Label Noise SGD Provably Prefers Flat Global Minimizers

Instance-Conditioned GAN

Differentially Private Empirical Risk Minimization under the Fairness Lens

Near-Optimal No-Regret Learning in General Games

Improving Anytime Prediction with Parallel Cascaded Networks and a Temporal-Difference Loss

Local Hyper-Flow Diffusion

Unsupervised Speech Recognition

Individual Privacy Accounting via a Rényi Filter

Logarithmic Regret from Sublinear Hints

On the Sample Complexity of Privately Learning Axis-Aligned Rectangles

Towards Best-of-All-Worlds Online Learning with Feedback Graphs

Scalars are universal: Equivariant machine learning, structured like classical physics

Deep Networks Provably Classify Data on Curves

Differentially Private Sampling from Distributions

Can multi-label classification networks know what they don’t know?

Margin-Independent Online Multiclass Learning via Convex Geometry

Renyi Differential Privacy of The Subsampled Shuffle Model In Distributed Learning

SLOE: A Faster Method for Statistical Inference in High-Dimensional Logistic Regression

Federated-EM with heterogeneity mitigation and variance reduction

Robust Allocations with Diversity Constraints

Shaping embodied agent behavior with activity-context priors from egocentric video

Adjusting for Autocorrelated Errors in Neural Networks for Time Series

Deep Explicit Duration Switching Models for Time Series

Shared Independent Component Analysis for Multi-Subject Neuroimaging

Provable Representation Learning for Imitation with Contrastive Fourier Features

Streaming Linear System Identification with Reverse Experience Replay

Are My Deep Learning Systems Fair? An Empirical Study of Fixed-Seed Training

A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum

Coresets for Decision Trees of Signals

Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learning

(ends 10:00 AM)

10 a.m.

Competition:

Competition Track Day 3: Overviews + Breakout Sessions

(ends 3:04 PM)

Roundtable:

How Copyright Shapes Your Datasets and What To Do About It

(ends 11:00 AM)

11 a.m.

Datasets and Benchmarks:

Dataset and Benchmark Symposium

(ends 2:00 PM)

3 p.m.

Invited Talk:

Gender, Allyship & Public Interest Technology

Meredith Broussard

(ends 4:30 PM)

4:30 p.m.

Poster Session 7 [4:30-6:00]

Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update

Episodic Multi-agent Reinforcement Learning with Curiosity-driven Exploration

RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem

VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization

SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients

Differentially Private Federated Bayesian Optimization with Distributed Exploration

Robust Visual Reasoning via Language Guided Neural Module Networks

Stochastic optimization under time drift: iterate averaging, step-decay schedules, and high probability guarantees

Learnable Fourier Features for Multi-dimensional Spatial Positional Encoding

CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings

Conflict-Averse Gradient Descent for Multi-task learning

Optimal Underdamped Langevin MCMC Method

Decoupling the Depth and Scope of Graph Neural Networks

Auditing Black-Box Prediction Models for Data Minimization Compliance

Adaptive wavelet distillation from neural networks through interpretations

Safe Policy Optimization with Local Generalized Linear Function Approximations

On the Equivalence between Neural Network and Support Vector Machine

Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning

Stronger NAS with Weaker Predictors

Dynamic Trace Estimation

On the Generative Utility of Cyclic Conditionals

Learning to Select Exogenous Events for Marked Temporal Point Process

A Contrastive Learning Approach for Training Variational Autoencoder Priors

What training reveals about neural network complexity

Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers

Learning Domain Invariant Representations in Goal-conditioned Block MDPs

Sample Selection for Fair and Robust Training

Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language

BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer

Long Short-Term Transformer for Online Action Detection

Learning Optimal Predictive Checklists

Understanding Deflation Process in Over-parametrized Tensor Decomposition

Systematic Generalization with Edge Transformers

Uniform Sampling over Episode Difficulty

Grounding Representation Similarity Through Statistical Testing

Revealing and Protecting Labels in Distributed Training

Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots

Continuous-time edge modelling using non-parametric point processes

Understanding Instance-based Interpretability of Variational Auto-Encoders

Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks

Constrained Robust Submodular Partitioning

UCB-based Algorithms for Multinomial Logistic Regression Bandits

AutoBalance: Optimized Loss Functions for Imbalanced Data

VigDet: Knowledge Informed Neural Temporal Point Process for Coordination Detection on Social Media

Looking Beyond Single Images for Contrastive Semantic Segmentation Learning

Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data

Associative Memories via Predictive Coding

Robust and differentially private mean estimation

CoAtNet: Marrying Convolution and Attention for All Data Sizes

Deep Synoptic Monte-Carlo Planning in Reconnaissance Blind Chess

Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networks

Stability and Generalization of Bilevel Programming in Hyperparameter Optimization

Self-Adaptable Point Processes with Nonparametric Time Decays

Generalized Shape Metrics on Neural Representations

High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails

Matrix encoding networks for neural combinatorial optimization

Continuous Latent Process Flows

Dataset Distillation with Infinitely Wide Convolutional Networks

Imitation with Neural Density Models

The Benefits of Implicit Regularization from SGD in Least Squares Problems

Robust Counterfactual Explanations on Graph Neural Networks

Dissecting the Diffusion Process in Linear Graph Convolutional Networks

Data Sharing and Compression for Cooperative Networked Control

STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning

On the Representation of Solutions to Elliptic PDEs in Barron Spaces

Learning 3D Dense Correspondence via Canonical Point Autoencoder

Subgraph Federated Learning with Missing Neighbor Generation

Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees

Regulating algorithmic filtering on social media

Information-constrained optimization: can adaptive processing of gradients help?

Online Robust Reinforcement Learning with Model Uncertainty

Deeply Shared Filter Bases for Parameter-Efficient Convolutional Neural Networks

Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble

Multi-Agent Reinforcement Learning in Stochastic Networked Systems

The future is log-Gaussian: ResNets and their infinite-depth-and-width limit at initialization

Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent

Approximate optimization of convex functions with outlier noise

Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery

Learning Signal-Agnostic Manifolds of Neural Fields

HyperSPNs: Compact and Expressive Probabilistic Circuits

A Biased Graph Neural Network Sampler with Near-Optimal Regret

Efficient Statistical Assessment of Neural Network Corruption Robustness

Realistic evaluation of transductive few-shot learning

Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes

Reliable Post hoc Explanations: Modeling Uncertainty in Explainability

An Exponential Lower Bound for Linearly Realizable MDP with Constant Suboptimality Gap

Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning

Causal Abstractions of Neural Networks

Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination

TriBERT: Human-centric Audio-visual Representation Learning

Meta-Adaptive Nonlinear Control: Theory and Algorithms

Contrastively Disentangled Sequential Variational Autoencoder

Towards understanding retrosynthesis by energy-based models

Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning

Universal Graph Convolutional Networks

Extracting Deformation-Aware Local Features by Learning to Deform

Dynamic Inference with Neural Interpreters

True Few-Shot Learning with Language Models

Controlling Neural Networks with Rule Representations

Fairness in Ranking under Uncertainty

Fairness via Representation Neutralization

Learning to Assimilate in Chaotic Dynamical Systems

Differential Privacy Over Riemannian Manifolds

How can classical multidimensional scaling go wrong?

Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones

An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks

Learning in Multi-Stage Decentralized Matching Markets

Understanding Interlocking Dynamics of Cooperative Rationalization

Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals

Learning to Learn Dense Gaussian Processes for Few-Shot Learning

Implicit Transformer Network for Screen Content Image Continuous Super-Resolution

Efficient Algorithms for Learning Depth-2 Neural Networks with General ReLU Activations

Heuristic-Guided Reinforcement Learning

Revisiting Smoothed Online Learning

Dimension-free empirical entropy estimation

Deep Extrapolation for Attribute-Enhanced Generation

Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation

Online Selective Classification with Limited Feedback

Embedding Principle of Loss Landscape of Deep Neural Networks

Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions

Efficient Neural Network Training via Forward and Backward Propagation Sparsification

Representing Hyperbolic Space Accurately using Multi-Component Floats

A Computationally Efficient Method for Learning Exponential Family Distributions

Joint inference and input optimization in equilibrium networks

ProTo: Program-Guided Transformer for Program-Guided Tasks

Property-Aware Relation Networks for Few-Shot Molecular Property Prediction

Differentially Private Learning with Adaptive Clipping

Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling

Pessimism Meets Invariance: Provably Efficient Offline Mean-Field Multi-Agent RL

Locality Sensitive Teaching

SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning

Knowledge-inspired 3D Scene Graph Prediction in Point Cloud

Lower Bounds on Metropolized Sampling Methods for Well-Conditioned Distributions

Distributed Estimation with Multiple Samples per User: Sharp Rates and Phase Transition

Backdoor Attack with Imperceptible Input and Latent Modification

Functional Regularization for Reinforcement Learning via Learned Fourier Features

Unifying Width-Reduced Methods for Quasi-Self-Concordant Optimization

Conservative Offline Distributional Reinforcement Learning

REMIPS: Physically Consistent 3D Reconstruction of Multiple Interacting People under Weak Supervision

Bounds all around: training energy-based models with bidirectional bounds

Convergence and Alignment of Gradient Descent with Random Backpropagation Weights

A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis

A Minimalist Approach to Offline Reinforcement Learning

Simple Stochastic and Online Gradient Descent Algorithms for Pairwise Learning

Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning

The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition

SimiGrad: Fine-Grained Adaptive Batching for Large Scale Training using Gradient Similarity Measurement

Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds and Benign Overfitting

DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks

Techniques for Symbol Grounding with SATNet

Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory

RED : Looking for Redundancies for Data-FreeStructured Compression of Deep Neural Networks

Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods

Reinforcement Learning based Disease Progression Model for Alzheimer’s Disease

Perturbation Theory for the Information Bottleneck

Deconvolutional Networks on Graph Data

Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer

Robust Learning of Optimal Auctions

SOFT: Softmax-free Transformer with Linear Complexity

Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators

A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs

Few-Shot Segmentation via Cycle-Consistent Transformer

Risk Bounds and Calibration for a Smart Predict-then-Optimize Method

Latent Execution for Neural Program Synthesis Beyond Domain-Specific Languages

Combiner: Full Attention Transformer with Sparse Computation Cost

Geometry Processing with Neural Fields

Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network

Observation-Free Attacks on Stochastic Bandits

Fast Extra Gradient Methods for Smooth Structured Nonconvex-Nonconcave Minimax Problems

DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer

Minibatch and Momentum Model-based Methods for Stochastic Weakly Convex Optimization

Identity testing for Mallows model

Meta-learning to Improve Pre-training

Adaptive Diffusion in Graph Neural Networks

Slice Sampling Reparameterization Gradients

Probabilistic Transformer For Time Series Analysis

Subgame solving without common knowledge

Multiwavelet-based Operator Learning for Differential Equations

Efficiently Learning One Hidden Layer ReLU Networks From Queries

Can we globally optimize cross-validation loss? Quasiconvexity in ridge regression

Discovering and Achieving Goals via World Models

Understanding and Improving Early Stopping for Learning with Noisy Labels

Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training

Pointwise Bounds for Distribution Estimation under Communication Constraints

Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embedding

PLUGIn: A simple algorithm for inverting generative models with recovery guarantees

Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning

Closing the Gap: Tighter Analysis of Alternating Stochastic Gradient Methods for Bilevel Problems

Fast Training Method for Stochastic Compositional Optimization Problems

Noether’s Learning Dynamics: Role of Symmetry Breaking in Neural Networks

Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity

Fast Doubly-Adaptive MCMC to Estimate the Gibbs Partition Function with Weak Mixing Time Bounds

ReLU Regression with Massart Noise

Unintended Selection: Persistent Qualification Rate Disparities and Interventions

Fast Bayesian Inference for Gaussian Cox Processes via Path Integral Formulation

Robust Deep Reinforcement Learning through Adversarial Loss

Learning to delegate for large-scale vehicle routing

TöRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis

Which Mutual-Information Representation Learning Objectives are Sufficient for Control?

Unbiased Classification through Bias-Contrastive and Bias-Balanced Learning

Generalized Linear Bandits with Local Differential Privacy

Efficiently Identifying Task Groupings for Multi-Task Learning

A Unified View of cGANs with and without Classifiers

Improving Self-supervised Learning with Automated Unsupervised Outlier Arbitration

Dynamic COVID risk assessment accounting for community virus exposure from a spatial-temporal transmission model

Automated Dynamic Mechanism Design

Robust Predictable Control

Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization

Fair Sequential Selection Using Supervised Learning Models

Momentum Centering and Asynchronous Update for Adaptive Gradient Methods

Asymptotically Exact Error Characterization of Offline Policy Evaluation with Misspecified Linear Models

Topographic VAEs learn Equivariant Capsules

On Path Integration of Grid Cells: Group Representation and Isotropic Scaling

COMBO: Conservative Offline Model-Based Policy Optimization

Time-series Generation by Contrastive Imitation

Global Convergence to Local Minmax Equilibrium in Classes of Nonconvex Zero-Sum Games

Clockwork Variational Autoencoders

Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models

Differentially Private Model Personalization

Rates of Estimation of Optimal Transport Maps using Plug-in Estimators via Barycentric Projections

Scalable and Stable Surrogates for Flexible Classifiers with Fairness Constraints

Model-Based Episodic Memory Induces Dynamic Hybrid Controls

FedDR – Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization

A Regression Approach to Learning-Augmented Online Algorithms

(ends 6:00 PM)

6 p.m.

Affinity Workshop:

WiML Workshop 2

(ends 11:00 PM)

11 p.m.

Town Hall:

Town Hall

(ends 12:00 AM)

FRI 10 DEC

midnight

Datasets and Benchmarks:

Dataset and Benchmark Track 3

(ends 1:00 AM)

Oral Session 4: Theory [12:00-1:00]

Oral s 12:00-12:15

[12:00] Risk Monotonicity in Statistical Learning

Q&A s 12:15-12:20

[12:15] Q&A

Oral s 12:20-12:35

[12:20] Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds and Benign Overfitting

Q&A s 12:35-12:40

[12:35] Q&A

Oral s 12:40-12:55

[12:40] The decomposition of the higher-order homology embedding constructed from the $k$-Laplacian

Q&A s 12:55-1:00

[12:55] Q&A

(ends 1:00 AM)

Oral Session 4: Vision Applications and Optimization [12:00-1:00]

Oral s 12:00-12:15

[12:00] Passive attention in artificial neural networks predicts human visual selectivity

Q&A s 12:15-12:20

[12:15] Q&A

Oral s 12:20-12:35

[12:20] Shape As Points: A Differentiable Poisson Solver

Q&A s 12:35-12:40

[12:35] Q&A

Oral s 12:40-12:55

[12:40] Optimal Rates for Random Order Online Optimization

Q&A s 12:55-1:00

[12:55] Q&A

(ends 1:00 AM)

2 a.m.

Competition:

Competition Track Day 4: Overviews + Breakout Sessions

(ends 6:44 AM)

Affinity Workshop:

Black in AI Workshop

(ends 7:00 AM)

Affinity Workshop:

WiML Workshop 3

(ends 7:00 AM)

7 a.m.

Invited Talk:

The Collective Intelligence of Army Ants, and the Robots They Inspire

Radhika Nagpal

(ends 8:30 AM)

8:30 a.m.

Demonstration:

Demonstrations 4

(ends 9:50 AM)

Datasets and Benchmarks:

Dataset and Benchmark Poster Session 4

(ends 10:00 AM)

Poster Session 8 [8:30-10:00]

T-LoHo: A Bayesian Regularization Model for Structured Sparsity and Smoothness on Graphs

Solving Graph-based Public Goods Games with Tree Search and Imitation Learning

Smooth Normalizing Flows

RMM: Reinforced Memory Management for Class-Incremental Learning

Speedy Performance Estimation for Neural Architecture Search

Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition

Learning to Draw: Emergent Communication through Sketching

To The Point: Correspondence-driven monocular 3D category reconstruction

Distributed Deep Learning In Open Collaborations

Learning Graph Models for Retrosynthesis Prediction

Robust Implicit Networks via Non-Euclidean Contractions

Sparse is Enough in Scaling Transformers

Adversarial Feature Desensitization

Intriguing Properties of Contrastive Losses

Detecting Anomalous Event Sequences with Temporal Point Processes

Parametric Complexity Bounds for Approximating PDEs with Neural Networks

ResT: An Efficient Transformer for Visual Recognition

Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach

Risk-averse Heteroscedastic Bayesian Optimization

Improving Transferability of Representations via Augmentation-Aware Self-Supervision

Learning Fast-Inference Bayesian Networks

Explainable Semantic Space by Grounding Language to Vision with Cross-Modal Contrastive Learning

SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios

Explanation-based Data Augmentation for Image Classification

Predicting Deep Neural Network Generalization with Perturbation Response Curves

Last iterate convergence of SGD for Least-Squares in the Interpolation regime.

CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions

Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation

Intriguing Properties of Vision Transformers

Active Learning of Convex Halfspaces on Graphs

End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering

To Beam Or Not To Beam: That is a Question of Cooperation for Language GANs

DNN-based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel

Conditional Generation Using Polynomial Expansions

How Powerful are Performance Predictors in Neural Architecture Search?

Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning

Progressive Feature Interaction Search for Deep Sparse Network

Local Explanation of Dialogue Response Generation

The Utility of Explainable AI in Ad Hoc Human-Machine Teaming

Fuzzy Clustering with Similarity Queries

Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Clean Images

Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games

Near Optimal Policy Optimization via REPS

Algorithmic Instabilities of Accelerated Gradient Descent

TransformerFusion: Monocular RGB Scene Reconstruction using Transformers

Play to Grade: Testing Coding Games as Classifying Markov Decision Process

Think Big, Teach Small: Do Language Models Distil Occam’s Razor?

Early-stopped neural networks are consistent

Shift Invariance Can Reduce Adversarial Robustness

Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs

Is Automated Topic Model Evaluation Broken? The Incoherence of Coherence

Multi-view Contrastive Graph Clustering

Memory-efficient Patch-based Inference for Tiny Deep Learning

Luna: Linear Unified Nested Attention

Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL

Zero Time Waste: Recycling Predictions in Early Exit Neural Networks

On the Existence of The Adversarial Bayes Classifier

Visual Adversarial Imitation Learning using Variational Models

Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks

Towards Lower Bounds on the Depth of ReLU Neural Networks

The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations

Learning Knowledge Graph-based World Models of Textual Environments

Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization

Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution

Invariant Causal Imitation Learning for Generalizable Policies

Task-Agnostic Undesirable Feature Deactivation Using Out-of-Distribution Data

Private Non-smooth ERM and SCO in Subquadratic Steps

Dynamic Analysis of Higher-Order Coordination in Neuronal Assemblies via De-Sparsified Orthogonal Matching Pursuit

Influence Patterns for Explaining Information Flow in BERT

Localization, Convexity, and Star Aggregation

Online Facility Location with Multiple Advice

Robust Online Correlation Clustering

Can contrastive learning avoid shortcut solutions?

When False Positive is Intolerant: End-to-End Optimization with Low FPR for Multipartite Ranking

Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures

COHESIV: Contrastive Object and Hand Embedding Segmentation In Video

Improving Contrastive Learning on Imbalanced Data via Open-World Sampling

Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis

ParK: Sound and Efficient Kernel Ridge Regression by Feature Space Partitions

Sparse Uncertainty Representation in Deep Learning with Inducing Weights

Bellman-consistent Pessimism for Offline Reinforcement Learning

Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks

GemNet: Universal Directional Graph Neural Networks for Molecules

Antipodes of Label Differential Privacy: PATE and ALIBI

Contrastive Learning of Global and Local Video Representations

Exploring the Limits of Out-of-Distribution Detection

A Normative and Biologically Plausible Algorithm for Independent Component Analysis

LSH-SMILE: Locality Sensitive Hashing Accelerated Simulation and Learning

Edge Representation Learning with Hypergraphs

Concentration inequalities under sub-Gaussian and sub-exponential conditions

Robustness of Graph Neural Networks at Scale

Going Beyond Linear Transformers with Recurrent Fast Weight Programmers

On the Expressivity of Markov Reward

Neural Scene Flow Prior

Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation

Label consistency in overfitted generalized $k$-means

KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support

Towards Deeper Deep Reinforcement Learning with Spectral Normalization

Memory-Efficient Approximation Algorithms for Max-k-Cut and Correlation Clustering

Uniform Concentration Bounds toward a Unified Framework for Robust Clustering

Active clustering for labeling training data

Adversarial Intrinsic Motivation for Reinforcement Learning

Multi-Facet Clustering Variational Autoencoders

How Fine-Tuning Allows for Effective Meta-Learning

Scalable Neural Data Server: A Data Recommender for Transfer Learning

High Probability Complexity Bounds for Line Search Based on Stochastic Oracles

Hierarchical Clustering: $O(1)$-Approximation for Well-Clustered Graphs

The Value of Information When Deciding What to Learn

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration

Practical Near Neighbor Search via Group Testing

Fast Projection onto the Capped Simplex with Applications to Sparse Regression in Bioinformatics

Infinite Time Horizon Safety of Bayesian Neural Networks

NTopo: Mesh-free Topology Optimization using Implicit Neural Representations

Curriculum Design for Teaching via Demonstrations: Theory and Applications

Dynamic Causal Bayesian Optimization

Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity

Independent Prototype Propagation for Zero-Shot Compositionality

Risk Monotonicity in Statistical Learning

Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces

Entropic Desired Dynamics for Intrinsic Control

Dual Parameterization of Sparse Variational Gaussian Processes

Universal Rate-Distortion-Perception Representations for Lossy Compression

Hierarchical Skills for Efficient Exploration

Sequential Algorithms for Testing Closeness of Distributions

Foundations of Symbolic Languages for Model Interpretability

How Well do Feature Visualizations Support Causal Understanding of CNN Activations?

An Uncertainty Principle is a Price of Privacy-Preserving Microdata

Batch Active Learning at Scale

Joint Semantic Mining for Weakly Supervised RGB-D Salient Object Detection

Contrastive Learning for Neural Topic Model

A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning

Optimization-Based Algebraic Multigrid Coarsening Using Reinforcement Learning

Explaining Latent Representations with a Corpus of Examples

EDGE: Explaining Deep Reinforcement Learning Policies

On Plasticity, Invariance, and Mutually Frozen Weights in Sequential Task Learning

Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions

Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers

Constrained Two-step Look-Ahead Bayesian Optimization

Learning with Labeling Induced Abstentions

On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)

Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning

Consistency Regularization for Variational Auto-Encoders

Interactive Label Cleaning with Example-based Explanations

A Compositional Atlas of Tractable Circuit Operations for Probabilistic Inference

Better Algorithms for Individually Fair $k$-Clustering

HNPE: Leveraging Global Parameters for Neural Posterior Estimation

Contrastive Active Inference

CCVS: Context-aware Controllable Video Synthesis

Convergence of adaptive algorithms for constrained weakly convex optimization

Scaling up Continuous-Time Markov Chains Helps Resolve Underspecification

M-FAC: Efficient Matrix-Free Approximations of Second-Order Information

Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks: A Tale of Symmetry II

Learning to Ground Multi-Agent Communication with Autoencoders

A Theoretical Analysis of Fine-tuning with Linear Teachers

Directional Message Passing on Molecular Graphs via Synthetic Coordinates

Regularization in ResNet with Stochastic Depth

CROCS: Clustering and Retrieval of Cardiac Signals Based on Patient Disease Class, Sex, and Age

Reinforcement Learning with State Observation Costs in Action-Contingent Noiselessly Observable Markov Decision Processes

On Blame Attribution for Accountable Multi-Agent Sequential Decision Making

Rethinking the Pruning Criteria for Convolutional Neural Network

Capacity and Bias of Learned Geometric Embeddings for Directed Graphs

DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras

Large-Scale Unsupervised Object Discovery

On Linear Stability of SGD and Input-Smoothness of Neural Networks

Designing Counterfactual Generators using Deep Model Inversion

A Faster Maximum Cardinality Matching Algorithm with Applications in Machine Learning

Towards Robust and Reliable Algorithmic Recourse

Learning to Time-Decode in Spiking Neural Networks Through the Information Bottleneck

Invertible DenseNets with Concatenated LipSwish

Coresets for Clustering with Missing Values

Scatterbrain: Unifying Sparse and Low-rank Attention

Generating High-Quality Explanations for Navigation in Partially-Revealed Environments

Hash Layers For Large Sparse Models

An Information-theoretic Approach to Distribution Shifts

Per-Pixel Classification is Not All You Need for Semantic Segmentation

Structured Denoising Diffusion Models in Discrete State-Spaces

Emergent Communication of Generalizations

Learning latent causal graphs via mixture oracles

ErrorCompensatedX: error compensation for variance reduced algorithms

On the Frequency Bias of Generative Models

Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices

On Locality of Local Explanation Models

Relative Flatness and Generalization

SOPE: Spectrum of Off-Policy Estimators

Strategic Behavior is Bliss: Iterative Voting Improves Social Welfare

Support Recovery of Sparse Signals from a Mixture of Linear Measurements

Bridging the Imitation Gap by Adaptive Insubordination

Tracking Without Re-recognition in Humans and Machines

Directed Graph Contrastive Learning

Space-time Mixing Attention for Video Transformer

Algorithmic stability and generalization of an unsupervised feature selection algorithm

Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information

Laplace Redux - Effortless Bayesian Deep Learning

Explicable Reward Design for Reinforcement Learning Agents

$\alpha$-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression

Estimating the Unique Information of Continuous Variables

Parallel and Efficient Hierarchical k-Median Clustering

Generic Neural Architecture Search via Regression

Implicit Regularization in Matrix Sensing via Mirror Descent

Exponential Separation between Two Learning Models and Adversarial Robustness

Catch-A-Waveform: Learning to Generate Audio from a Single Short Example

When Are Solutions Connected in Deep Networks?

Efficient Online Estimation of Causal Effects by Deciding What to Observe

Accelerating Quadratic Optimization with Reinforcement Learning

Improved Coresets and Sublinear Algorithms for Power Means in Euclidean Spaces

The Effect of the Intrinsic Dimension on the Generalization of Quadratic Classifiers

Neural Flows: Efficient Alternative to Neural ODEs

End-to-end reconstruction meets data-driven regularization for inverse problems

SNIPS: Solving Noisy Inverse Problems Stochastically

Dirichlet Energy Constrained Learning for Deep Graph Neural Networks

Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives

A Comprehensively Tight Analysis of Gradient Descent for PCA

Three-dimensional spike localization and improved motion correction for Neuropixels recordings

Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descent

Reinforcement Learning in Newcomblike Environments

The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning

Sparse Flows: Pruning Continuous-depth Models

SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks

Encoding Spatial Distribution of Convolutional Features for Texture Representation

Online Active Learning with Surrogate Loss Functions

Learning to Compose Visual Relations

Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction

On Training Implicit Models

Communication-efficient SGD: From Local SGD to One-Shot Averaging

On the Power of Differentiable Learning versus PAC and SQ Learning

Adaptive Proximal Gradient Methods for Structured Neural Networks

Distributionally Robust Imitation Learning

On the Power of Edge Independent Graph Models

Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels

The functional specialization of visual cortex emerges from training parallel pathways with self-supervised predictive learning

Adversarial Training Helps Transfer Learning via Better Representations

SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision

Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization

Reward is enough for convex MDPs

Does enforcing fairness mitigate biases caused by subpopulation shift?

Shapley Residuals: Quantifying the limits of the Shapley value for explanations

Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows

The Limits of Optimal Pricing in the Dark

No RL, No Simulation: Learning to Navigate without Navigating

Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings

Towards Sharper Generalization Bounds for Structured Prediction

Topological Relational Learning on Graphs

Federated Linear Contextual Bandits

Improved Regularization and Robustness for Fine-tuning in Neural Networks

Robust Contrastive Learning Using Negative Samples with Diminished Semantics

SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs

A Gaussian Process-Bayesian Bernoulli Mixture Model for Multi-Label Active Learning

You Never Cluster Alone

Self-Supervised Bug Detection and Repair

No Regrets for Learning the Prior in Bandits

ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning

Efficient Generalization with Distributionally Robust Learning

Minimax Regret for Stochastic Shortest Path

Turing Completeness of Bounded-Precision Recurrent Neural Networks

Why Do Better Loss Functions Lead to Less Transferable Features?

Making a (Counterfactual) Difference One Rationale at a Time

3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds

On Contrastive Representations of Stochastic Processes