Downloads 2020
Number of events: 2021
- 3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data
- 3D Self-Supervised Methods for Medical Imaging
- 3D Shape Reconstruction from Vision and Touch
- 3rd Robot Learning Workshop
- A Bandit Learning Algorithm and Applications to Auction Design
- A Bayesian Nonparametrics View into Deep Representations
- A Bayesian Perspective on Training Speed and Model Selection
- A Benchmark for Systematic Generalization in Grounded Language Understanding
- A Biologically Plausible Neural Network for Slow Feature Analysis
- A Boolean Task Algebra for Reinforcement Learning
- A/B Testing in Dense Large-Scale Networks: Design and Inference
- A Catalyst Framework for Minimax Optimization
- A causal view of compositional zero-shot recognition
- A Causal View on Robustness of Neural Networks
- Accelerating Reinforcement Learning through GPU Atari Emulation
- Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping
- Acceleration with a Ball Optimization Oracle
- Achieving Equalized Odds by Resampling Sensitive Attributes
- A Class of Algorithms for General Instrumental Variable Models
- A Closer Look at Accuracy vs. Robustness
- A Closer Look at the Training Strategy for Modern Meta-Learning
- A Combinatorial Perspective on Transfer Learning
- A Computational Separation between Private Learning and Online Learning
- A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval
- A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions
- A convex optimization formulation for multivariate regression
- A Convolutional Auto-Encoder for Haplotype Assembly and Viral Quasispecies Reconstruction
- Active Invariant Causal Prediction: Experiment Selection through Stability
- Active Structure Learning of Causal DAGs via Directed Clique Trees
- AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients
- Adam with Bandit Sampling for Deep Learning
- Adaptation Properties Allow Identification of Optimized Neural Codes
- Adapting Neural Architectures Between Domains
- Adapting to Misspecification in Contextual Bandits
- Adaptive Discretization for Model-Based Reinforcement Learning
- Adaptive Experimental Design with Temporal Interference: A Maximum Likelihood Approach
- Adaptive Gradient Quantization for Data-Parallel SGD
- Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
- Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes
- Adaptive Learned Bloom Filter (Ada-BF): Efficient Utilization of the Classifier with Application to Real-Time Information Filtering on the Web
- Adaptive Learning of Rank-One Models for Efficient Pairwise Sequence Alignment
- Adaptive Online Estimation of Piecewise Polynomial Trends
- Adaptive Probing Policies for Shortest Path Routing
- Adaptive Reduced Rank Regression
- Adaptive Sampling for Stochastic Risk-Averse Learning
- Adaptive Shrinkage Estimation for Streaming Graphs
- AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
- AdaTune: Adaptive Tensor Program Compilation Made Efficient
- A Decentralized Parallel Algorithm for Training Generative Adversarial Nets
- A Dictionary Approach to Domain-Invariant Learning in Deep Networks
- A Discrete Variational Recurrent Topic Model without the Reparametrization Trick
- Advances and Opportunities: Machine Learning for Education
- Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization
- Adversarial Attacks on Deep Graph Matching
- Adversarial Attacks on Linear Contextual Bandits
- Adversarial Bandits with Corruptions
- Adversarial Blocking Bandits
- Adversarial Counterfactual Learning and Evaluation for Recommender System
- Adversarial Crowdsourcing Through Robust Rank-One Matrix Completion
- Adversarial Distributional Training for Robust Deep Learning
- Adversarial Example Games
- Adversarial Learning for Robust Deep Clustering
- Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models
- Adversarially Robust Few-Shot Learning: A Meta-Learning Approach
- Adversarially Robust Streaming Algorithms via Differential Privacy
- Adversarial Robustness of Supervised Sparse Coding
- Adversarial robustness via robust low rank representations
- Adversarial Self-Supervised Contrastive Learning
- Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization
- Adversarial Sparse Transformer for Time Series Forecasting
- Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation
- Adversarial Training is a Form of Data-dependent Operator Norm Regularization
- Adversarial Weight Perturbation Helps Robust Generalization
- AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows
- A Dynamical Central Limit Theorem for Shallow Neural Networks
- A Fair Classifier Using Kernel Density Estimation
- A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization
- A Finite-Time Analysis of Two Time-Scale Actor-Critic Methods
- A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding
- A Future of Work for the Invisible Workers in A.I.
- A Game Theoretic Analysis of Additive Adversarial Attacks and Defenses
- A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning
- A Game-Theoretic Analysis of the Empirical Revenue Maximization Algorithm with Endogenous Sampling
- A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks
- A General Large Neighborhood Search Framework for Solving Integer Linear Programs
- A General Method for Robust Learning from Batches
- Agnostic $Q$-learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity
- Agnostic Learning of a Single Neuron with Gradient Descent
- Agnostic Learning with Multiple Objectives
- A graph similarity for deep learning
- Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient Space
- A Group-Theoretic Framework for Data Augmentation
- AI Assisted Data Labeling
- AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity
- AI for Earth Sciences
- A kernel test for quasi-independence
- A Knowledge Graph Reasoning Prototype
- Algorithmic Fairness through the Lens of Causality and Interpretability
- Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
- A Limitation of the PAC-Bayes Framework
- All-or-nothing statistical and computational phase transitions in sparse spiked matrix estimation
- All Word Embeddings from One Embedding
- All your loss are belong to Bayes
- Almost Optimal Model-Free Reinforcement Learningvia Reference-Advantage Decomposition
- Almost Surely Stable Deep Dynamics
- A Local Temporal Difference Code for Distributional Reinforcement Learning
- A Loss Function for Generative Neural Networks Based on Watson’s Perceptual Model
- A mathematical model for automatic differentiation in machine learning
- A mathematical theory of cooperative communication
- A Matrix Chernoff Bound for Markov Chains and Its Application to Co-occurrence Matrices
- A Maximum-Entropy Approach to Off-Policy Evaluation in Average-Reward MDPs
- A mean-field analysis of two-player zero-sum games
- A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings
- A meta-learning approach to (re)discover plasticity rules that carve a desired function into a neural network
- Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring
- Analytical Probability Distributions and Exact Expectation-Maximization for Deep Generative Networks
- Analytic Characterization of the Hessian in Shallow ReLU Models: A Tale of Symmetry
- An Analysis of SVD for Deep Rotation Estimation
- An analytic theory of shallow networks dynamics for hinge loss classification
- An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits
- An Efficient Adversarial Attack for Tree Ensembles
- An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search
- An Efficient Framework for Clustered Federated Learning
- An efficient nonconvex reformulation of stagewise convex optimization problems
- An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits
- An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay
- A new convergent variant of Q-learning with linear function approximation
- A new inference approach for training shallow and deep generalized linear models of noisy interacting neurons
- An Imitation from Observation Approach to Transfer Learning with Dynamics Mismatch
- An implicit function learning approach for parametric modal regression
- An Improved Analysis of Stochastic Gradient Descent with Momentum
- An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods
- A Non-Asymptotic Analysis for Stein Variational Gradient Descent
- An operator view of policy gradient methods
- An Optimal Elimination Algorithm for Learning a Best Arm
- A Novel Approach for Constrained Optimization in Graphical Models
- A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances
- A novel variational form of the Schatten-$p$ quasi-norm
- An Unbiased Risk Estimator for Learning with Augmented Classes
- An Unsupervised Information-Theoretic Perceptual Quality Metric
- AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection
- A polynomial-time algorithm for learning nonparametric causal graphs
- Applications of Common Entropy for Causal Inference
- Approximate Cross-Validation for Structured Models
- Approximate Cross-Validation with Low-Rank Data in High Dimensions
- Approximate Heavily-Constrained Learning with Lagrange Multiplier Models
- Approximation Based Variance Reduction for Reparameterization Gradients
- A Randomized Algorithm to Reduce the Support of Discrete Measures
- A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent
- A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection
- ARMA Nets: Expanding Receptive Field for Dense Prediction
- A Robust Functional EM Algorithm for Incomplete Panel Count Data
- A Scalable Approach for Privacy-Preserving Collaborative Machine Learning
- A Scalable MIP-based Method for Learning Optimal Multivariate Decision Trees
- A Self-Tuning Actor-Critic Algorithm
- A shooting formulation of deep learning
- A Simple and Efficient Smoothing Method for Faster Optimization and Local Exploration
- A Simple Language Model for Task-Oriented Dialogue
- A simple normative network approximates local non-Hebbian learning in the cortex
- A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems
- A Single Recipe for Online Submodular Maximization with Adversarial or Stochastic Constraints
- A Spectral Energy Distance for Parallel Speech Synthesis
- Assessing SATNet's Ability to Solve the Symbol Grounding Problem
- Assisted Learning: A Framework for Multi-Organization Learning
- A Statistical Framework for Low-bitwidth Training of Deep Neural Networks
- A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning
- A Stochastic Path Integral Differential EstimatoR Expectation Maximization Algorithm
- A Study on Encodings for Neural Architecture Search
- Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability
- Asymptotically Optimal Exact Minibatch Metropolis-Hastings
- Asymptotic Guarantees for Generative Modeling Based on the Smooth Wasserstein Distance
- Asymptotic normality and confidence intervals for derivatives of 2-layers neural network in the random features model
- A Theoretical Framework for Target Propagation
- A Tight Lower Bound and Efficient Reduction for Swap Regret
- A Topological Filter for Learning with Label Noise
- Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
- AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Control
- Attention-Gated Brain Propagation: How the brain can implement reward-based error backpropagation
- Attribute Prototype Network for Zero-Shot Learning
- Attribution Preservation in Network Compression for Reliable Network Interpretation
- Audeo: Audio Generation for a Silent Performance Video
- Auditing Differentially Private Machine Learning: How Private is Private SGD?
- A Unified Switching System Perspective and Convergence Analysis of Q-Learning Algorithms
- A Unified View of Label Shift Estimation
- A Unifying View of Optimism in Episodic Reinforcement Learning
- A Universal Approximation Theorem of Deep Neural Networks for Expressing Probability Distributions
- AutoBSS: An Efficient Algorithm for Block Stacking Style Search
- Autoencoders that don't overfit towards the Identity
- Autofocused oracles for model-based design
- Auto Learning Attention
- Automated dataset extraction from SEC filings
- Automatically Learning Compact Quality-aware Surrogates for Optimization Problems
- Automatic Curriculum Learning through Value Disagreement
- Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
- Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation
- AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference
- Autoregressive Score Matching
- AutoSync: Learning to Synchronize for Data-Parallel Distributed Deep Learning
- Auxiliary Task Reweighting for Minimum-data Learning
- A Variational Approach for Learning from Positive and Unlabeled Data
- AvE: Assistance via Empowerment
- AViD Dataset: Anonymized Videos from Diverse Countries
- Avoiding Side Effects By Considering Future Tasks
- Avoiding Side Effects in Complex Environments
- Axioms for Learning from Pairwise Comparisons
- BabyMind: How Babies Learn and How Machines Can Imitate
- Backpropagating Linearly Improves Transferability of Adversarial Examples
- Bad Global Minima Exist and SGD Can Reach Them
- BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning
- Balanced Meta-Softmax for Long-Tailed Visual Recognition
- Bandit Linear Control
- BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed Bandits
- Bandit Samplers for Training Graph Neural Networks
- Barking up the right tree: an approach to search over molecule synthesis DAGs
- Batched Coarse Ranking in Multi-Armed Bandits
- Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks
- Batch normalization provably avoids ranks collapse for randomly initialised deep networks
- Baxter Permutation Process
- Bayes Consistency vs. H-Consistency: The Interplay between Surrogate Loss Functions and the Scoring Function Class
- Bayesian Attention Modules
- Bayesian Bits: Unifying Quantization and Pruning
- Bayesian Causal Structural Learning with Zero-Inflated Poisson Bayesian Networks
- Bayesian Deep Ensembles via the Neural Tangent Kernel
- Bayesian Deep Learning and a Probabilistic Perspective of Generalization
- Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods
- Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels
- Bayesian Multi-type Mean Field Multi-agent Imitation Learning
- Bayesian Optimization for Iterative Learning
- Bayesian Optimization of Risk Measures
- Bayesian Probabilistic Numerical Integration with Tree-Based Models
- Bayesian Pseudocoresets
- Bayesian Robust Optimization for Imitation Learning
- BayReL: Bayesian Relational Learning for Multi-omics Data Integration
- Belief-Dependent Macro-Action Discovery in POMDPs using the Value of Information
- Belief Propagation Neural Networks
- Benchmarking Deep Inverse Models over time, and the Neural-Adjoint method
- Benchmarking Deep Learning Interpretability in Time Series Predictions
- BERT Loses Patience: Fast and Robust Inference with Early Exit
- Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs
- Beta R-CNN: Looking into Pedestrian Detection from Another Perspective
- Better Full-Matrix Regret via Parameter-Free Online Learning
- Better Set Representations For Relational Reasoning
- Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency
- Beyond BackPropagation: Novel Ideas for Training Neural Architectures
- Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
- Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses
- Beyond Lazy Training for Over-parameterized Tensor Decomposition
- Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples
- Beyond the Mean-Field: Structured Deep Gaussian Processes Improve the Predictive Uncertainties
- Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning
- Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs
- Bidirectional Convolutional Poisson Gamma Dynamical Systems
- Big Bird: Transformers for Longer Sequences
- Big Self-Supervised Models are Strong Semi-Supervised Learners
- Bi-level Score Matching for Learning Energy-based Latent Variable Models
- Biological and Artificial Reinforcement Learning
- Biological credit assignment through dynamic inversion of feedforward networks
- Biologically Inspired Mechanisms for Adversarial Robustness
- Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework
- Black-Box Optimization with Local Generative Surrogates
- Black-Box Ripper: Copying black-box models using generative evolutionary algorithms
- Blind Video Temporal Consistency via Deep Video Prior
- BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images
- Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
- Boosting Adversarial Training with Hypersphere Embedding
- Boosting First-Order Methods by Shifting Objective: New Schemes with Faster Worst-Case Rates
- Bootstrapping neural processes
- Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning
- BOSS: Bayesian Optimization over String Spaces
- BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization
- Boundary thickness and robustness in learning models
- BoxE: A Box Embedding Model for Knowledge Base Completion
- Breaking Reversibility Accelerates Langevin Dynamics for Non-Convex Optimization
- Breaking the Communication-Privacy-Accuracy Trilemma
- Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model
- Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning
- Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS
- BRP-NAS: Prediction-based NAS using GCNs
- Building powerful and equivariant graph neural networks with structural message-passing
- Byzantine Resilient Distributed Multi-Task Learning
- Calibrated Reliable Regression using Maximum Mean Discrepancy
- Calibrating CNNs for Lifelong Learning
- Calibrating Deep Neural Networks using Focal Loss
- Calibration of Shared Equilibria in General Sum Partially Observable Markov Games
- Can Graph Neural Networks Count Substructures?
- Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study
- Can I Trust My Fairness Metric? Assessing Fairness with Unlabeled Data and Bayesian Inference
- Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction
- Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?
- Can Temporal-Diﬀerence and Q-Learning Learn Representation? A Mean-Field Theory
- Can the Brain Do Backpropagation? --- Exact Implementation of Backpropagation in Predictive Coding Networks
- Cascaded Text Generation with Markov Transformers
- CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
- CASTLE: Regularization via Auxiliary Causal Graph Discovery
- Causal analysis of Covid-19 Spread in Germany
- Causal Discovery and Causality-Inspired Machine Learning
- Causal Discovery from Soft Interventions with Unknown Targets: Characterization and Learning
- Causal Discovery in Physical Systems from Videos
- Causal Estimation with Functional Confounders
- Causal Imitation Learning With Unobserved Confounders
- Causal Intervention for Weakly-Supervised Semantic Segmentation
- Causal Learning
- Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models
- Certifiably Adversarially Robust Detection of Out-of-Distribution Data
- Certified Defense to Image Transformations via Randomized Smoothing
- Certified Monotonic Neural Networks
- Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks
- Certifying Confidence via Randomized Smoothing
- Certifying Strategyproof Auction Networks
- Chaos, Extremism and Optimism: Volume Analysis of Learning in Games
- Characterizing emergent representations in a space of candidate learning rules for deep networks
- Characterizing Optimal Mixed Policies: Where to Intervene and What to Observe
- CHIP: A Hawkes Process Model for Continuous-time Networks with Scalable and Consistent Estimation
- Choice Bandits
- CircleGAN: Generative Adversarial Learning across Spherical Circles
- Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Evolvability
- Classification with Valid and Adaptive Coverage
- CLEARER: Multi-Scale Neural Architecture Search for Image Restoration
- Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow
- CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection
- COBE: Contextualized Object Embeddings from Narrated Instructional Video
- CodeCMR: Cross-Modal Retrieval For Function-Level Binary Source Code Matching
- Coded Sequential Matrix Multiplication For Straggler Mitigation
- Co-exposure Maximization in Online Social Networks
- CogLTX: Applying BERT to Long Texts
- CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models
- Coherent Hierarchical Multi-Label Classification Networks
- CoinDICE: Off-Policy Confidence Interval Estimation
- CoinPress: Practical Private Mean and Covariance Estimation
- ColdGANs: Taming Language GANs with Cautious Sampling Strategies
- Collapsing Bandits and Their Application to Public Health Intervention
- Collegial Ensembles
- ColliFlow: A Library for Executing Collaborative Intelligence Graphs
- Color Visual Illusions: A Statistics-based Computational Model
- Combining Deep Reinforcement Learning and Search for Imperfect-Information Games
- CoMIR: Contrastive Multimodal Image Representation for Registration
- Community detection in sparse time-evolving graphs with a dynamical Bethe-Hessian
- Community detection using fast low-cardinality semidefinite programming
- Compact task representations as a normative model for higher-order brain activity
- Comparator-Adaptive Convex Bandits
- Competition Track Friday
- Competition Track Saturday
- Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval
- Compositional Explanations of Neurons
- Compositional Generalization by Learning Analytical Expressions
- Compositional Generalization via Neural-Symbolic Stack Machines
- Compositional Visual Generation with Energy Based Models
- Compositional Zero-Shot Learning via Fine-Grained Dense Feature Composition
- Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection
- Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding
- CompRess: Self-Supervised Learning by Compressing Representations
- Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programming
- Conditioning and Processing: Techniques to Improve Information-Theoretic Generalization Bounds
- Confidence sequences for sampling without replacement
- Conformal Symplectic and Relativistic Optimization
- Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning
- Conic Descent and its Application to Memory-efficient Optimization over Positive Semidefinite Matrices
- Consequences of Misaligned AI
- Consequential Decisions in Dynamic Environments
- Conservative Q-Learning for Offline Reinforcement Learning
- Consistency Regularization for Certified Robustness of Smoothed Classifiers
- Consistent Estimation of Identifiable Nonparametric Mixture Models from Grouped Observations
- Consistent feature selection for analytic deep neural networks
- Consistent Plug-in Classifiers for Complex Objectives and Constraints
- Consistent Structural Relation Learning for Zero-Shot Segmentation
- Constant-Expansion Suffices for Compressed Sensing with Generative Priors
- Constrained episodic reinforcement learning in concave-convex and knapsack settings
- Constraining Variational Inference with Geometric Jensen-Shannon Divergence
- Content Provider Dynamics and Coordination in Recommendation Ecosystems
- Contextual Games: Multi-Agent Learning with Side Information
- Contextual Reserve Price Optimization in Auctions via Mixed Integer Programming
- Continual Deep Learning by Functional Regularisation of Memorable Past
- Continual Learning in Low-rank Orthogonal Subspaces
- Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks
- Continual Learning of Control Primitives : Skill Discovery via Reset-Games
- Continual Learning with Node-Importance based Adaptive Group Sparse Regularization
- Continuous Meta-Learning without Tasks
- Continuous Object Representation Networks: Novel View Synthesis without Target View Supervision
- Continuous Regularized Wasserstein Barycenters
- Continuous Submodular Maximization: Beyond DR-Submodularity
- Continuous Surface Embeddings
- ContraGAN: Contrastive Learning for Conditional Image Generation
- Contrastive learning of global and local features for medical image segmentation with limited annotations
- Contrastive Learning with Adversarial Examples
- ConvBERT: Improving BERT with Span-based Dynamic Convolution
- Convergence and Stability of Graph Convolutional Networks on Large Random Graphs
- Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters
- Convex optimization based on global lower second-order models
- Convolutional Generation of Textured 3D Meshes
- Convolutional Tensor-Train LSTM for Spatio-Temporal Learning
- Cooperative AI
- Cooperative Heterogeneous Deep Reinforcement Learning
- Cooperative Multi-player Bandit Optimization
- CO-Optimal Transport
- COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning
- COPT: Coordinated Optimal Transport on Graphs
- Coreference Resolution for Neutralizing Gendered Pronouns
- Coresets for Near-Convex Functions
- Coresets for Regressions with Panel Data
- Coresets for Robust Training of Deep Neural Networks against Noisy Labels
- Coresets via Bilevel Optimization for Continual Learning and Streaming
- Correlation Robust Influence Maximization
- Correspondence learning via linearly-invariant embedding
- CoSE: Compositional Stroke Embeddings
- COT-GAN: Generating Sequential Data via Causal Optimal Transport
- Co-Tuning for Transfer Learning
- Counterexample-Guided Learning of Monotonic Neural Networks
- Counterfactual Contrastive Learning for Weakly-Supervised Vision-Language Grounding
- Counterfactual Data Augmentation using Locally Factored Dynamics
- Counterfactual Prediction for Bundle Treatment
- Counterfactual Predictions under Runtime Confounding
- Counterfactual Vision-and-Language Navigation: Unravelling the Unseen
- Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators
- Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search
- Critic Regularized Regression
- Cross-lingual Retrieval for Iterative Self-Supervised Training
- Cross-Scale Internal Graph Neural Network for Image Super-Resolution
- CrossTransformers: spatially-aware few-shot transfer
- Cross-validation Confidence Intervals for Test Error
- Crowd Science Workshop: Remoteness, Fairness, and Mechanisms as Challenges of Data Supply by Humans for Automation
- Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality
- CryptoNAS: Private Inference on a ReLU Budget
- CSER: Communication-efficient SGD with Error Reset
- CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
- Curriculum By Smoothing
- Curriculum Learning by Dynamic Instance Hardness
- Curriculum learning for multilevel budgeted combinatorial problems
- Curvature Regularization to Prevent Distortion in Graph Embedding
- Cycle-Contrast for Self-Supervised Video Representation Learning
- DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks
- Dark Experience for General Continual Learning: a Strong, Simple Baseline
- Data Diversification: A Simple Strategy For Neural Machine Translation
- De-Anonymizing Text by Fingerprinting Language Generation
- Debiased Contrastive Learning
- Debiasing Averaged Stochastic Gradient Descent to handle missing values
- Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization
- Debugging Tests for Model Explanations
- Decentralized Accelerated Proximal Gradient Descent
- Decentralized Langevin Dynamics for Bayesian Learning
- Decentralized TD Tracking with Linear Function Approximation and its Finite-Time Analysis
- Decision-Making with Auto-Encoding Variational Bayes
- Decisions, Counterfactual Explanations and Strategic Behavior
- Decision trees as partitioning machines to characterize their generalization properties
- Deep active inference agents using Monte-Carlo methods
- Deep Archimedean Copulas
- Deep Automodulators
- Deep Diffusion-Invariant Wasserstein Distributional Classification
- Deep Direct Likelihood Knockoffs
- Deep Energy-based Modeling of Discrete-Time Physics
- Deep Evidential Regression
- Deep Graph Pose: a semi-supervised deep graphical model for improved animal pose tracking
- DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs
- Deep Imitation Learning for Bimanual Robotic Manipulation
- Deep Inverse Q-learning with Constraints
- Deep Learning through Information Geometry
- Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel
- Deeply Learned Spectral Total Variation Decomposition
- Deep Metric Learning with Spherical Embedding
- Deep Multimodal Fusion by Channel Exchanging
- DeepRacing AI - Autonomous Motorsport Racing
- Deep Rao-Blackwellised Particle Filters for Time Series Forecasting
- Deep reconstruction of strange attractors from time series
- Deep Reinforcement and InfoMax Learning
- Deep Reinforcement Learning
- Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games
- Deep Relational Topic Modeling via Graph Poisson Gamma Belief Network
- Deep Shells: Unsupervised Shape Correspondence with Optimal Transport
- Deep Smoothing of the Implied Volatility Surface
- Deep Statistical Solvers
- Deep Structural Causal Models for Tractable Counterfactual Inference
- Deep Subspace Clustering with Data Augmentation
- DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
- Deep Transformation-Invariant Clustering
- Deep Transformers with Latent Depth
- Deep Variational Instance Segmentation
- Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring
- Delay and Cooperation in Nonstochastic Linear Bandits
- Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians
- Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation
- Demixed shared component analysis of neural population data from multiple brain areas
- Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases
- Demystifying Orthogonal Monte Carlo and Beyond
- Denoised Smoothing: A Provable Defense for Pretrained Classifiers
- Denoising Diffusion Probabilistic Models
- Dense Correspondences between Human Bodies via Learning Transformation Synchronization on Graphs
- Depth Uncertainty in Neural Networks
- (De)Randomized Smoothing for Certifiable Defense against Patch Attacks
- Design Space for Graph Neural Networks
- Detecting Hands and Recognizing Physical Contact in the Wild
- Detecting Interactions from Neural Networks via Topological Analysis
- Detection as Regression: Certified Object Detection with Median Smoothing
- Deterministic Approximation for Submodular Maximization over a Matroid in Nearly Linear Time
- Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data
- Differentiable Augmentation for Data-Efficient GAN Training
- Differentiable Causal Discovery from Interventional Data
- Differentiable computer vision, graphics, and physics in machine learning
- Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization
- Differentiable Meta-Learning of Bandit Policies
- Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement
- Differentiable Top-k with Optimal Transport
- Differential Geometry meets Deep Learning (DiffGeo4DL)
- Differentially Private Clustering: Tight Approximation Ratios
- Differentially-Private Federated Linear Bandits
- DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling
- Digraph Inception Convolutional Networks
- Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures
- Directional convergence and alignment in deep learning
- Directional Pruning of Deep Neural Networks
- Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces
- Dirichlet Graph Variational Autoencoder
- DisARM: An Antithetic Gradient Estimator for Binary Latent Variables
- DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction
- Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation
- Discovering conflicting groups in signed networks
- Discovering Reinforcement Learning Algorithms
- Discovering Symbolic Models from Deep Learning with Inductive Biases
- Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching
- Disentangling by Subspace Diffusion
- Disentangling Human Error from Ground Truth in Segmentation of Medical Images
- DISK: Learning local features with policy gradient
- Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation
- Dissecting Neural ODEs
- Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning
- Distributed Distillation for On-Device Learning
- Distributed Newton Can Communicate Less and Resist Byzantine Workers
- Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
- Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning
- Distributionally Robust Federated Averaging
- Distributionally Robust Local Non-parametric Conditional Estimation
- Distributionally Robust Parametric Maximum Likelihood Estimation
- Distributional Robustness with IPMs and links to Regularization and GANs
- Distribution-free binary classification: prediction sets, confidence intervals and calibration
- Distribution Matching for Crowd Counting
- Diverse Image Captioning with Context-Object Split Latent Spaces
- Diversity can be Transferred: Output Diversification for White- and Black-box Attacks
- Diversity-Guided Multi-Objective Bayesian Optimization With Batch Evaluations
- Do Adversarially Robust ImageNet Models Transfer Better?
- Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
- Domain Adaptation as a Problem of Inference on Graphical Models
- Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
- Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization
- Domain Generalization via Entropy Regularization
- Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies
- Dual-Free Stochastic Decentralized Optimization with Variance Reduction
- Dual Instrumental Variable Regression
- Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion
- Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks
- Dual-Resolution Correspondence Networks
- Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning
- DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
- DynaBERT: Dynamic BERT with Adaptive Width and Depth
- Dynamic allocation of limited memory resources in reinforcement learning
- Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification
- Dynamic Fusion of Eye Movement Data and Verbal Narrations in Knowledge-rich Domains
- Dynamic Regret of Convex and Smooth Functions
- Dynamic Regret of Policy Optimization in Non-Stationary Environments
- Dynamic Submodular Maximization
- Early-Learning Regularization Prevents Memorization of Noisy Labels
- EcoLight: Intersection Control in Developing Regions Under Extreme Budget and Network Constraints
- Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization
- Effective Diversity in Population Based Reinforcement Learning
- Efficient active learning of sparse halfspaces with arbitrary bounded noise
- Efficient Algorithms for Device Placement of DNN Graph Operators
- Efficient Clustering Based On A Unified View Of K-means And Ratio-cut
- Efficient Clustering for Stretched Mixtures: Landscape and Optimality
- Efficient Contextual Bandits with Continuous Actions
- Efficient Distance Approximation for Structured High-Dimensional Distributions via Learning
- Efficient estimation of neural tuning during naturalistic behavior
- Efficient Exact Verification of Binarized Neural Networks
- Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization
- Efficient Generation of Structured Objects with Constrained Adversarial Networks
- Efficient Learning of Discrete Graphical Models
- Efficient Learning of Generative Models via Finite-Difference Score Matching
- Efficient Low Rank Gaussian Variational Inference for Neural Networks
- Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity
- Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning
- Efficient Nonmyopic Bayesian Optimization via One-Shot Multi-Step Trees
- Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent
- Efficient Planning in Large MDPs with Weak Linear Function Approximation
- Efficient Projection-free Algorithms for Saddle Point Problems
- Efficient semidefinite-programming-based inference for binary and multi-class MRFs
- Efficient Variational Inference for Sparse Deep Learning with Theoretical Guarantee
- Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data
- Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks
- Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design
- Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences
- Empirical Likelihood for Contextual Bandits
- Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
- End-to-End Learning and Intervention in Games
- Energy-based Out-of-distribution Detection
- Ensemble Distillation for Robust Model Fusion in Federated Learning
- Ensembling geophysical models with Bayesian Neural Networks
- Ensuring Fairness Beyond the Training Data
- Entropic Causal Inference: Identifiability and Finite Sample Results
- Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form
- Entrywise convergence of iterative methods for eigenproblems
- Equivariant Networks for Hierarchical Structures
- Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs
- Error Bounds of Imitating Policies and Environments
- Escaping Saddle-Point Faster under Interpolation-like Conditions
- Escaping the Gravitational Pull of Softmax
- Estimating decision tree learnability with polylogarithmic sample complexity
- Estimating Fluctuations in Neural Representations of Uncertain Environments
- Estimating Rank-One Spikes from Heavy-Tailed Noise via Self-Avoiding Walks
- Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks
- Estimating Training Data Influence by Tracing Gradient Descent
- Estimating weighted areas under the ROC curve
- Estimation and Imputation in Probabilistic Principal Component Analysis with Missing Not At Random Data
- Estimation of Skill Distribution from a Tournament
- Evaluating and Rewarding Teamwork Using Cooperative Game Abstractions
- Evaluating Attribution for Graph Neural Networks
- Every View Counts: Cross-View Consistency in 3D Object Detection with Hybrid-Cylindrical-Spherical Voxelization
- Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders
- EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning
- Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation
- Evolving Normalization-Activation Layers
- Exact expressions for double descent and implicit regularization via surrogate random design
- Exactly Computing the Local Lipschitz Constant of ReLU Networks
- Exact Recovery of Mangled Clusters with Same-Cluster Queries
- Exchangeable Neural ODE for Set Modeling
- Exemplar Guided Active Learning
- Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation
- ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks
- Experimental design for MRI by greedy policy search
- Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation
- Explainable Voting
- Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay
- Explicit Regularisation in Gaussian Noise Injections
- Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits
- Exploiting MMD and Sinkhorn Divergences for Fair and Transferable Representation Learning
- Exploiting the Surrogate Gap in Online Multiclass Classification
- Exploiting weakly supervised visual patterns to learn from partial annotations
- Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling
- Exponential ergodicity of mirror-Langevin diffusions
- Extrapolation Towards Imaginary 0-Nearest Neighbour and Its Improved Convergence Rate
- Factor Graph Grammars
- Factor Graph Neural Networks
- Factorizable Graph Convolutional Networks
- Factorized Neural Processes for Neural Processes: K-Shot Prediction of Neural Responses
- Fair AI in Finance
- Fair Hierarchical Clustering
- Fair Multiple Decision Making Through Soft Interventions
- Fairness constraints can help exact inference in structured prediction
- Fairness in Streaming Submodular Maximization: Algorithms and Hardness
- Fairness without Demographics through Adversarially Reweighted Learning
- Fairness with Overlapping Groups; a Probabilistic Perspective
- Fair Performance Metric Elicitation
- Fair regression via plug-in estimator and recalibration with statistical guarantees
- Fair regression with Wasserstein barycenters
- Faithful Embeddings for Knowledge Base Queries
- Falcon: Fast Spectral Inference on Encrypted Data
- Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation
- Fast Adaptive Non-Monotone Submodular Maximization Subject to a Knapsack Constraint
- Fast Adversarial Robustness Certification of Nearest Prototype Classifiers for Arbitrary Seminorms
- Fast and Accurate $k$-means++ via Rejection Sampling
- Fast and Automatic Visual Label Conflict Resolution
- Fast and Flexible Temporal Point Processes with Triangular Maps
- Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev
- Fast Epigraphical Projection-based Incremental Algorithms for Wasserstein Distributionally Robust Support Vector Machine
- Faster DBSCAN via subsampled similarity queries
- Faster Differentially Private Samplers via Rényi Divergence Analysis of Discretized Langevin MCMC
- Faster Randomized Infeasible Interior Point Methods for Tall/Wide Linear Programs
- Faster Wasserstein Distance Estimation with the Sinkhorn Divergence
- Fast Fourier Convolution
- Fast geometric learning with symbolic matrices
- Fast Matrix Square Roots with Applications to Gaussian Processes and Bayesian Optimization
- Fast Transformers with Clustered Attention
- Fast Unbalanced Optimal Transport on a Tree
- f-Divergence Variational Inference
- Feature Importance Ranking for Deep Learning
- Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Tests
- Federated Accelerated Stochastic Gradient Descent
- Federated Bayesian Optimization via Thompson Sampling
- Federated Principal Component Analysis
- FedSplit: an algorithmic framework for fast federated optimization
- Feedback Control Perspectives on Learning
- Few-Cost Salient Object Detection with Adversarial-Paced Learning
- Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies
- Few-shot Image Generation with Elastic Weight Consolidation
- Few-shot Visual Reasoning with Meta-Analogical Contrastive Learning
- f-GAIL: Learning f-Divergence for Generative Adversarial Imitation Learning
- Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications
- Field-wise Learning for Multi-field Categorical Data
- Fighting Copycat Agents in Behavioral Cloning from Observation Histories
- Finding All $\epsilon$-Good Arms in Stochastic Bandits
- Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems
- Finding the Homology of Decision Boundaries with Active Learning
- Fine-Grained Dynamic Head for Object Detection
- Finer Metagenomic Reconstruction via Biodiversity Optimization
- Finite Continuum-Armed Bandits
- Finite-Sample Analysis of Contractive Stochastic Approximation Using Smooth Convex Envelopes
- Finite-Time Analysis for Double Q-learning
- Finite-Time Analysis of Round-Robin Kullback-Leibler Upper Confidence Bounds for Optimal Adaptive Allocation with Multiple Plays and Markovian Rewards
- Finite Versus Infinite Neural Networks: an Empirical Study
- Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks
- First Order Constrained Optimization in Policy Space
- First-Order Methods for Large-Scale Market Equilibrium Computation
- First Workshop on Quantum Tensor Networks in Machine Learning
- Fixed-Support Wasserstein Barycenters: Computational Hardness and Fast Algorithm
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
- FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs
- Flexible mean field variational inference using mixtures of non-overlapping exponential families
- FleXOR: Trainable Fractional Quantization
- Flows for simultaneous manifold learning and density estimation
- Focus of Attention Improves Information Transfer in Visual Features
- Follow the Perturbed Leader: Optimism and Fast Parallel Algorithms for Smooth Minimax Games
- Forethought and Hindsight in Credit Assignment
- Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes
- Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
- Fourier Sparse Leverage Scores and Approximate Kernel Learning
- Fourier Spectrum Discrepancies in Deep Network Generated Images
- Fourier-transform-based attribution priors improve the interpretability and stability of deep learning models for genomics
- FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training
- From Boltzmann Machines to Neural Networks and Back Again
- From Finite to Countable-Armed Bandits
- From Predictions to Decisions: Using Lookahead Regularization
- From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering
- FrugalML: How to use ML Prediction APIs more accurately and cheaply
- Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels
- Fully Dynamic Algorithm for Constrained Submodular Optimization
- Functional Regularization for Representation Learning: A Unified Theoretical Perspective
- Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing
- Further Analysis of Outlier Detection with Deep Generative Models
- GAIT-prop: A biologically plausible learning rule derived from backpropagation of error
- Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction
- GAN Memory with No Forgetting
- GANSpace: Discovering Interpretable GAN Controls
- Gaussian Gated Linear Networks
- Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective
- GCN meets GPU: Decoupling “When to Sample” from “How to Sample”
- GCOMB: Learning Budget-constrained Combinatorial Algorithms over Billion-sized Graphs
- General Control Functions for Causal Effect Estimation from IVs
- Generalised Bayesian Filtering via Sequential Monte Carlo
- Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics
- Generalization Bound of Gradient Descent for Non-Convex Metric Learning
- Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization
- Generalized Boosting
- Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
- Generalized Hindsight for Reinforcement Learning
- Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs
- Generalized Leverage Score Sampling for Neural Networks
- General Transportability of Soft Interventions: Completeness Results
- Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning
- Generating Correct Answers for Progressive Matrices Intelligence Tests
- Generating Novelty in Open-World Multi-Agent Strategic Board Games
- Generative 3D Part Assembly via Dynamic Graph Learning
- Generative causal explanations of black-box classifiers
- Generative Neurosymbolic Machines
- Generative View Synthesis: From Single-view Semantics to Novel-view Images
- Geometric All-way Boolean Tensor Decomposition
- Geometric Dataset Distances via Optimal Transport
- Geometric Exploration for Online Control
- Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction
- Gibbs Sampling with People
- Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
- Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems
- Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology
- Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
- Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data
- GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
- Goal-directed Generation of Discrete Structures with Conditional Generative Models
- GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network
- GPS-Net: Graph-based Photometric Stereo Network
- GPU-Accelerated Primal Learning for Extremely Fast Large-Scale Classification
- GradAug: A New Regularization Method for Deep Neural Networks
- Gradient Boosted Normalizing Flows
- Gradient-EM Bayesian Meta-Learning
- Gradient Estimation with Stochastic Softmax Tricks
- Gradient Regularized V-Learning for Dynamic Treatment Regimes
- Gradient Surgery for Multi-Task Learning
- Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning
- GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
- GramGAN: Deep 3D Texture Synthesis From 2D Exemplars
- Graph Contrastive Learning with Augmentations
- Graph Cross Networks with Vertex Infomax Pooling
- Graph Geometry Interaction Learning
- Graph Information Bottleneck
- Graph Meta Learning via Local Subgraphs
- Graphon Neural Networks and the Transferability of Graph Neural Networks
- Graph Policy Network for Transferable Active Learning on Graphs
- Graph Random Neural Networks for Semi-Supervised Learning on Graphs
- Graph Stochastic Neural Networks for Semi-supervised Learning
- Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Grasps
- GreedyFool: Distortion-Aware Sparse Adversarial Attack
- Greedy inference with structure-exploiting lazy maps
- Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough
- Group Contextual Encoding for 3D Point Clouds
- Group-Fair Online Allocation in Continuous Time
- Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge
- GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators
- Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses
- Guiding Deep Molecular Optimization with Genetic Exploration
- Hamiltonian Monte Carlo using an adjoint-differentiated Laplace approximation: Bayesian inference for latent Gaussian models and beyond
- HAMLETS: Human And Model in the Loop Evaluation and Training Strategies
- Handling Missing Data with Graph Representation Learning
- Hard Example Generation by Texture Synthesis for Cross-domain Shape Similarity Learning
- Hard Negative Mixing for Contrastive Learning
- Hardness of Learning Neural Networks with Natural Weights
- Hard Shape-Constrained Kernel Machines
- Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks
- HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks
- Heavy-tailed Representations, Text Polarity Classification & Data Augmentation
- Hedging in games: Faster convergence of external and swap regrets
- Heuristic Domain Adaptation
- Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights
- Hierarchical Granularity Transfer Learning
- Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems
- Hierarchical Neural Architecture Search for Deep Stereo Matching
- Hierarchical nucleation in deep neural networks
- Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample
- Hierarchical Poset Decoding for Compositional Generalization in Language
- Hierarchical Quantized Autoencoders
- HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
- High-contrast “gaudy” images improve the training of deep neural network models of visual cortex
- High-Dimensional Bayesian Optimization via Nested Riemannian Manifolds
- High-Dimensional Contextual Policy Search with Unknown Context Rewards using Bayesian Optimization
- High-Dimensional Sparse Linear Bandits
- Higher-Order Certification For Randomized Smoothing
- Higher-Order Spectral Clustering of Directed Graphs
- High-Fidelity Generative Image Compression
- High-recall causal discovery for autocorrelated time series with latent confounders
- High-Throughput Synchronous Deep RL
- HiPPO: Recurrent Memory with Optimal Polynomial Projections
- Hitting the High Notes: Subset Selection for Maximizing Expected Order Statistics
- HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory
- H-Mem: Harnessing synaptic plasticity with Hebbian Memory Networks
- HOI Analysis: Integrating and Decomposing Human-Object Interaction
- Hold me tight! Influence of discriminative features on deep network boundaries
- How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods
- How does This Interaction Affect Me? Interpretable Attribution for Feature Interactions
- How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?
- How do fair decisions fare in long-term qualification?
- How hard is to distinguish graphs with graph neural networks?
- How many samples is a good initial point worth in Low-rank Matrix Recovery?
- How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?
- How to Characterize The Landscape of Overparameterized Convolutional Neural Networks
- How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization
- HRN: A Holistic Approach to One Class Learning
- Human in the loop dialogue systems
- Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View Consistency
- Hybrid Models for Learning to Branch
- Hybrid Variance-Reduced SGD Algorithms For Minimax Problems with Nonconvex-Linear Function
- HYDRA: Pruning Adversarially Robust Neural Networks
- HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss
- Hyperparameter Ensembles for Robustness and Uncertainty Quantification
- Hypersolvers: Toward Fast Continuous-Depth Models
- IBM Federated Learning Community Edition: An Interactive Demonstration
- ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping
- I Can’t Believe It’s Not Better! Bridging the gap between theory and empiricism in probabilistic machine learning
- ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA
- ICNet: Intra-saliency Correlation Network for Co-Saliency Detection
- IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method
- Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models
- Identifying Learning Rules From Neural Network Observables
- Identifying Mislabeled Data using the Area Under the Margin Ranking
- Identifying signal and noise structure in neural population activity with Gaussian process factor models
- ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool
- Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy
- Implicit Distributional Reinforcement Learning
- Implicit Graph Neural Networks
- Implicit Neural Representations with Periodic Activation Functions
- Implicit Rank-Minimizing Autoencoder
- Implicit Regularization and Convergence for Weight Normalization
- Implicit Regularization in Deep Learning May Not Be Explainable by Norms
- Impossibility Results for Grammar-Compressed Linear Algebra
- Improved Algorithms for Convex-Concave Minimax Optimization
- Improved Algorithms for Online Submodular Maximization via First-order Regret Bounds
- Improved Analysis of Clipping Algorithms for Non-convex Optimization
- Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nystrom method
- Improved Guarantees for k-means++ and k-means++ Parallel
- Improved Sample Complexity for Incremental Autonomous Exploration in MDPs
- Improved Schemes for Episodic Memory-based Lifelong Learning
- Improved Techniques for Training Score-Based Generative Models
- Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows
- Improving Auto-Augment via Augmentation-Wise Weight Sharing
- Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
- Improving Generalization in Reinforcement Learning with Mixture Regularization
- Improving Inference for Neural Image Compression
- Improving Local Identifiability in Probabilistic Box Embeddings
- Improving model calibration with accuracy versus uncertainty optimization
- Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention
- Improving Neural Network Training in Low Dimensional Random Bases
- Improving Online Rent-or-Buy Algorithms with Sequential Decision Making and ML Predictions
- Improving Policy-Constrained Kidney Exchange via Pre-Screening
- Improving robustness against common corruptions by covariate shift adaptation
- Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms
- Improving Sparse Vector Technique with Renyi Differential Privacy
- Incorporating BERT into Parallel Sequence Decoding with Adapters
- Incorporating Interpretable Output Constraints in Bayesian Neural Networks
- Incorporating Pragmatic Reasoning Communication into Emergent Language
- Independent Policy Gradient Methods for Competitive Reinforcement Learning
- Inductive Quantum Embedding
- Inference for Batched Bandits
- Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation
- Inferring learning rules from animal decision-making
- Influence-Augmented Online Planning for Complex Environments
- Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback
- Information theoretic limits of learning a sparse rule
- Information Theoretic Regret Bounds for Online Nonlinear Control
- Information-theoretic Task Selection for Meta-Reinforcement Learning
- Input-Aware Dynamic Backdoor Attack
- In search of robust measures of generalization
- Instance Based Approximations to Profile Maximum Likelihood
- Instance-based Generalization in Reinforcement Learning
- Instance-optimality in differential privacy via approximate inverse sensitivity mechanisms
- Instance Selection for GANs
- Instance-wise Feature Grouping
- Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients
- Interferobot: aligning an optical interferometer by a reinforcement learning agent
- Interior Point Solving for LP-based prediction+optimisation
- International Workshop on Scalability, Privacy, and Security in Federated Learning (SpicyFL 2020)
- Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs
- Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrations
- Interpretable Inductive Biases and Physically Structured Learning
- Interpretable multi-timescale models for predicting fMRI responses to continuous natural speech
- Interpretable Sequence Learning for Covid-19 Forecasting
- Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding
- Interventional Few-Shot Learning
- Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks
- Intra-Processing Methods for Debiasing Neural Networks
- Introducing Routing Uncertainty in Capsule Networks
- Inverse Learning of Symmetries
- Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics
- Inverse Reinforcement Learning from a Gradient-based Learner
- Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax
- Inverting Gradients - How easy is it to break privacy in federated learning?
- Investigating Gender Bias in Language Models Using Causal Mediation Analysis
- Is Long Horizon RL More Difficult Than Short Horizon RL?
- Is normalization indispensable for training deep neural network?
- Is Plug-in Solver Sample-Efficient for Feature-based Reinforcement Learning?
- ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding
- Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
- JAX MD: A Framework for Differentiable Physics
- Joint Contrastive Learning with Infinite Possibilities
- Joint Policy Search for Multi-agent Collaboration with Imperfect Information
- Joints in Random Forests
- Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout
- Kalman Filtering Attention for User Behavior Modeling in CTR Prediction
- Kernel Alignment Risk Estimator: Risk Prediction from Training Data
- Kernel Based Progressive Distillation for Adder Neural Networks
- Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks
- Kernel Methods Through the Roof: Handling Billions of Points Efficiently
- KFC: A Scalable Approximation Algorithm for $k$−center Fair Clustering
- Knowledge Augmented Deep Neural Networks for Joint Facial Expression and Action Unit Recognition
- Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher
- Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control
- KR2ML - Knowledge Representation and Reasoning Meets Machine Learning
- Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity
- Labelling unlabelled videos from scratch with multi-modal self-supervision
- Lamina-specific neuronal properties promote robust, stable signal propagation in feedforward networks
- Language and Visual Entity Relationship Graph for Agent Navigation
- Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration
- Language-Conditioned Imitation Learning for Robot Manipulation Tasks
- Language Models are Few-Shot Learners
- Language Through a Prism: A Spectral Approach for Multiscale Language Representations
- LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-resolution and Beyond
- Large-Scale Adversarial Training for Vision-and-Language Representation Learning
- Large-Scale Methods for Distributionally Robust Optimization
- Latent Bandits Revisited
- Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings
- Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings
- Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings
- Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings
- Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings
- Latent Template Induction with Gumbel-CRFs
- Latent World Models For Intrinsically Motivated Exploration
- Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge
- Learnability with Indirect Supervision Signals
- Learning About Objects by Learning to Interact with Them
- Learning abstract structure for drawing by efficient motor program induction
- Learning Affordance Landscapes for Interaction Exploration in 3D Environments
- Learning Agent Representations for Ice Hockey
- Learning Augmented Energy Minimization via Speed Scaling
- Learning Black-Box Attackers with Transferable Priors and Query Feedback
- Learning Bounds for Risk-sensitive Learning
- Learning by Minimizing the Sum of Ranked Range
- Learning Causal Effects via Weighted Empirical Risk Minimization
- Learning Certified Individually Fair Representations
- Learning Composable Energy Surrogates for PDE Order Reduction
- Learning compositional functions via multiplicative weight updates
- Learning Compositional Rules via Neural Program Synthesis
- Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
- Learning Deep Attribution Priors Based On Prior Knowledge
- Learning Deformable Tetrahedral Meshes for 3D Reconstruction
- Learning Differentiable Programs with Admissible Neural Heuristics
- Learning Differential Equations that are Easy to Solve
- Learning discrete distributions: user vs item-level privacy
- Learning discrete distributions with infinite support
- Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration
- Learning Disentangled Representations and Group Structure of Dynamical Environments
- Learning Disentangled Representations of Videos with Missing Data
- Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction
- Learning Dynamic Belief Graphs to Generalize on Text-Based Games
- Learning efficient task-dependent representations with synaptic plasticity
- Learning Feature Sparse Principal Subspace
- Learning from Aggregate Observations
- Learning from Failure: De-biasing Classifier from Biased Classifier
- Learning from Label Proportions: A Mutual Contamination Framework
- Learning from Mixtures of Private and Public Populations
- Learning from Positive and Unlabeled Data with Arbitrary Positive Shift
- Learning Global Transparent Models consistent with Local Contrastive Explanations
- Learning Graph Structure With A Finite-State Automaton Layer
- Learning Guidance Rewards with Trajectory-space Smoothing
- Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE
- Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning
- Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence
- Learning Individually Inferred Communication for Multi-Agent Cooperation
- Learning Invariances in Neural Networks from Training Data
- Learning Invariants through Soft Unification
- Learning Kernel Tests Without Data Splitting
- Learning Latent Space Energy-Based Prior Model
- Learning Linear Programs from Optimal Decisions
- Learning Loss for Test-Time Augmentation
- Learning Manifold Implicitly via Explicit Heat-Kernel Learning
- Learning Meaningful Representations of Life (LMRL.org)
- Learning Meets Combinatorial Algorithms
- Learning Multi-Agent Communication through Structured Attentive Reasoning
- Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks
- Learning Mutational Semantics
- Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views
- Learning of Discrete Graphical Models with Neural Networks
- Learning Optimal Representations with the Decodable Information Bottleneck
- Learning outside the Black-Box: The pursuit of interpretable models
- Learning Parities with Neural Networks
- Learning Physical Constraints with Neural Projections
- Learning Physical Graph Representations from Visual Scenes
- Learning Representations from Audio-Visual Spatial Alignment
- Learning Restricted Boltzmann Machines with Sparse Latent Variables
- Learning Retrospective Knowledge with Reverse Reinforcement Learning
- Learning Rich Rankings
- Learning Robust Decision Policies from Observational Data
- Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search
- Learning Semantic-aware Normalization for Generative Adversarial Networks
- Learning Some Popular Gaussian Graphical Models without Condition Number Bounds
- Learning sparse codes from compressed representations with biologically plausible local wiring constraints
- Learning Sparse Prototypes for Text Generation
- Learning Strategic Network Emergence Games
- Learning Strategy-Aware Linear Classifiers
- Learning Structured Distributions From Untrusted Batches: Faster and Simpler
- Learning the Geometry of Wave-Based Imaging
- Learning the Linear Quadratic Regulator from Nonlinear Observations
- Learning to Adapt to Evolving Domains
- Learning to Approximate a Bregman Divergence
- Learning to Decode: Reinforcement Learning for Decoding of Sparse Graph-Based Channel Codes
- Learning to Detect Objects with a 1 Megapixel Event Camera
- Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning
- Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
- Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
- Learning to Incentivize Other Learning Agents
- Learning to Learn Variational Semantic Memory
- Learning to Learn with Feedback and Local Plasticity
- Learning to Mutate with Hypergradient Guided Population
- Learning to Orient Surfaces by Self-supervised Spherical CNNs
- Learning to Play No-Press Diplomacy with Best Response Policy Iteration
- Learning to Play Sequential Games versus Unknown Opponents
- Learning to Prove Theorems by Learning to Generate Theorems
- Learning to search efficiently for causally near-optimal treatments
- Learning to Select Best Forecast Tasks for Clinical Outcome Prediction
- Learning to solve TV regularised problems with unrolled algorithms
- Learning to summarize with human feedback
- Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping
- Learning under Model Misspecification: Applications to Variational and Ensemble methods
- Learning Utilities and Equilibria in Non-Truthful Auctions
- Learning with Differentiable Pertubed Optimizers
- Learning with Operator-valued Kernels in Reproducing Kernel Krein Spaces
- Learning with Optimized Random Features: Exponential Speedup by Quantum Machine Learning without Sparsity and Low-Rank Assumptions
- Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms
- Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning
- Leveraging Predictions in Smoothed Online Convex Optimization via Gradient-based Algorithms
- Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations
- Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting
- Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation
- Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
- Limits on Testing Structural Changes in Ising Models
- Limits to Depth Efficiencies of Self-Attention
- Linear Disentangled Representations and Unsupervised Action Estimation
- Linear Dynamical Systems as a Core Computational Primitive
- Linearly Converging Error Compensated SGD
- Linear-Sample Learning of Low-Rank Distributions
- Linear Time Sinkhorn Divergences using Positive Features
- Lipschitz Bounds and Provably Robust Training by Laplacian Smoothing
- Lipschitz-Certifiable Training with a Tight Outer Bound
- List-Decodable Mean Estimation via Iterative Multi-Filtering
- Listening to Sounds of Silence for Speech Denoising
- LMdiff: A Visual Diff Tool to Compare LanguageModels
- Locally-Adaptive Nonparametric Online Learning
- Locally Differentially Private (Contextual) Bandits Learning
- Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms
- LoCo: Local Contrastive Representation Learning
- Logarithmic Pruning is All You Need
- Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems
- Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment
- Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
- Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
- Look-ahead Meta Learning for Continual Learning
- LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration
- Low Distortion Block-Resampling with Spatially Stochastic Networks
- Lower Bounds and Optimal Algorithms for Personalized Federated Learning
- Machine Learning and the Physical Sciences
- Machine Learning for Autonomous Driving
- Machine Learning for Creativity and Design 4.0
- Machine Learning for Economic Policy
- Machine Learning for Engineering Modeling, Simulation and Design
- Machine Learning for Health (ML4H): Advancing Healthcare for All
- Machine Learning for Mobile Health
- Machine Learning for Molecules
- Machine Learning for Structural Biology
- Machine Learning for Systems
- Machine Learning for the Developing World (ML4D): Improving Resilience
- Make One-Shot Video Object Segmentation Efficient Again
- Making Non-Stochastic Control (Almost) as Easy as Stochastic
- Manifold GPLVMs for discovering non-Euclidean latent structure in neural data
- Manifold structure in graph embeddings
- Marginal Utility for Planning in Continuous or Large Discrete Action Spaces
- Margins are Insufficient for Explaining Gradient Boosting
- Markovian Score Climbing: Variational Inference with KL(p||q)
- MATE: Plugging in Model Awareness to Task Embedding for Meta Learning
- Matérn Gaussian Processes on Riemannian Manifolds
- Matrix Completion with Hierarchical Graph Side Information
- Matrix Completion with Quantified Uncertainty through Low Rank Gaussian Copula
- Matrix Inference and Estimation in Multi-Layer Models
- Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness
- MCUNet: Tiny Deep Learning on IoT Devices
- MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
- Measuring Robustness to Natural Distribution Shifts in Image Classification
- Measuring Systematic Generalization in Neural Proof Generation with Transformers
- Medical Imaging Meets NeurIPS
- Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards
- Memory-Efficient Learning of Stable Linear Dynamical Systems for Prediction and Control
- MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler
- MeshSDF: Differentiable Iso-Surface Extraction
- Meta-Consolidation for Continual Learning
- Meta-Gradient Reinforcement Learning with an Objective Discovered Online
- Meta-Learning
- Meta-learning from Tasks with Heterogeneous Attribute Spaces
- Meta-Learning Requires Meta-Augmentation
- Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes
- Meta-Learning through Hebbian Plasticity in Random Networks
- Meta-Learning with Adaptive Hyperparameters
- Meta-Neighborhoods
- MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
- MetaPoison: Practical General-purpose Clean-label Data Poisoning
- MetaSDF: Meta-Learning Signed Distance Functions
- Meta-trained agents implement Bayes-optimal agents
- Metric-Free Individual Fairness in Online Learning
- Minibatch Stochastic Approximate Proximal Point Methods
- Minibatch vs Local SGD for Heterogeneous Distributed Learning
- MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers
- Minimax Bounds for Generalized Linear Models
- Minimax Classification with 0-1 Loss and Performance Guarantees
- Minimax Dynamics of Optimally Balanced Spiking Networks of Excitatory and Inhibitory Neurons
- Minimax Estimation of Conditional Moment Models
- Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks
- Minimax Optimal Nonparametric Estimation of Heterogeneous Treatment Effects
- Minimax Regret of Switching-Constrained Online Convex Optimization: No Phase Transition
- Minimax Value Interval for Off-Policy Evaluation and Policy Optimization
- MinMax Methods for Optimal Transport and Beyond: Regularization, Approximation and Numerics
- Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization
- Mitigating Manipulation in Peer Review via Randomized Reviewer Assignments
- Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions
- Mixed Hamiltonian Monte Carlo for Mixed Discrete and Continuous Variables
- ML Competitions at the Grassroots (CiML 2020)
- MLPH: Machine Learning in Public Health
- ML Retrospectives, Surveys & Meta-Analyses (ML-RSA)
- MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles
- Model Agnostic Multilevel Explanations
- Model-based Adversarial Meta-Reinforcement Learning
- Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity
- Model-based Policy Optimization with Unsupervised Model Adaptation
- Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs
- Model Class Reliance for Random Forests
- Model Fusion via Optimal Transport
- Modeling and Optimization Trade-off in Meta-learning
- Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows
- Modeling Noisy Annotations for Crowd Counting
- Modeling Shared responses in Neuroimaging Studies through MultiView ICA
- Modeling Task Effects on Meaning Representation in the Brain via Zero-Shot MEG Prediction
- Model Interpretability through the Lens of Computational Complexity
- Model Inversion Networks for Model-Based Optimization
- Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets
- Model Selection for Production System via Automated Online Experiments
- Model Selection in Contextual Stochastic Bandit Problems
- Modern Hopfield Networks and Attention for Immune Repertoire Classification
- Modular Meta-Learning with Shrinkage
- MolDesigner: Interactive Design of Efficacious Drugs with Deep Learning
- MomentumRNN: Integrating Momentum into Recurrent Neural Networks
- MONICA: MObile Neural voIce Command Assistant for mobile games
- Monotone operator equilibrium networks
- MOPO: Model-based Offline Policy Optimization
- MOReL: Model-Based Offline Reinforcement Learning
- MosAIc: Finding Artistic Connections across Culture with Conditional Image Retrieval
- Most ReLU Networks Suffer from $\ell^2$ Adversarial Perturbations
- Movement Pruning: Adaptive Sparsity by Fine-Tuning
- MPNet: Masked and Permuted Pre-training for Language Understanding
- MRI Banding Removal via Adversarial Training
- Multi-agent active perception with prediction rewards
- Multi-agent Trajectory Prediction with Fuzzy Query Attention
- Multifaceted Uncertainty Estimation for Label-Efficient Deep Learning
- Multi-Fidelity Bayesian Optimization via Deep Neural Networks
- Multilabel Classification by Hierarchical Partitioning and Data-dependent Grouping
- Multi-label classification: do Hamming loss and subset accuracy really conflict with each other?
- Multi-label Contrastive Predictive Coding
- Multimodal Generative Learning Utilizing Jensen-Shannon-Divergence
- Multimodal Graph Networks for Compositional Generalization in Visual Question Answering
- MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation
- Multiparameter Persistence Image for Topological Machine Learning
- Multi-Plane Program Induction with 3D Box Priors
- Multipole Graph Neural Operator for Parametric Partial Differential Equations
- Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates
- Multiscale Deep Equilibrium Models
- Multi-Stage Influence Function
- Multi-task Additive Models for Robust Estimation and Automatic Structure Discovery
- Multi-task Batch Reinforcement Learning with Metric Learning
- Multi-task Causal Learning with Gaussian Processes
- Multi-Task Reinforcement Learning with Soft Modularization
- Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement
- Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance
- Munchausen Reinforcement Learning
- MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Models
- Musical Speech: A Transformer-based Composition Tool
- Mutual exclusivity as a challenge for deep neural networks
- Myersonian Regression
- NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity
- Natural Graph Networks
- Natural Policy Gradient Primal-Dual Method for Constrained Markov Decision Processes
- Navigating the Broader Impacts of AI Research
- Near-Optimal Comparison Based Clustering
- Near-Optimal Reinforcement Learning with Self-Play
- Near-Optimal SQ Lower Bounds for Agnostically Learning Halfspaces and ReLUs under Gaussian Marginals
- Network Diffusions via Neural Mean-Field Dynamics
- Network size and size of the weights in memorization with two-layers neural networks
- Network-to-Network Translation with Conditional Invertible Neural Networks
- NeuMiss networks: differentiable programming for supervised learning with missing values.
- Neural Anisotropy Directions
- Neural Architecture Generator Optimization
- Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systems
- Neural Complexity Measures
- Neural Controlled Differential Equations for Irregular Time Series
- Neural Dynamic Policies for End-to-End Sensorimotor Learning
- Neural encoding with visual attention
- Neural Execution Engines: Learning to Execute Subroutines
- Neural FFTs for Universal Texture Image Synthesis
- Neural Manifold Ordinary Differential Equations
- Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows
- Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs
- Neural Methods for Point-wise Dependency Estimation
- Neural Networks Fail to Learn Periodic Functions and How to Fix It
- Neural Networks Learning and Memorization with (almost) no Over-Parameterization
- Neural Networks with Recurrent Generative Feedback
- Neural Networks with Small Weights and Depth-Separation Barriers
- Neural Non-Rigid Tracking
- Neural Path Features and Neural Path Kernel : Understanding the role of gates in deep learning
- Neural Power Units
- Neural Sparse Representation for Image Restoration
- Neural Sparse Voxel Fields
- Neural Star Domain as Primitive Representation
- Neural Topographic Factor Analysis for fMRI Data
- Neural Unsigned Distance Fields for Implicit Function Learning
- Neuronal Gaussian Process Regression
- Neuron-level Structured Pruning using Polarization Regularizer
- Neuron Merging: Compensating for Pruned Neurons
- Neuron Shapley: Discovering the Responsible Neurons
- Neurosymbolic Reinforcement Learning with Formally Verified Exploration
- Neurosymbolic Transformers for Multi-Agent Communication
- Neutralizing Self-Selection Bias in Sampling for Sortition
- Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning
- Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding
- Node Embeddings and Exact Low-Rank Representations of Complex Networks
- Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising
- Noise-Contrastive Estimation for Multivariate Point Processes
- Nonasymptotic Guarantees for Spiked Matrix Recovery with Generative Priors
- Non-Convex SGD Learns Halfspaces with Adversarial Label Noise
- Nonconvex Sparse Graph Learning under Laplacian Constrained Graphical Model
- Non-Crossing Quantile Regression for Distributional Reinforcement Learning
- Non-Euclidean Universal Approximation
- Non-parametric Models for Non-negative Functions
- Non-reversible Gaussian processes for identifying latent dynamical structure in neural data
- Non-Stochastic Control with Bandit Feedback
- No-Regret Learning and Mixed Nash Equilibria: They Do Not Mix
- No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium
- No-regret Learning in Price Competitions under Consumer Reference Effects
- Normalizing Kalman Filters for Multivariate Time Series Analysis
- No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems
- Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning
- Novelty Search in Representational Space for Sample Efficient Exploration
- Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning
- NVAE: A Deep Hierarchical Variational Autoencoder
- Object-Centric Learning with Slot Attention
- Object Goal Navigation using Goal-Oriented Semantic Exploration
- Object Representations for Learning and Reasoning
- Ode to an ODE
- Offline Imitation Learning with a Misspecified Simulator
- Offline Reinforcement Learning
- Off-Policy Evaluation and Learning for External Validity under a Covariate Shift
- Off-Policy Evaluation via the Regularized Lagrangian
- Off-Policy Imitation Learning from Observations
- Off-Policy Interval Estimation with Lipschitz Value Iteration
- Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding
- On 1/n neural representation and robustness
- On Adaptive Attacks to Adversarial Example Defenses
- On Adaptive Distance Estimation
- Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free
- On Completeness-aware Concept-Based Explanations in Deep Neural Networks
- O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers
- On Convergence and Generalization of Dropout Training
- On Convergence of Nearest Neighbor Classifiers over Feature Transformations
- On Correctness of Automatic Differentiation for Non-Differentiable Functions
- One-bit Supervision for Image Classification
- On Efficiency in Hierarchical Reinforcement Learning
- One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers
- One-sample Guided Object Representation Disassembling
- One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL
- On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces
- On Infinite-Width Hypernetworks
- On Learning Ising Models under Huber's Contamination Model
- Online Adaptation for Consistent Mesh Reconstruction in the Wild
- Online Agnostic Boosting via Regret Minimization
- Online Algorithm for Unsupervised Sequential Selection with Contextual Information
- Online Algorithms for Multi-shop Ski Rental with Machine Learned Advice
- Online Bayesian Goal Inference for Boundedly Rational Planning Agents
- Online Bayesian Persuasion
- Online Convex Optimization Over Erdos-Renyi Random Networks
- Online Decision Based Visual Tracking via Reinforcement Learning
- Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning
- Online Influence Maximization under Linear Threshold Model
- Online Learning in Contextual Bandits using Gated Linear Networks
- Online learning with dynamics: A minimax perspective
- Online Learning with Primary and Secondary Losses
- Online Linear Optimization with Many Hints
- Online MAP Inference of Determinantal Point Processes
- Online Matrix Completion with Side Information
- Online Meta-Critic Learning for Off-Policy Actor-Critic Methods
- Online Multitask Learning with Long-Term Memory
- Online Neural Connectivity Estimation with Noisy Group Testing
- Online Non-Convex Optimization with Imperfect Feedback
- Online Optimization with Memory and Competitive Control
- Online Planning with Lookahead Policies
- Online Robust Regression via SGD on the l1 loss
- Online Sinkhorn: Optimal Transport distances from sample streams
- Online Structured Meta-learning
- On Numerosity of Deep Neural Networks
- On Power Laws in Deep Ensembles
- On ranking via sorting by estimated expected utility
- On Regret with Multiple Best Arms
- On Reward-Free Reinforcement Learning with Linear Function Approximation
- On Second Order Behaviour in Augmented Neural ODEs
- On Testing of Samplers
- On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems
- On the Convergence of Smooth Regularized Approximate Value Iteration Schemes
- On the distance between two neural networks and the stability of learning
- On the Equivalence between Online and Private Learnability beyond Binary Classification
- On the equivalence of molecular graph convolution and molecular wave function with poor basis set
- On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method
- On the Error Resistance of Hinge-Loss Minimization
- On the Expressiveness of Approximate Inference in Bayesian Neural Networks
- On the linearity of large non-linear models: when and why the tangent kernel is constant
- On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them
- On the Modularity of Hypernetworks
- On the Optimal Weighted $\ell_2$ Regularization in Overparameterized Linear Regression
- On the Power of Louvain in the Stochastic Block Model
- On the Role of Sparsity and DAG Constraints for Learning Linear DAGs
- On the Similarity between the Laplace and Neural Tangent Kernels
- On the Stability and Convergence of Robust Adversarial Reinforcement Learning: A Case Study on Linear Quadratic Systems
- On the Theory of Transfer Learning: The Importance of Task Diversity
- On the Tightness of Semidefinite Relaxations for Certifying Robustness to Adversarial Examples
- On the Trade-off between Adversarial and Backdoor Robustness
- On the training dynamics of deep networks with $L_2$ regularization
- On the universality of deep learning
- On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law
- On Uniform Convergence and Low-Norm Interpolation Learning
- On Warm-Starting Neural Network Training
- OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification
- Open Graph Benchmark: Datasets for Machine Learning on Graphs
- OPT2020: Optimization for Machine Learning
- Optimal Adaptive Electrode Selection to Maximize Simultaneously Recorded Neuron Yield
- Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards
- Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization
- Optimal Approximation - Smoothness Tradeoffs for Soft-Max Functions
- Optimal Best-arm Identification in Linear Bandits
- Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization
- Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform
- Optimal Learning from Verified Training Data
- Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient
- Optimally Deceiving a Learning Leader in Stackelberg Games
- Optimal Prediction of the Number of Unseen Species with Multiplicity
- Optimal Private Median Estimation under Minimal Distributional Assumptions
- Optimal Query Complexity of Secure Stochastic Convex Optimization
- Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms
- Optimal Variance Control of the Score-Function Gradient Estimator for Importance-Weighted Bounds
- Optimal visual search based on a model of target detectability in natural images
- Optimistic Dual Extrapolation for Coherent Non-monotone Variational Inequalities
- Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks
- Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions
- Optimizing Mode Connectivity via Neuron Alignment
- Optimizing Neural Networks via Koopman Operator Theory
- OrganITE: Optimal transplant donor organ offering using an individual treatment effect
- Organizing recurrent network dynamics by task-computation to enable continual learning
- OTLDA: A Geometry-aware Optimal Transport Approach for Topic Modeling
- Outlier Robust Mean Estimation with Subgaussian Rates via Stability
- Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree
- Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality
- PAC-Bayes Analysis Beyond the Usual Bounds
- PAC-Bayesian Bound for the Conditional Value at Risk
- PAC-Bayes Learning Bounds for Sample-Dependent Priors
- Parabolic Approximation Line Search for DNNs
- Parameterized Explainer for Graph Neural Network
- Parametric Instance Classification for Unsupervised Visual Feature learning
- Part-dependent Label Noise: Towards Instance-dependent Label Noise
- Partially View-aligned Clustering
- Partial Optimal Transport with applications on Positive-Unlabeled Learning
- Passport-aware Normalization for Deep Model Protection
- Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning
- Path Integral Based Convolution and Pooling for Graph Neural Networks
- Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks
- PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning
- Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targets
- PEP: Parameter Ensembling by Perturbation
- Permute-and-Flip: A new mechanism for differentially private selection
- Personalized Federated Learning with Moreau Envelopes
- Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach
- Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability
- PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks
- Phase retrieval in high dimensions: Statistical and computational phase transitions
- PIE-NET: Parametric Inference of Point Cloud Edges
- Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games
- Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
- PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goals
- Planning in Markov Decision Processes with Gap-Dependent Sample Complexity
- Planning with General Objective Functions: Going Beyond Total Rewards
- PLANS: Neuro-Symbolic Program Learning from Videos
- PLLay: Efficient Topological Layer based on Persistent Landscapes
- Pointer Graph Networks
- Point process models for sequence detection in high-dimensional neural spike trains
- Policy Improvement via Imitation of Multiple Oracles
- POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis
- Polynomial-Time Computation of Optimal Correlated Equilibria in Two-Player Extensive-Form Games with Public Chance Moves and Beyond
- POMDPs in Continuous Time and Discrete Spaces
- POMO: Policy Optimization with Multiple Optima for Reinforcement Learning
- Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework
- Position-based Scaled Gradient for Model Quantization and Pruning
- Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
- Posterior Re-calibration for Imbalanced Datasets
- Post-training Iterative Hierarchical Data Augmentation for Deep Networks
- Practical Low-Rank Communication Compression in Decentralized Deep Learning
- Practical No-box Adversarial Attacks against DNNs
- Practical Quasi-Newton Methods for Training Deep Neural Networks
- PRANK: motion Prediction based on RANKing
- Precise expressions for random projections: Low-rank approximation and randomized Newton
- Predicting Training Time Without Training
- Prediction with Corrupted Expert Advice
- Predictive coding in balanced neural networks with noise, chaos and delays
- Predictive inference is free with the jackknife+-after-bootstrap
- Predictive Information Accelerates Learning in RL
- Preference-based Reinforcement Learning with Finite-Time Guarantees
- Preference learning along multiple criteria: A game-theoretic perspective
- Pre-training via Paraphrasing
- Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm
- Primal-Dual Mesh Convolutional Neural Networks
- Principal Neighbourhood Aggregation for Graph Nets
- Privacy Amplification via Random Check-Ins
- Privacy Preserving Machine Learning - PriML and PPML Joint Edition
- Private Identity Testing for High-Dimensional Distributions
- Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity
- Probabilistic Active Meta-Learning
- Probabilistic Circuits for Variational Inference in Discrete Graphical Models
- Probabilistic Fair Clustering
- Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations
- Probabilistic Linear Solvers for Machine Learning
- Probabilistic Orientation Estimation with Matrix Fisher Distributions
- Probabilistic Time Series Forecasting with Shape and Temporal Diversity
- Probably Approximately Correct Constrained Learning
- Probing Embedding Spaces in Deep Neural Networks
- Profile Entropy: A Fundamental Measure for the Learnability and Compressibility of Distributions
- Program Synthesis with Pragmatic Communication
- Projected Stein Variational Gradient Descent
- Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method
- Projection Robust Wasserstein Distance and Riemannian Optimization
- Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning
- Promoting Stochasticity for Expressive Policies via a Simple and Efficient Regularization Method
- Prophet Attention: Predicting Attention with Future Attention
- PrototypeML: Visual Design of Arbitrarily Complex Neural Networks
- Provable Online CP/PARAFAC Decomposition of a Structured Tensor via Dictionary Learning
- Provable Overlapping Community Detection in Weighted Graphs
- Provably adaptive reinforcement learning in metric spaces
- Provably Consistent Partial-Label Learning
- Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning
- Provably Efficient Neural Estimation of Structural Equation Models: An Adversarial Approach
- Provably Efficient Neural GTD for Off-Policy Learning
- Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits
- Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration
- Provably Good Batch Reinforcement Learning Without Great Exploration
- Provably Robust Metric Learning
- Proximal Mapping for Deep Regularization
- Proximity Operator of the Matrix Perspective Function and its Applications
- Pruning Filter in Filter
- Pruning neural networks without any data by iteratively conserving synaptic flow
- Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point
- PyGlove: Symbolic Programming for Automated Machine Learning
- Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning
- Quantifying the Empirical Wasserstein Distance to a Set of Measures: Beating the Curse of Dimensionality
- Quantile Propagation for Wasserstein-Approximate Gaussian Processes
- Quantitative Propagation of Chaos for SGD in Wide Neural Networks
- Quantized Variational Inference
- RandAugment: Practical Automated Data Augmentation with a Reduced Search Space
- Randomized tests for high-dimensional regression: A more efficient and powerful solution
- Random Reshuffling is Not Always Better
- Random Reshuffling: Simple Analysis with Vast Improvements
- Random Walk Graph Neural Networks
- RANet: Region Attention Network for Semantic Segmentation
- Rankmax: An Adaptive Projection Alternative to the Softmax Function
- Rational neural networks
- Ratio Trace Formulation of Wasserstein Discriminant Analysis
- RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning
- RD$^2$: Reward Decomposition with Representation Decomposition
- Real World Games Look Like Spinning Tops
- Reasoning about Uncertainties in Discrete-Time Dynamical Systems using Polynomial Forms.
- Reciprocal Adversarial Learning via Characteristic Functions
- Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate
- Reconsidering Generative Objectives For Counterfactual Reasoning
- Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN
- Recovery of sparse linear classifiers from mixture of responses
- Recurrent Quantum Neural Networks
- Recurrent Switching Dynamical Systems Models for Multiple Interacting Neural Populations
- Recursive Inference for Variational Autoencoders
- Reducing Adversarially Robust Learning to Non-Robust PAC Learning
- Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization
- Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals
- Regression with reject option and application to kNN
- Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses
- Regret in Online Recommendation Systems
- Regularized linear autoencoders recover the principal components, eventually
- Regularizing Black-box Models for Improved Interpretability
- Regularizing Towards Permutation Invariance In Recurrent Models
- Reinforced Molecular Optimization with Neighborhood-Controlled Grammars
- Reinforcement Learning for Control with Multiple Frequencies
- Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting
- Reinforcement Learning with Augmented Data
- Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing
- Reinforcement Learning with Feedback Graphs
- Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension
- Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D
- RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
- RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
- Relative gradient optimization of the Jacobian term in unsupervised deep learning
- Reliable Graph Neural Networks via Robust Aggregation
- Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies
- Reparameterizing Mirror Descent as Gradient Descent
- Replica-Exchange Nos\'e-Hoover Dynamics for Bayesian Learning on Large Datasets
- RepPoints v2: Verification Meets Regression for Object Detection
- Representation Learning for Integrating Multi-domain Outcomes to Optimize Individualized Treatment
- Rescuing neural spike train models from bad MLE
- Reservoir Computing meets Recurrent Kernels and Structured Transforms
- Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts
- Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis
- Resistance AI Workshop
- Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless Bandits
- Restoring Negative Information in Few-Shot Object Detection
- RetaiL: Open your own grocery store to reduce waste
- Rethinking Importance Weighting for Deep Learning under Distribution Shift
- Rethinking Learnable Tree Filter for Generic Feature Transform
- Rethinking pooling in graph neural networks
- Rethinking Pre-training and Self-training
- Rethinking the Value of Labels for Improving Class-Imbalanced Learning
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist
- Reverse-engineering recurrent neural network solutions to a hierarchical inference task for mice
- Revisiting Frank-Wolfe for Polytopes: Strict Complementarity and Sparsity
- Revisiting Parameter Sharing for Automatic Neural Channel Number Search
- Revisiting the Sample Complexity of Sparse Spectrum Approximation of Gaussian Processes
- Reward Propagation Using Graph Convolutional Networks
- Reward-rational (implicit) choice: A unifying formalism for reward learning
- Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement
- Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian
- Riemannian Continuous Normalizing Flows
- Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret
- R-learning in actor-critic model offers a biologically relevant mechanism for sequential decision-making
- RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning
- RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference
- Robust, Accurate Stochastic Optimization for Variational Inference
- Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs
- Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization
- Robust compressed sensing using generative models
- Robust Correction of Sampling Bias using Cumulative Distribution Functions
- Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations
- Robust Density Estimation under Besov IPM Losses
- Robust Disentanglement of a Few Factors at a Time using rPU-VAE
- Robust Federated Learning: The Case of Affine Distribution Shifts
- Robust Gaussian Covariance Estimation in Nearly-Matrix Multiplication Time
- Robust large-margin learning in hyperbolic space
- Robust Meta-learning for Mixed Linear Regression with Small Batches
- Robust Multi-Agent Reinforcement Learning with Model Uncertainty
- Robust Multi-Object Matching via Iterative Reweighting of the Graph Connection Laplacian
- Robustness Analysis of Non-Convex Stochastic Gradient Descent using Biased Expectations
- Robustness of Bayesian Neural Networks to Gradient-Based Attacks
- Robustness of Community Detection to Random Geometric Perturbations
- Robustness, Verification, Privacy: Addressing Machine Learning Adversaries
- Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation
- Robust Optimization for Fairness with Noisy Protected Groups
- Robust Persistence Diagrams using Reproducing Kernels
- Robust Pre-Training by Adversarial Contrastive Learning
- Robust Quantization: One Model to Rule Them All
- Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization
- Robust Recursive Partitioning for Heterogeneous Treatment Effects with Uncertainty Quantification
- Robust Reinforcement Learning via Adversarial training with Langevin Dynamics
- Robust Sequence Submodular Maximization
- Robust Sub-Gaussian Principal Component Analysis and Width-Independent Schatten Packing
- Rotated Binary Neural Network
- Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud
- RSKDD-Net: Random Sample-based Keypoint Detector and Descriptor
- SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection
- Safe Reinforcement Learning via Curriculum Induction
- Sample complexity and effective dimension for regression on manifolds
- Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction
- Sample Complexity of Uniform Convergence for Multicalibration
- Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining
- Sample-Efficient Reinforcement Learning of Undercomplete POMDPs
- Sample Efficient Reinforcement Learning via Low-Rank Matrix Estimation
- Sampling-Decomposable Generative Adversarial Recommender
- Sampling from a k-DPP without looking at all items
- Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot
- Scalable Belief Propagation via Relaxed Scheduling
- Scalable Graph Neural Networks via Bidirectional Propagation
- Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward
- ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
- Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
- SCOP: Scientific Control for Reliable Neural Network Pruning
- SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images
- SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks
- Searching for Low-Bit Weights in Quantized Neural Networks
- Second Order Optimality in Decentralized Non-Convex Optimization via Perturbed Gradient Tracking
- Second Order PAC-Bayesian Bounds for the Weighted Majority Vote
- Second Workshop on AI for Humanitarian Assistance and Disaster Response
- Secretary and Online Matching Problems with Machine Learned Advice
- Security Analysis of Safe and Seldonian Reinforcement Learning Algorithms
- See, Hear, Explore: Curiosity via Audio-Visual Association
- Self-Adaptively Learning to Demoiré from Focused and Defocused Image Pairs
- Self-Adaptive Training: beyond Empirical Risk Minimization
- Self-Distillation Amplifies Regularization in Hilbert Space
- Self-Distillation as Instance-Specific Label Smoothing
- Self-Imitation Learning via Generalized Lower Bound Q-learning
- Self-Learning Transformations for Improving Gaze and Head Redirection
- Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
- Self-Paced Deep Reinforcement Learning
- Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
- Self-supervised Co-Training for Video Representation Learning
- Self-Supervised Few-Shot Learning on Point Clouds
- Self-Supervised Generative Adversarial Compression
- Self-Supervised Graph Transformer on Large-Scale Molecular Data
- Self-Supervised Learning by Cross-Modal Audio-Video Clustering
- Self-Supervised Learning for Speech and Audio Processing
- Self-Supervised Learning -- Theory and Practice
- Self-supervised learning through the eyes of a child
- Self-Supervised MultiModal Versatile Networks
- Self-Supervised Relational Reasoning for Representation Learning
- Self-Supervised Relationship Probing
- Self-Supervised Visual Representation Learning from Hierarchical Grouping
- Self-training Avoids Using Spurious Features Under Domain Shift
- Semantic Visual Navigation by Watching YouTube Videos
- Semialgebraic Optimization for Lipschitz Constants of ReLU Networks
- Semi-Supervised Neural Architecture Search
- Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization
- Sense and Sensitivity Analysis: Simple Post-Hoc Analysis of Bias Due to Unobserved Confounding
- Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals
- Sequential Bayesian Experimental Design with Variable Cost Structure
- Set2Graph: Learning Graphs From Sets
- SEVIR : A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology
- SGD with shuffling: optimal rates without component convexity and large epoch requirements
- ShapeFlow: Learnable Deformation Flows Among 3D Shapes
- Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning
- Shared Interest: Human Annotations vs. AI Saliency
- Shared Space Transfer Learning for analyzing multi-site fMRI data
- Shared Visual Representations in Human and Machine Intelligence (SVRHM)
- Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms
- Sharper Generalization Bounds for Pairwise Learning
- Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth
- Sharp uniform convergence bounds through empirical centralization
- ShiftAddNet: A Hardware-Inspired Deep Network
- Simple and Fast Algorithm for Binary Integer and Online Linear Programming
- Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness
- Simple and Scalable Sparse k-means Clustering via Feature Ranking
- Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering
- Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints
- Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations
- Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition
- Simultaneous Preference and Metric Learning from Paired Comparisons
- Sinkhorn Barycenter via Functional Gradient Descent
- Sinkhorn Natural Gradient for Generative Models
- SIRI: Spatial Relation Induced Network For Spatial Description Resolution
- Skeleton-bridged Point Completion: From Global Inference to Local Adjustment
- Sliding Window Algorithms for k-Clustering Problems
- SLIP: Learning to Predict in Unknown Dynamical Systems with Long-Term Memory
- Small Nash Equilibrium Certificates in Very Large Games
- Smooth And Consistent Probabilistic Regression Trees
- Smoothed Analysis of Online and Differentially Private Learning
- Smoothed Geometry for Robust Attribution
- Smoothly Bounding User Contributions in Differential Privacy
- SMYRF - Efficient Attention using Asymmetric Clustering
- SnapBoost: A Heterogeneous Boosting Machine
- Soft Contrastive Learning for Visual Localization
- SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds
- Softmax Deep Double Deterministic Policy Gradients
- SOLOv2: Dynamic and Fast Instance Segmentation
- Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
- Space-Time Correspondence as a Contrastive Random Walk
- Sparse and Continuous Attention Mechanisms
- Sparse Graphical Memory for Robust Planning
- Sparse Learning with CART
- Sparse Spectrum Warped Input Measures for Nonstationary Kernel Learning
- Sparse Symplectically Integrated Neural Networks
- Sparse Weight Activation Training
- Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
- Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks
- Spike and slab variational Bayes for high dimensional logistic regression
- Spin-Weighted Spherical CNNs
- Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses
- Stable and expressive recurrent vision models
- Stage-wise Conservative Linear Bandits
- Stateful Posted Pricing with Vanishing Regret via Dynamic Deterministic Markov Decision Processes
- Stationary Activations for Uncertainty Calibration in Deep Learning
- Statistical and Topological Properties of Sliced Probability Divergences
- Statistical control for spatio-temporal MEG/EEG source imaging with desparsified mutli-task Lasso
- Statistical Efficiency of Thompson Sampling for Combinatorial Semi-Bandits
- Statistical Guarantees of Distributed Nearest Neighbor Classification
- Statistical Optimal Transport posed as Learning Kernel Embedding
- Statistical-Query Lower Bounds via Functional Gradients
- Steady State Analysis of Episodic Reinforcement Learning
- Steering Distortions to Preserve Classes and Neighbors in Supervised Dimensionality Reduction
- STEER : Simple Temporal Regularization For Neural ODE
- Stein Self-Repulsive Dynamics: Benefits From Past Samples
- STLnet: Signal Temporal Logic Enforced Multivariate Recurrent Neural Networks
- Stochastic Deep Gaussian Processes over Graphs
- Stochastic Gradient Descent in Correlated Settings: A Study on Gaussian Processes
- Stochasticity of Deterministic Gradient Descent: Large Learning Rate for Multiscale Objective Function
- Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model
- Stochastic Normalization
- Stochastic Normalizing Flows
- Stochastic Optimization for Performative Prediction
- Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping
- Stochastic Optimization with Laggard Data Pipelines
- Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems
- Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
- Stochastic Stein Discrepancies
- Storage Efficient and Dynamic Flexible Runtime Channel Pruning via Deep Reinforcement Learning
- StratLearner: Learning a Strategy for Misinformation Prevention in Social Networks
- Strictly Batch Imitation Learning by Energy-based Distribution Matching
- Strongly Incremental Constituency Parsing with Graph Neural Networks
- Strongly local p-norm-cut algorithms for semi-supervised learning and local graph clustering
- Structured Convolutions for Efficient Neural Network Design
- Structured Prediction for Conditional Meta-Learning
- Subgraph Neural Networks
- Subgroup-based Rank-1 Lattice Quasi-Monte Carlo
- Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces
- Submodular Maximization Through Barrier Functions
- Submodular Meta-Learning
- Sub-sampling for Efficient Non-Parametric Bandit Exploration
- Succinct and Robust Multi-Agent Communication With Temporal Message Control
- Sufficient dimension reduction for classification using principal optimal transport direction
- SuperLoss: A Generic Loss for Robust Curriculum Learning
- Supermasks in Superposition
- Supervised Contrastive Learning
- SURF: A Simple, Universal, Robust, Fast Distribution Learning Algorithm
- SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
- SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence
- Swapping Autoencoder for Deep Image Manipulation
- Synbols: Probing Learning Algorithms with Synthetic Datasets
- Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis
- Synthesizing Tasks for Block-based Programming
- Synthetic Data Generators -- Sequential and Private
- System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina
- Tackling Climate Change with ML
- Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
- Talking to Strangers: Zero-Shot Emergent Communication
- Taming Discrete Integration via the Boon of Dimensionality
- Targeted Adversarial Perturbations for Monocular Depth Prediction
- Task-Agnostic Amortized Inference of Gaussian Process Hyperparameters
- Task-agnostic Exploration in Reinforcement Learning
- Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes
- Task-Oriented Feature Distillation
- Task-Robust Model-Agnostic Meta-Learning
- TaylorGAN: Neighbor-Augmented Policy Update Towards Sample-Efficient Natural Language Generation
- Teaching a GAN What Not to Learn
- Telescoping Density-Ratio Estimation
- Temporal Positive-unlabeled Learning for Biomedical Hypothesis Generation via Risk Estimation
- Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks
- Temporal Variability in Implicit Online Learning
- Tensor Completion Made Practical
- Testing Determinantal Point Processes
- Texture Interpolation for Probing Visual Perception
- The Adaptive Complexity of Maximizing a Gross Substitutes Valuation
- The Advantage of Conditional Meta-Learning for Biased Regularization and Fine Tuning
- The All-or-Nothing Phenomenon in Sparse Tensor PCA
- The Autoencoding Variational Autoencoder
- The Challenges of Real World Reinforcement Learning
- The Complete Lasso Tradeoff Diagram
- The Complexity of Adversarially Robust Proper Learning of Halfspaces with Agnostic Noise
- The Cone of Silence: Speech Separation by Localization
- The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations for Neural Network Verification
- The Convolution Exponential and Generalized Sylvester Flows
- The Devil is in the Detail: A Framework for Macroscopic Prediction via Microscopic Models
- The Dilemma of TriHard Loss and an Element-Weighted TriHard Loss for Person Re-Identification
- The Discrete Gaussian for Differential Privacy
- The Diversified Ensemble Neural Network
- The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space
- The Generalization-Stability Tradeoff In Neural Network Pruning
- The Generalized Lasso with Nonlinear Observations and Generative Priors
- The Genomic Bottleneck: A Lesson from Biology
- The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes
- The Implications of Local Correlation on Learning Some Deep Functions
- The interplay between randomness and structure during learning in RNNs
- The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning
- The Lottery Ticket Hypothesis for Pre-trained BERT Networks
- The MAGICAL Benchmark for Robust Imitation
- The Mean-Squared Error of Double Q-Learning
- The NetHack Learning Environment
- Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View
- The Origins and Prevalence of Texture Bias in Convolutional Neural Networks
- Theory-Inspired Path-Regularized Differential Network Architecture Search
- The phase diagram of approximation rates for deep neural networks
- The Pitfalls of Simplicity Bias in Neural Networks
- The Potts-Ising model for discrete multivariate data
- The Power of Comparisons for Actively Learning Linear Classifiers
- The Power of Predictions in Online Control
- The pre-registration experiment: an alternative publication model for machine learning research
- The Primal-Dual method for Learning Augmented Algorithms
- The Real AI Revolution
- The route to chaos in routing games: When is price of anarchy too optimistic?
- The Smoothed Possibility of Social Choice
- The Statistical Complexity of Early-Stopped Mirror Descent
- The Statistical Cost of Robust Kernel Hyperparameter Turning
- The Strong Screening Rule for SLOPE
- The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
- The Value Equivalence Principle for Model-Based Reinforcement Learning
- The Wasserstein Proximal Gradient Algorithm
- Throughput-Optimal Topology Design for Cross-Silo Federated Learning
- Thunder: a Fast Coordinate Selection Solver for Sparse Learning
- Tight First- and Second-Order Regret Bounds for Adversarial Linear Bandits
- Tight last-iterate convergence rates for no-regret learning in multi-player games
- Tight Nonparametric Convergence Rates for Stochastic Gradient Descent under the Noiseless Linear Model
- Time-Reversal Symmetric ODE Network
- Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network
- TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning
- Top-KAST: Top-K Always Sparse Training
- Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
- Topological Data Analysis and Beyond
- TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search
- Towards a Better Global Loss Landscape of GANs
- Towards a Combinatorial Characterization of Bounded-Memory Learning
- Towards Better Generalization of Adaptive Gradient Methods
- Towards Convergence Rate Analysis of Random Forests for Classification
- Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts
- Towards Deeper Graph Neural Networks with Differentiable Group Normalization
- Towards Interpretable Natural Language Understanding with Explanations as Latent Variables
- Towards Learning Convolutions from Scratch
- Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples
- Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes
- Towards More Practical Adversarial Attacks on Graph Neural Networks
- Towards Neural Programming Interfaces
- Towards Playing Full MOBA Games with Deep Reinforcement Learning
- Towards practical differentially private causal graph discovery
- Towards Problem-dependent Optimal Learning Rates
- Towards Safe Policy Improvement for Non-Stationary MDPs
- Towards Scalable Bayesian Learning of Causal DAGs
- Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous GNNs
- Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam in Deep Learning
- Towards Understanding Hierarchical Learning: Benefits of Neural Representations
- Toward the Fundamental Limits of Imitation Learning
- (Track1) Abstraction & Reasoning in AI systems: Modern Perspectives
- (Track1) Abstraction & Reasoning in AI systems: Modern Perspectives Q&A
- (Track1) Advances in Approximate Inference
- (Track1) Advances in Approximate Inference Q&A
- (Track1) Federated Learning and Analytics: Industry Meets Academia
- (Track1) Federated Learning and Analytics: Industry Meets Academia Q&A
- (Track1) Sketching and Streaming Algorithms
- (Track1) Sketching and Streaming Algorithms Q&A
- (Track1) There and Back Again: A Tale of Slopes and Expectations
- (Track1) There and Back Again: A Tale of Slopes and Expectations Q&A
- (Track1) Where Neuroscience meets AI (And What’s in Store for the Future)
- (Track2) Beyond Accuracy: Grounding Evaluation Metrics for Human-Machine Learning Systems
- (Track2) Beyond Accuracy: Grounding Evaluation Metrics for Human-Machine Learning Systems Q&A
- (Track2) Deep Conversational AI Q&A
- (Track2) Deeper Conversational AI
- (Track2) Equivariant Networks
- (Track2) Equivariant Networks Q&A
- (Track2) Explaining Machine Learning Predictions: State-of-the-art, Challenges, and Opportunities
- (Track2) Explaining Machine Learning Predictions: State-of-the-art, Challenges, and Opportunities Q&A
- (Track2) Machine Learning for Astrophysics and Astrophysics Problems for Machine Learning
- (Track2) Practical Uncertainty Estimation and Out-of-Distribution Robustness in Deep Learning
- (Track2) Practical Uncertainty Estimation and Out-of-Distribution Robustness in Deep Learning Q&A
- (Track3) Deep Implicit Layers: Neural ODEs, Equilibrium Models, and Differentiable Optimization
- (Track3) Deep Implicit Layers: Neural ODEs, Equilibrium Models, and Differentiable Optimization Q&A
- (Track3) Designing Learning Dynamics
- (Track3) Designing Learning Dynamics Q&A
- (Track3) Offline Reinforcement Learning: From Algorithm Design to Practical Applications
- (Track3) Offline Reinforcement Learning: From Algorithm Design to Practical Applications Q&A
- (Track3) Policy Optimization in Reinforcement Learning
- (Track3) Policy Optimization in Reinforcement Learning Q&A
- Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation
- Trading Personalization for Accuracy: Data Debugging in Collaborative Filtering
- Train-by-Reconnect: Decoupling Locations of Weights from Their Values
- Training Generative Adversarial Networks by Solving Ordinary Differential Equations
- Training Generative Adversarial Networks with Limited Data
- Training Linear Finite-State Machines
- Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification
- Training Stronger Baselines for Learning to Optimize
- Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning
- Transductive Information Maximization for Few-Shot Learning
- Transferable Calibration with Lower Bias and Variance in Domain Adaptation
- Transferable Graph Optimizers for ML Compilers
- Transfer Learning via $\ell_1$ Regularization
- Tree! I am no Tree! I am a low dimensional Hyperbolic Embedding
- Triple descent and the two kinds of overfitting: where & why do they appear?
- Truncated Linear Regression in High Dimensions
- Trust the Model When It Is Confident: Masked Model-based Actor-Critic
- Truthful Data Acquisition via Peer Prediction
- tspDB: Time Series Predict DB
- TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation
- UCLID-Net: Single View Reconstruction in Object Space
- UCSG-NET- Unsupervised Discovering of Constructive Solid Geometry Tree
- UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging
- Ultrahyperbolic Representation Learning
- Ultra-Low Precision 4-bit Training of Deep Neural Networks
- Unbalanced Sobolev Descent
- Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation
- Uncertainty-aware Self-training for Few-shot Text Classification
- Uncertainty Aware Semi-Supervised Learning on Graph Data
- Uncertainty Quantification for Inferring Hawkes Networks
- Uncovering the Topology of Time-Varying fMRI Data using Cubical Persistence
- Understanding and Exploring the Network with Stochastic Architectures
- Understanding and Improving Fast Adversarial Training
- Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features
- Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks
- Understanding Deep Architecture with Reasoning Layer
- Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition
- Understanding Global Feature Contributions With Additive Importance Measures
- Understanding Gradient Clipping in Private SGD: A Geometric Perspective
- Understanding spiking networks through convex optimization
- Understanding the Role of Training Regimes in Continual Learning
- Unfolding recurrence by Green’s functions for optimized reservoir computing
- Unfolding the Alternating Optimization for Blind Super Resolution
- Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks
- Universal Domain Adaptation through Self Supervision
- Universal Function Approximation on Graphs
- Universal guarantees for decision tree induction via a higher-order splitting criterion
- Universally Quantized Neural Compression
- UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging
- Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms
- Unsupervised Data Augmentation for Consistency Training
- Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models
- Unsupervised Learning of Dense Visual Representations
- Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control
- Unsupervised Learning of Object Landmarks via Self-Training Correspondence
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- Unsupervised object-centric video generation and decomposition in 3D
- Unsupervised Representation Learning by Invariance Propagation
- Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning
- Unsupervised Sound Separation Using Mixture Invariant Training
- Unsupervised Text Generation by Learning from Search
- Unsupervised Translation of Programming Languages
- Untangling tradeoffs between recurrence and self-attention in artificial neural networks
- Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss
- User-Dependent Neural Sequence Models for Continuous-Time Event Data
- Using noise to probe recurrent neural network structure and prune synapses
- UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object Detection
- VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data
- Value-driven Hindsight Modelling
- VarGrad: A Low-Variance Gradient Estimator for Variational Inference
- Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis
- Variance reduction for Random Coordinate Descent-Langevin Monte Carlo
- Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization
- Variational Amodal Object Completion
- Variational Bayesian Monte Carlo with Noisy Likelihoods
- Variational Bayesian Unlearning
- Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings
- Variational Interaction Information Maximization for Cross-domain Disentanglement
- Variational Policy Gradient Method for Reinforcement Learning with General Utilities
- Video Frame Interpolation without Temporal Priors
- Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement
- VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain
- Walking in the Shadow: A New Perspective on Descent Directions for Constrained Minimization
- Walsh-Hadamard Variational Inference for Bayesian Deep Learning
- Wasserstein Distances for Stereo Disparity Estimation
- Watch out! Motion is Blurring the Vision of Your Deep Neural Networks
- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
- Wavelet Flow: Fast Training of High Resolution Normalizing Flows
- Weak Form Generalized Hamiltonian Learning
- Weakly Supervised Deep Functional Maps for Shape Matching
- Weakly-Supervised Reinforcement Learning for Controllable Behavior
- Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
- Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings
- Weston-Watkins Hinge Loss and Ordered Partitions
- What Did You Think Would Happen? Explaining Agent Behaviour through Intended Outcomes
- What Do Neural Networks Learn When Trained With Random Labels?
- What if Neural Networks had SVDs?
- What is being transferred in transfer learning?
- What Makes for Good Views for Contrastive Learning?
- What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation
- What shapes feature representations? Exploring datasets, architectures, and training
- What went wrong and when? Instance-wise feature importance for time-series black-box models
- When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes
- When Counterpoint Meets Chinese Folk Melodies
- When Do Neural Networks Outperform Kernel Methods?
- Why are Adaptive Methods Good for Attention Models?
- Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective
- Why Normalizing Flows Fail to Detect Out-of-Distribution Data
- Winning the Lottery with Continuous Sparsification
- Wisdom of the Ensemble: Improving Consistency of Deep Learning Models
- Woodbury Transformations for Deep Generative Flows
- WoodFisher: Efficient Second-Order Approximation for Neural Network Compression
- WOR and $p$'s: Sketches for $\ell_p$-Sampling Without Replacement
- Wordplay: When Language Meets Games
- Workshop on Computer Assisted Programming (CAP)
- Workshop on Dataset Curation and Security
- Workshop on Deep Learning and Inverse Problems
- Worst-Case Analysis for Randomly Collected Data
- X-CAL: Explicit Calibration for Survival Analysis
- xLP: Explainable Link Prediction Demo
- You Can’t Escape Hyperparameters and Latent Variables: Machine Learning as a Software Engineering Enterprise
- Your Classifier can Secretly Suffice Multi-Source Domain Adaptation
- Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling
- Zap Q-Learning With Nonlinear Function Approximation
- Zero-Resource Knowledge-Grounded Dialogue Generation