NIPS 2017 Papers

Browse

mini compact topic detail

Learning with Feature Evolvable Streams

Reconstruct & Crush Network

Practical Bayesian Optimization for Model Fitting with Bayesian Adaptive Direct Search

Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks

Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks

Sobolev Training for Neural Networks

Probabilistic Rule Realization and Selection

Unsupervised Sequence Classification using Sequential Output Statistics

On Fairness and Calibration

The Numerics of GANs

Bandits Dueling on Partially Ordered Sets

Variational Laws of Visual Attention for Dynamic Scenes

Sparse Approximate Conic Hulls

Associative Embedding: End-to-End Learning for Joint Detection and Grouping

Non-convex Finite-Sum Optimization Via SCSG Methods

Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation

Attentional Pooling for Action Recognition

Trimmed Density Ratio Estimation

Language Modeling with Recurrent Highway Hypernetworks

Deanonymization in the Bitcoin P2P Network

Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization

Scalable Variational Inference for Dynamical Systems

Time-dependent spatially varying graphical models, with application to brain fMRI data analysis

Asynchronous Parallel Coordinate Minimization for MAP Inference

Semisupervised Clustering, AND-Queries and Locally Encodable Source Coding

Query Complexity of Clustering with Side Information

Thinking Fast and Slow with Deep Learning and Tree Search

Fast-Slow Recurrent Neural Networks

Learning to Inpaint for Image Compression

Online Prediction with Selfish Experts

Optimistic posterior sampling for reinforcement learning: worst-case regret bounds

Learning Koopman Invariant Subspaces for Dynamic Mode Decomposition

ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization

Matching neural paths: transfer from recognition to correspondence search

Learning spatiotemporal piecewise-geodesic trajectories from longitudinal manifold-valued data

Nonbacktracking Bounds on the Influence in Independent Cascade Models

Integration Methods and Optimization Algorithms

Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets

Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results

Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples

Subset Selection and Summarization in Sequential Data

Question Asking as Program Generation

Inductive Representation Learning on Large Graphs

Sharpness, Restart and Acceleration

Matrix Norm Estimation from a Few Entries

Convolutional Phase Retrieval

Predictive-State Decoders: Encoding the Future into Recurrent Networks

Revisiting Perceptron: Efficient and Label-Optimal Learning of Halfspaces

Union of Intersections (UoI) for Interpretable Data Driven Discovery and Prediction

Learning the Morphology of Brain Signals Using Alpha-Stable Convolutional Sparse Coding

Gradient Descent Can Take Exponential Time to Escape Saddle Points

Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations

Learning Overcomplete HMMs

GP CaKe: Effective brain connectivity with causal kernels

Contrastive Learning for Image Captioning

One-Sided Unsupervised Domain Mapping

Robust Hypothesis Test for Nonlinear Effect with Gaussian Processes

First-Order Adaptive Sample Size Methods to Reduce Complexity of Empirical Risk Minimization

Online multiclass boosting

Self-Normalizing Neural Networks

Unsupervised learning of object frames by dense equivariant image labelling

One-Shot Imitation Learning

Detrended Partial Cross Correlation for Brain Connectivity Analysis

Label Distribution Learning Forests

Learning to Pivot with Adversarial Networks

Differentiable Learning of Submodular Functions

On Blackbox Backpropagation and Jacobian Sensing

Neural Discrete Representation Learning

A Greedy Approach for Budgeted Maximum Inner Product Search

Saliency-based Sequential Image Attention with Multiset Prediction

Faster and Non-ergodic O(1/K) Stochastic Alternating Direction Method of Multipliers

Is Input Sparsity Time Possible for Kernel Low-Rank Approximation?

Policy Gradient With Value Function Approximation For Collective Multiagent Planning

Adversarial Symmetric Variational Autoencoder

End-to-End Differentiable Proving

A New Theory for Matrix Completion

Controllable Invariance through Adversarial Feature Learning

Introspective Classification with Convolutional Nets

SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

Compression-aware Training of Deep Networks

Matching on Balanced Nonlinear Representations for Treatment Effects Estimation

Solving Most Systems of Random Quadratic Equations

Multiscale Semi-Markov Dynamics for Intracortical Brain-Computer Interfaces

Decoupling "when to update" from "how to update"

Lower bounds on the robustness to adversarial perturbations

A Screening Rule for l1-Regularized Ising Model Estimation

Minimizing a Submodular Function from Samples

Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees

Safe Model-based Reinforcement Learning with Stability Guarantees

Learning Efficient Object Detection Models with Knowledge Distillation

Improved Dynamic Regret for Non-degenerate Functions

Deep Mean-Shift Priors for Image Restoration

Safe and Nested Subgame Solving for Imperfect-Information Games

Recycling Privileged Learning and Distribution Matching for Fairness

Geometric Descent Method for Convex Composite Minimization

PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs

Efficient Online Linear Optimization with Approximation Algorithms

Nonparametric Online Regression while Learning the Metric

Unsupervised Image-to-Image Translation Networks

Coded Distributed Computing for Inverse Problems

Convergence Analysis of Two-layer Neural Networks with ReLU Activation

Avoiding Discrimination through Causal Reasoning

Dykstra's Algorithm, ADMM, and Coordinate Descent: Connections, Insights, and Extensions

Adversarial Surrogate Losses for Ordinal Regression

Learning multiple visual domains with residual adapters

Multimodal Learning and Reasoning for Visual Question Answering

Diffusion Approximations for Online Principal Component Estimation and Global Convergence

Non-monotone Continuous DR-submodular Maximization: Structure and Algorithms

Learning with Average Top-k Loss

Hypothesis Transfer Learning via Transformation Functions

On the Power of Truncated SVD for General High-rank Matrix Estimation Problems

MarrNet: 3D Shape Reconstruction via 2.5D Sketches

Mixture-Rank Matrix Approximation for Collaborative Filtering

Toward Multimodal Image-to-Image Translation

On the Model Shrinkage Effect of Gamma Process Edge Partition Models

Learning Spherical Convolution for Fast Features from 360° Imagery

Preventing Gradient Explosions in Gated Recurrent Units

Towards Accurate Binary Convolutional Neural Network

Gated Recurrent Convolution Neural Network for OCR

Learning a Multi-View Stereo Machine

Variable Importance Using Decision Trees

Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks

Structured Embedding Models for Grouped Data

Universal Style Transfer via Feature Transforms

f-GANs in an Information Geometric Nutshell

Uprooting and Rerooting Higher-Order Graphical Models

On Structured Prediction Theory with Calibrated Convex Surrogate Losses

MaskRNN: Instance Level Video Object Segmentation

Inference in Graphical Models via Semidefinite Programming Hierarchies

Phase Transitions in the Pooled Data Problem

A Linear-Time Kernel Goodness-of-Fit Test

k-Support and Ordered Weighted Sparsity for Overlapping Groups: Hardness and Algorithms

Learning to See Physics via Visual De-animation

Cortical microcircuits as gated-recurrent neural networks

Parametric Simplex Method for Sparse Learning

A simple model of recognition and recall memory

Interactive Submodular Bandit

From Parity to Preference-based Notions of Fairness in Classification

The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings

Pose Guided Person Image Generation

Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model

Hunt For The Unique, Stable, Sparse And Fast Feature Learning On Graphs

Scalable Generalized Linear Bandits: Online Computation and Hashing

Inferring Generative Model Structure with Static Analysis

Group Sparse Additive Machine

Label Efficient Learning of Transferable Representations acrosss Domains and Tasks

Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent

Probabilistic Models for Integration Error in the Assessment of Functional Cardiac Models

On the Consistency of Quick Shift

Dilated Recurrent Neural Networks

Decoding with Value Networks for Neural Machine Translation

Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning

Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization

Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis

Deep Subspace Clustering Networks

Wider and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning

Concentration of Multilinear Functions of the Ising Model with Applications to Network Data

A General Framework for Robust Interactive Learning

Maxing and Ranking with Few Assumptions

Multi-view Matrix Factorization for Linear Dynamical System Estimation

Experimental Design for Learning Causal Graphs with Latent Variables

Unsupervised Learning of Disentangled Representations from Video

On clustering network-valued data

Online Dynamic Programming

Active Learning from Peers

On Separability of Loss Functions, and Revisiting Discriminative Vs Generative Models

Learning to Model the Tail

When Cyclic Coordinate Descent Outperforms Randomized Coordinate Descent

Stochastic Mirror Descent in Variationally Coherent Optimization Problems

Real Time Image Saliency for Black Box Classifiers

Linear Time Computation of Moments in Sum-Product Networks

Efficient Approximation Algorithms for Strings Kernel Based Sequence Classification

Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference

Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples

Kernel functions based on triplet comparisons

A Meta-Learning Perspective on Cold-Start Recommendations for Items

An Error Detection and Correction Framework for Connectomics

Convergence of Gradient EM on Multi-component Mixture of Gaussians

Affinity Clustering: Hierarchical Clustering at Scale

Stochastic Submodular Maximization: The Case of Coverage Functions

Neural Expectation Maximization

Predicting Scene Parsing and Motion Dynamics in the Future

Efficient and Flexible Inference for Stochastic Systems

GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process

Kernel Feature Selection via Conditional Covariance Minimization

Subspace Clustering via Tangent Cones

Structured Bayesian Pruning via Log-Normal Multiplicative Noise

Cross-Spectral Factor Analysis

A Sharp Error Analysis for the Fused Lasso, with Application to Approximate Changepoint Screening

Few-Shot Adversarial Domain Adaptation

Practical Hash Functions for Similarity Estimation and Dimensionality Reduction

The Scaling Limit of High-Dimensional Online Independent Component Analysis

Unsupervised Transformation Learning via Convex Relaxations

Approximation Algorithms for $\ell_0$-Low Rank Approximation

On Frank-Wolfe and Equilibrium Computation

Neural Variational Inference and Learning in Undirected Graphical Models

Learning Mixture of Gaussians with Streaming Data

Learning Hierarchical Information Flow with Recurrent Neural Modules

Spectral Mixture Kernels for Multi-Output Gaussian Processes

The power of absolute discounting: all-dimensional distribution estimation

Gradient Episodic Memory for Continual Learning

Protein Interface Prediction using Graph Convolutional Networks

Acceleration and Averaging in Stochastic Descent Dynamics

Random Projection Filter Bank for Time Series Data

Style Transfer from Non-Parallel Text by Cross-Alignment

Towards Generalization and Simplicity in Continuous Control

Modulating early visual processing by language

Z-Forcing: Training Stochastic Recurrent Networks

Inverse Reward Design

Causal Effect Inference with Deep Latent-Variable Models

Effective Parallelisation for Machine Learning

When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness

Filtering Variational Objectives

Good Semi-supervised Learning That Requires a Bad GAN

Clustering Stable Instances of Euclidean k-means.

Robust Conditional Probabilities

Learning Linear Dynamical Systems via Spectral Filtering

Communication-Efficient Distributed Learning of Discrete Distributions

Attend and Predict: Understanding Gene Regulation by Selective Attention on Chromatin

Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles

Solid Harmonic Wavelet Scattering: Predicting Quantum Molecular Energy from Invariant Descriptors of 3D Electronic Densities

Poincaré Embeddings for Learning Hierarchical Representations

Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

Learning Identifiable Gaussian Bayesian Networks in Polynomial Time and Sample Complexity

Scalable Log Determinants for Gaussian Process Kernel Learning

Learning with Bandit Feedback in Potential Games

Generalizing GANs: A Turing Perspective

Statistical Cost Sharing

Boltzmann Exploration Done Right

Neural Networks for Efficient Bayesian Decoding of Natural Images from Retinal Neurons

Learning Combinatorial Optimization Algorithms over Graphs

Scalable Planning with Tensorflow for Hybrid Nonlinear Domains

Learned in Translation: Contextualized Word Vectors

Invariance and Stability of Deep Convolutional Representations

Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes

Spectrally-normalized margin bounds for neural networks

Population Matching Discrepancy and Applications in Deep Learning

Hierarchical Clustering Beyond the Worst-Case

The Expressive Power of Neural Networks: A View from the Width

Countering Feedback Delays in Multi-Agent Learning

Asynchronous Coordinate Descent under More Realistic Assumptions

Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls

Optimal Shrinkage of Singular Values Under Random Data Contamination

Efficient Second-Order Online Kernel Learning with Adaptive Embedding

Implicit Regularization in Matrix Factorization

Early stopping for kernel boosting algorithms: A general analysis with localized complexities

Value Prediction Network

A Learning Error Analysis for Structured Prediction with Approximate Inference

Estimating High-dimensional Non-Gaussian Multiple Index Models via Stein’s Lemma

Recurrent Ladder Networks

Gaussian Quadrature for Kernel Features

SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability

A framework for Multi-A(rmed)/B(andit) Testing with Online FDR Control

Estimating Mutual Information for Discrete-Continuous Mixtures

Unbounded cache model for online language modeling with open vocabulary

Fader Networks:Manipulating Images by Sliding Attributes

Action Centered Contextual Bandits

Collaborative Deep Learning in Fixed Topology Networks

Exploring Generalization in Deep Learning

Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaos

Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space

Attention is All you Need

Predictive State Recurrent Neural Networks

Learning Neural Representations of Human Cognition across Many fMRI Studies

Self-Supervised Intrinsic Image Decomposition

A KL-LUCB algorithm for Large-Scale Crowdsourcing

Bregman Divergence for Stochastic Variance Reduction: Saddle-Point and Adversarial Prediction

Gradient Methods for Submodular Maximization

Parameter-Free Online Learning via Model Selection

Smooth Primal-Dual Coordinate Descent Algorithms for Nonsmooth Convex Optimization

Gradients of Generative Models for Improved Discriminative Analysis of Tandem Mass Spectra

Permutation-based Causal Inference Algorithms with Interventions

Learning Disentangled Representations with Semi-Supervised Deep Generative Models

Training Quantized Nets: A Deeper Understanding

Higher-Order Total Variation Classes on Grids: Minimax Theory and Trend Filtering Methods

Multiscale Quantization for Fast Similarity Search

Learning Populations of Parameters

The Importance of Communities for Learning to Influence

Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks

Extracting low-dimensional dynamics from multiple large-scale neural population recordings by learning to predict correlations

Online control of the false discovery rate with decaying memory

Do Deep Neural Networks Suffer from Crowding?

Improved Training of Wasserstein GANs

Clustering with Noisy Queries

Learning from uncertain curves: The 2-Wasserstein metric for Gaussian processes

Gradient descent GAN optimization is locally stable

Imagination-Augmented Agents for Deep Reinforcement Learning

Learning from Complementary Labels

Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning

Min-Max Propagation

What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?

Discriminative State Space Models

Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model

Approximate Supermodularity Bounds for Experimental Design

Dualing GANs

Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference

Approximation and Convergence Properties of Generative Adversarial Learning

AdaGAN: Boosting Generative Models

Finite sample analysis of the GTD Policy Evaluation Algorithms in Markov Setting

From Bayesian Sparsity to Gated Recurrent Nets

Hierarchical Implicit Models and Likelihood-Free Variational Inference

Straggler Mitigation in Distributed Optimization Through Data Encoding

Task-based End-to-end Model Learning in Stochastic Optimization

SVD-Softmax: Fast Softmax Approximation on Large Vocabulary Neural Networks

Plan, Attend, Generate: Planning for Sequence-to-Sequence Models

Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification

Improving the Expected Improvement Algorithm

Hybrid Reward Architecture for Reinforcement Learning

Multi-View Decision Processes: The Helper-AI Problem

ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching

Robust Imitation of Diverse Behaviors

A Sample Complexity Measure with Applications to Learning Optimal Auctions

Local Aggregative Games

On the Complexity of Learning Neural Networks

Riemannian approach to batch normalization

Online Learning with Transductive Regret

Online Learning with a Hint

Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent

Variational Inference for Gaussian Process Models with Linear Complexity

Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

Renyi Differential Privacy Mechanisms for Posterior Sampling

Identifying Outlier Arms in Multi-Armed Bandit

Self-supervised Learning of Motion Capture

EEG-GRAPH: A Factor-Graph-Based Model for Capturing Spatial, Temporal, and Observational Relationships in Electroencephalograms

Identification of Gaussian Process State Space Models

Learning Graph Representations with Embedding Propagation

K-Medoids For K-Means Seeding

Real-Time Bidding with Side Information

Fair Clustering Through Fairlets

Bayesian Optimization with Gradients

Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization

GibbsNet: Iterative Adversarial Inference for Deep Graphical Models

Stochastic and Adversarial Online Learning without Hyperparameters

Active Exploration for Learning Symbolic Representations

A-NICE-MC: Adversarial Training for MCMC

Teaching Machines to Describe Images with Natural Language Feedback

Triangle Generative Adversarial Networks

PRUNE: Preserving Proximity and Global Ranking for Network Embedding

Clone MCMC: Parallel High-Dimensional Gaussian Gibbs Sampling

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Selective Classification for Deep Neural Networks

Perturbative Black Box Variational Inference

Online Reinforcement Learning in Stochastic Games

Fast, Sample-Efficient Algorithms for Structured Phase Retrieval

Group Additive Structure Identification for Kernel Nonparametric Regression

Efficient Modeling of Latent Information in Supervised Learning using Gaussian Processes

Position-based Multiple-play Bandit Problem with Unknown Position Bias

Polynomial time algorithms for dual volume sampling

Excess Risk Bounds for the Bayes Risk using Variational Inference in Latent Gaussian Models

Maximum Margin Interval Trees

A simple neural network module for relational reasoning

Online Learning for Multivariate Hawkes Processes

Minimax Estimation of Bandable Precision Matrices

Q-LDA: Uncovering Latent Patterns in Text-based Sequential Decision Processes

Hash Embeddings for Efficient Word Representations

Monte-Carlo Tree Search by Best Arm Identification

Sample and Computationally Efficient Learning Algorithms under S-Concave Distributions

Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon

Hindsight Experience Replay

Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice

Accelerated Stochastic Greedy Coordinate Descent by Soft Thresholding Projection onto Simplex

Working hard to know your neighbor's margins: Local descriptor learning loss

Context Selection for Embedding Models

A Unified Approach to Interpreting Model Predictions

DropoutNet: Addressing Cold Start in Recommender Systems

Beyond Worst-case: A Probabilistic Analysis of Affine Policies in Dynamic Optimization

Multi-Task Learning for Contextual Bandits

Thy Friend is My Friend: Iterative Collaborative Filtering for Sparse Matrix Estimation

Non-Stationary Spectral Kernels

SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud

Adaptive Classification for Prediction Under a Budget

Robust Optimization for Non-Convex Objectives

Overcoming Catastrophic Forgetting by Incremental Moment Matching

Accelerated First-order Methods for Geodesically Convex Optimization on Riemannian Manifolds

Stochastic Approximation for Canonical Correlation Analysis

Convergence rates of a partition based Bayesian multivariate density estimation method

Affine-Invariant Online Optimization and the Low-rank Experts Problem

Ranking Data with Continuous Labels through Oriented Recursive Partitions

Near-Optimal Edge Evaluation in Explicit Generalized Binomial Graphs

Targeting EEG/LFP Synchrony with Neural Nets

Simple strategies for recovering inner products from coarsely quantized random projections

Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach

Doubly Stochastic Variational Inference for Deep Gaussian Processes

Scalable Model Selection for Belief Networks

Balancing information exposure in social networks

Visual Interaction Networks: Learning a Physics Simulator from Video

Training recurrent networks to generate hypotheses about how the brain solves hard navigation problems

QMDP-Net: Deep Learning for Planning under Partial Observability

Discovering Potential Correlations via Hypercontractivity

Federated Multi-Task Learning

A Probabilistic Framework for Nonlinearities in Stochastic Neural Networks

Distral: Robust multitask reinforcement learning

Improved Graph Laplacian via Geometric Self-Consistency

Online Learning of Optimal Bidding Strategy in Repeated Multi-Commodity Auctions

Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net

The Expxorcist: Nonparametric Graphical Models Via Conditional Exponential Densities

A Minimax Optimal Algorithm for Crowdsourcing

Dual Path Networks

Unified representation of tractography and diffusion-weighted MRI data using sparse multidimensional arrays

Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach

Deep Reinforcement Learning from Human Preferences

VAE Learning via Stein Variational Gradient Descent

A Decomposition of Forecast Error in Prediction Markets

On the Fine-Grained Complexity of Empirical Risk Minimization: Kernel Methods and Neural Networks

Safe Adaptive Importance Sampling

Learning Active Learning from Data

Multi-Information Source Optimization

Inverse Filtering for Hidden Markov Models

Non-parametric Structured Output Networks

The Marginal Value of Adaptive Gradient Methods in Machine Learning

Mapping distinct timescales of functional interactions among brain networks

Polynomial Codes: an Optimal Design for High-Dimensional Coded Matrix Multiplication

Learning Low-Dimensional Metrics

A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning

Temporal Coherency based Criteria for Predicting Video Frames using Deep Multi-stage Generative Adversarial Networks

Deconvolutional Paragraph Representation Learning

Random Permutation Online Isotonic Regression

Multi-Armed Bandits with Metric Movement Costs

Reconstructing perceived faces from brain activations with deep adversarial neural decoding

Aggressive Sampling for Multi-class to Binary Reduction with Applications to Text Classification

Learning A Structured Optimal Bipartite Graph for Co-Clustering

Counterfactual Fairness

Independence clustering (without a matrix)

Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems

Triple Generative Adversarial Nets

Streaming Weak Submodularity: Interpreting Neural Networks on the Fly

Prototypical Networks for Few-shot Learning

Efficient Sublinear-Regret Algorithms for Online Sparse Linear Regression with Limited Observation

Optimized Pre-Processing for Discrimination Prevention

Fast amortized inference of neural activity from calcium imaging data with variational autoencoders

Adaptive Active Hypothesis Testing under Limited Information

Scalable Levy Process Priors for Spectral Kernel Learning

On-the-fly Operation Batching in Dynamic Computation Graphs

Dynamic Routing Between Capsules

On Tensor Train Rank Minimization : Statistical Efficiency and Scalable Algorithm

Structured Generative Adversarial Networks

Conservative Contextual Linear Bandits

FALKON: An Optimal Large Scale Kernel Method

Successor Features for Transfer in Reinforcement Learning

Nonlinear Acceleration of Stochastic Algorithms

Variational Memory Addressing in Generative Models

Deep Hyperspherical Learning

Conic Scan-and-Cover algorithms for nonparametric topic modeling

Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction

Recursive Sampling for the Nystrom Method

Joint distribution optimal transportation for domain adaptation

Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning

InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations

YASS: Yet Another Spike Sorter

Incorporating Side Information by Adaptive Convolution

Universal consistency and minimax rates for online Mondrian Forests

Multiresolution Kernel Approximation for Gaussian Process Regression

Influence Maximization with $\varepsilon$-Almost Submodular Threshold Functions

Diving into the shallows: a computational perspective on large-scale shallow learning

Collapsed variational Bayes for Markov jump processes

Welfare Guarantees from Data

Visual Reference Resolution using Attention Memory for Visual Dialog

Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks

Reducing Reparameterization Gradient Variance

On the Optimization Landscape of Tensor Decompositions

High-Order Attention Models for Visual Question Answering

A multi-agent reinforcement learning model of common-pool resource appropriation

A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning

Sparse convolutional coding for neuronal assembly detection

Concrete Dropout

Subset Selection under Noise

Limitations on Variance-Reduction and Acceleration Schemes for Finite Sums Optimization

Bayesian GAN

Off-policy evaluation for slate recommendation

Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes

Collecting Telemetry Data Privately

Adaptive Batch Size for Safe Policy Gradients

Certified Defenses for Data Poisoning Attacks

Gaussian process based nonlinear latent structure discovery in multivariate spike train data

Near Optimal Sketching of Low-Rank Tensor Regression

Eigen-Distortions of Hierarchical Representations

PASS-GLM: polynomial approximate sufficient statistics for scalable Bayesian GLM inference

Quantifying how much sensory information in a neural code is relevant for behavior

Dynamic-Depth Context Tree Weighting

Multi-Objective Non-parametric Sequential Prediction

Process-constrained batch Bayesian optimisation

Sparse Embedded $k$-Means Clustering

Deep Sets

ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events

On Optimal Generalizability in Parametric Learning

Spherical convolutions and their application in molecular modelling

Neural system identification for large populations separating “what” and “where”

Multi-output Polynomial Networks and Factorization Machines

VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning

Efficient Optimization for Linear Dynamical Systems with Applications to Clustering and Sparse Coding

Bayesian Compression for Deep Learning

Model-based Bayesian inference of neural activity and connectivity from all-optical interrogation of a neural circuit

Streaming Sparse Gaussian Process Approximations

A Regularized Framework for Sparse and Structured Neural Attention

A Universal Analysis of Large-Scale Regularized Least Squares Solutions

Tractability in Structured Probability Spaces

Is the Bellman residual a bad proxy?

Dynamic Importance Sampling for Anytime Bounds of the Partition Function

Clustering Billions of Reads for DNA Data Storage

Ensemble Sampling

Adaptive SVRG Methods under Error Bound Conditions with Unknown Growth Parameter

Net-Trim: Convex Pruning of Deep Neural Networks with Performance Guarantee

Near Minimax Optimal Players for the Finite-Time 3-Expert Prediction Problem

Learning to Compose Domain-Specific Transformations for Data Augmentation

Graph Matching via Multiplicative Update Algorithm

Stein Variational Gradient Descent as Gradient Flow

Differentially private Bayesian learning on distributed data

Hierarchical Attentive Recurrent Tracking

Shallow Updates for Deep Reinforcement Learning

Generalization Properties of Learning with Random Features

Approximation Bounds for Hierarchical Clustering: Average Linkage, Bisecting K-means, and Local Search

Tomography of the London Underground: a Scalable Model for Origin-Destination Data

Regret Minimization in MDPs with Options without Prior Knowledge

Adaptive Accelerated Gradient Converging Method under H\"{o}lderian Error Bound Condition

Variance-based Regularization with Convex Objectives

Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback

Unbiased estimates for linear regression via volume sampling

Wasserstein Learning of Deep Generative Point Process Models

Learning Causal Structures Using Regression Invariance

Partial Hard Thresholding: Towards A Principled Analysis of Support Recovery

Reinforcement Learning under Model Mismatch

Deep Voice 2: Multi-Speaker Neural Text-to-Speech

Rotting Bandits

Adversarial Ranking for Language Generation

Model-Powered Conditional Independence Test

AIDE: An algorithm for measuring the accuracy of probabilistic inference algorithms

Fully Decentralized Policies for Multi-Agent Systems: An Information Theoretic Approach

A PAC-Bayesian Analysis of Randomized Learning with Application to Stochastic Gradient Descent

Continual Learning with Deep Generative Replay

Deep Lattice Networks and Partial Monotonic Functions

Decomposable Submodular Function Minimization: Discrete and Continuous

LightGBM: A Highly Efficient Gradient Boosting Decision Tree

Mean Field Residual Networks: On the Edge of Chaos

Beyond Parity: Fairness Objectives for Collaborative Filtering

Cold-Start Reinforcement Learning with Softmax Policy Gradient

Gauging Variational Inference

Deep Recurrent Neural Network-Based Identification of Precursor microRNAs

Alternating Estimation for Structured High-Dimensional Multi-Response Models

A Bayesian Data Augmentation Approach for Learning Deep Models

State Aware Imitation Learning

Estimation of the covariance structure of heavy-tailed distributions

Robust Estimation of Neural Signals in Calcium Imaging

Premise Selection for Theorem Proving by Deep Graph Embedding

Convolutional Gaussian Processes

Principles of Riemannian Geometry in Neural Networks

Bridging the Gap Between Value and Policy Based Reinforcement Learning

VAIN: Attentional Multi-agent Predictive Modeling

An Empirical Bayes Approach to Optimizing Machine Learning Algorithms

Information-theoretic analysis of generalization capability of learning algorithms

Multitask Spectral Learning of Weighted Automata

Rigorous Dynamics and Consistent Estimation in Arbitrarily Conditioned Linear Systems

#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

Differentially Private Empirical Risk Minimization Revisited: Faster and More General

Multi-way Interacting Regression via Factorization Machines

ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games

An Empirical Study on The Properties of Random Bases for Kernel Methods

Decomposition-Invariant Conditional Gradient for General Polytopes with Line Search

Dual Discriminator Generative Adversarial Nets

Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems

How regularization affects the critical points in linear networks

SGD Learns the Conjugate Kernel Class of the Network

Differentiable Learning of Logical Rules for Knowledge Base Reasoning

Scalable Demand-Aware Recommendation

Beyond normality: Learning sparse probabilistic graphical models in the non-Gaussian setting

Practical Data-Dependent Metric Compression with Provable Guarantees

Toward Goal-Driven Neural Network Models for the Rodent Whisker-Trigeminal System

Accuracy First: Selecting a Differential Privacy Level for Accuracy Constrained ERM

Variational Inference via $\chi$ Upper Bound Minimization

EX2: Exploration with Exemplar Models for Deep Reinforcement Learning

Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network

Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks

Deep Multi-task Gaussian Processes for Survival Analysis with Competing Risks

On Quadratic Convergence of DC Proximal Newton Algorithm in Nonconvex Sparse Learning

Practical Locally Private Heavy Hitters

Large-Scale Quadratically Constrained Quadratic Program via Low-Discrepancy Sequences

Fisher GAN

Masked Autoregressive Flow for Density Estimation

Information Theoretic Properties of Markov Random Fields, and their Algorithmic Applications

Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe

Parallel Streaming Wasserstein Barycenters

Dynamic Revenue Sharing

Fitting Low-Rank Tensors in Constant Time

Runtime Neural Pruning

An inner-loop free solution to inverse problems using deep neural networks

Nonlinear random matrix theory for deep learning

Generative Local Metric Learning for Kernel Regression

Elementary Symmetric Polynomials for Optimal Experimental Design

REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models

Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation

Pixels to Graphs by Associative Embedding

Expectation Propagation for t-Exponential Family Using q-Algebra

Noise-Tolerant Interactive Learning Using Pairwise Comparisons

Inhomogeneous Hypergraph Clustering with Applications

Natural Value Approximators: Learning when to Trust Past Estimates

Few-Shot Learning Through an Information Retrieval Lens

Collaborative PAC Learning

Fast Black-box Variational Inference through Stochastic Trust-Region Optimization

The Reversible Residual Network: Backpropagation Without Storing Activations

Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols

Deep Supervised Discrete Hashing

OnACID: Online Analysis of Calcium Imaging Data in Real Time

Zap Q-Learning

MMD GAN: Towards Deeper Understanding of Moment Matching Network

Training Deep Networks without Learning Rates Through Coin Betting

Consistent Robust Regression

A graph-theoretic approach to multitasking

Compatible Reward Inverse Reinforcement Learning

Bayesian Dyadic Trees and Histograms for Regression

Data-Efficient Reinforcement Learning in Continuous State-Action Gaussian-POMDPs

Learning ReLUs via Gradient Descent

Neural Program Meta-Induction

Hiding Images in Plain Sight: Deep Steganography

Generating steganographic images via adversarial training

Stabilizing Training of Generative Adversarial Networks through Regularization

Alternating minimization for dictionary learning with random initialization

PixelGAN Autoencoders

Consistent Multitask Learning with Nonlinear Output Relations

Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models

Hierarchical Methods of Moments

Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration

Expectation Propagation with Stochastic Kinetic Model in Complex Interaction Systems

Revisit Fuzzy Neural Network: Demystifying Batch Normalization and ReLU with Generalized Hamming Network

Speeding Up Latent Variable Gaussian Graphical Model Estimation via Nonconvex Optimization

Revenue Optimization with Approximate Bid Predictions

Interpretable and Globally Optimal Prediction for Textual Grounding using Image Concepts

Adaptive Clustering through Semidefinite Programming

Lookahead Bayesian Optimization with Inequality Constraints

Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks

Learning Multiple Tasks with Multilinear Relationship Networks

Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data

Deep Dynamic Poisson Factorization Model

Learning Chordal Markov Networks via Branch and Bound

Repeated Inverse Reinforcement Learning

Deep Hyperalignment

Predicting User Activity Level In Point Processes With Mass Transport Equation

Log-normality and Skewness of Estimated State/Action Values in Reinforcement Learning

Nearest-Neighbor Sample Compression: Efficiency, Consistency, Infinite Dimensions

Reliable Decision Support using Counterfactual Models

Online to Offline Conversions, Universality and Adaptive Minibatch Sizes

A New Alternating Direction Method for Linear Programming

Train longer, generalize better: closing the generalization gap in large batch training of neural networks

A Scale Free Algorithm for Stochastic Bandits with Bounded Kurtosis

Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure

Deliberation Networks: Sequence Generation Beyond One-Pass Decoding

Model evidence from nonequilibrium simulations

Deep Learning with Topological Signatures

From which world is your graph

Regret Analysis for Continuous Dueling Bandit

Submultiplicative Glivenko-Cantelli and Uniform Convergence of Revenues

Positive-Unlabeled Learning with Non-Negative Risk Estimator

Optimal Sample Complexity of M-wise Data for Top-K Ranking

Learned D-AMP: Principled Neural Network based Compressive Image Recovery

NeuralFDR: Learning Discovery Thresholds from Hypothesis Features

Minimal Exploration in Structured Stochastic Bandits

Regularized Modal Regression with Applications in Cognitive Impairment Prediction

QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding

Best Response Regression

Linear regression without correspondence

TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning

Learning Affinity via Spatial Propagation Networks

Cost efficient gradient boosting

Online Convex Optimization with Stochastic Constraints

Testing and Learning on Distributions with Symmetric Noise Invariance

Max-Margin Invariant Features from Transformed Unlabelled Data

Translation Synchronization via Truncated Least Squares

Adaptive stimulus selection for optimizing neural population responses

A Dirichlet Mixture Model of Hawkes Processes for Event Sequence Clustering

DPSCREEN: Dynamic Personalized Screening

Generalized Linear Model Regression under Distance-to-set Penalties

Tensor Biclustering

Adaptive Bayesian Sampling with Monte Carlo EM

Shape and Material from Sound

Accelerated consensus via Min-Sum Splitting

Flexible statistical inference for mechanistic models of neural dynamics

Fixed-Rank Approximation of a Positive-Semidefinite Matrix from Streaming Data

Improving Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms and Its Applications

Learning Unknown Markov Decision Processes: A Thompson Sampling Approach

Linearly constrained Gaussian processes