ICML 2019 Papers

Browse

mini compact detail

Learning to Convolve: A Generalized Weight-Tying Approach

Similarity of Neural Network Representations Revisited

Active Learning with Disagreement Graphs

Moment-Based Variational Inference for Markov Jump Processes

Finding Mixed Nash Equilibria of Generative Adversarial Networks

Combining parametric and nonparametric models for off-policy evaluation

Orthogonal Random Forest for Causal Inference

Alternating Minimizations Converge to Second-Order Optimal Solutions

Unsupervised Label Noise Modeling and Loss Correction

Benefits and Pitfalls of the Exponential Mechanism with Applications to Hilbert Spaces and Functional PCA

Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms

State-Regularized Recurrent Neural Networks

Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Model

MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

A Framework for Bayesian Optimization in Embedded Subspaces

Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning

Minimal Achievable Sufficient Statistic Learning

CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration

Improving Model Selection by Employing the Test Data

Scale-free adaptive planning for deterministic dynamics & discounted rewards

Multi-Agent Adversarial Inverse Reinforcement Learning

A Tree-Based Method for Fast Repeated Sampling of Determinantal Point Processes

TarMAC: Targeted Multi-Agent Communication

Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning

Model-Based Active Exploration

Metric-Optimized Example Weights

Quantifying Generalization in Reinforcement Learning

Stein Point Markov Chain Monte Carlo

Simple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization

Online Adaptive Principal Component Analysis and Its extensions

NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks

On Variational Bounds of Mutual Information

Learning to Generalize from Sparse and Underspecified Rewards

Subspace Robust Wasserstein Distances

Stable and Fair Classification

Maximum Likelihood Estimation for Learning Populations of Parameters

SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning

Optimality Implies Kernel Sum Classifiers are Statistically Efficient

Efficient Full-Matrix Adaptive Regularization

Adjustment Criteria for Generalizing Experimental Findings

Semi-Cyclic Stochastic Gradient Descent

Circuit-GNN: Graph Neural Networks for Distributed Circuit Design

Analyzing and Improving Representations with the Soft Nearest Neighbor Loss

Finding Options that Minimize Planning Time

Discovering Options for Exploration by Minimizing Cover Time

Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models

Learning Novel Policies For Tasks

Categorical Feature Compression via Submodular Optimization

Formal Privacy for Functional Data with Gaussian Perturbations

Do ImageNet Classifiers Generalize to ImageNet?

Tensor Variable Elimination for Plated Factor Graphs

Automatic Posterior Transformation for Likelihood-Free Inference

Rao-Blackwellized Stochastic Gradients for Discrete Distributions

Improved Dynamic Graph Learning through Fault-Tolerant Sparsification

Concentration Inequalities for Conditional Value at Risk

Infinite Mixture Prototypes for Few-shot Learning

Functional Transparency for Structured Data: a Game-Theoretic Approach

On Connected Sublevel Sets in Deep Learning

Loss Landscapes of Regularized Linear Autoencoders

Self-Supervised Exploration via Disagreement

Sensitivity Analysis of Linear Structural Causal Models

Towards a Unified Analysis of Random Fourier Features

Fairwashing: the risk of rationalization

A Multitask Multiple Kernel Learning Algorithm for Survival Analysis with Application to Cancer Biology

Dynamic Measurement Scheduling for Event Forecasting using Deep RL

Characterizing Well-Behaved vs. Pathological Deep Neural Networks

Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances

Exploring interpretable LSTM neural networks over multi-variable data

GOODE: A Gaussian Off-The-Shelf Ordinary Differential Equation Solver

Trajectory-Based Off-Policy Deep Reinforcement Learning

Noise2Self: Blind Denoising by Self-Supervision

Generative Adversarial User Model for Reinforcement Learning Based Recommendation System

Particle Flow Bayes' Rule

Learning to Clear the Market

Blended Conditonal Gradients

Unreproducible Research is Reproducible

Making Convolutional Networks Shift-Invariant Again

On the Connection Between Adversarial Robustness and Saliency Map Interpretability

Sublinear Space Private Algorithms Under the Sliding Window Model

Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds

Robust Decision Trees Against Adversarial Examples

Active Learning for Decision-Making from Imbalanced Observational Data

kernelPSI: a Post-Selection Inference Framework for Nonlinear Variable Selection

Submodular Maximization beyond Non-negativity: Guarantees, Fast Algorithms, and Applications

Information-Theoretic Considerations in Batch Reinforcement Learning

Anytime Online-to-Batch, Optimism and Acceleration

Asynchronous Batch Bayesian Optimisation with Improved Local Penalisation

Decomposing feature-level variation with Covariate Gaussian Process Latent Variable Models

A Large-Scale Study on Regularization and Normalization in GANs

MIWAE: Deep Generative Modelling and Imputation of Incomplete Data Sets

Hessian Aided Policy Gradient

Overcoming Mean-Field Approximations in Recurrent Gaussian Process Models

Feature Grouping as a Stochastic Regularizer for High-Dimensional Structured Data

Fairness-Aware Learning for Continuous Attributes and Treatments

Estimating Information Flow in Deep Neural Networks

Power k-Means Clustering

GMNN: Graph Markov Neural Networks

A Conditional-Gradient-Based Augmented Lagrangian Framework

Random Shuffling Beats SGD after Finite Epochs

Wasserstein of Wasserstein Loss for Learning Generative Models

Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator

Variational Russian Roulette for Deep Bayesian Nonparametrics

Learning-to-Learn Stochastic Gradient Descent with Biased Regularization

The Odds are Odd: A Statistical Test for Detecting Adversarial Examples

Variational Implicit Processes

PAC Learnability of Node Functions in Networked Dynamical Systems

Graph Resistance and Learning from Pairwise Comparisons

Multi-objective training of Generative Adversarial Networks with multiple discriminators

Making Deep Q-learning methods robust to time discretization

Parameter-Efficient Transfer Learning for NLP

Differentially Private Fair Learning

Trainable Decoding of Sets of Sequences for Neural Sequence Models

Optimal Transport for structured data with application on graphs

Same, Same But Different: Recovering Neural Network Quantization Error Through Weight Factorization

Self-similar Epochs: Value in arrangement

On discriminative learning of prediction uncertainty

On the Limitations of Representing Functions on Sets

When Samples Are Strategically Selected

Understanding the Impact of Entropy on Policy Optimization

Transfer of Samples in Policy Search via Multiple Importance Sampling

Target-Based Temporal-Difference Learning

Understanding Geometry of Encoder-Decoder CNNs

Efficient Amortised Bayesian Inference for Hierarchical and Nonlinear Dynamical Systems

Emerging Convolutions for Generative Normalizing Flows

Agnostic Federated Learning

Learning to Route in Similarity Graphs

Learning from a Learner

White-box vs Black-box: Bayes Optimal Strategies for Membership Inference

Learning Models from Data with Measurement Error: Tackling Underreporting

On the Complexity of Approximating Wasserstein Barycenters

Estimate Sequences for Variance-Reduced Stochastic Composite Optimization

Learning to Infer Program Sketches

Scaling Up Ordinal Embedding: A Landmark Approach

Counterfactual Visual Explanations

Empirical Analysis of Beam Search Performance Degradation in Neural Sequence Models

FloWaveNet : A Generative Flow for Raw Audio

Non-Monotonic Sequential Text Generation

Escaping Saddle Points with Adaptive Gradient Methods

Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks

Analogies Explained: Towards Understanding Word Embeddings

Projections for Approximate Policy Iteration Algorithms

Distribution calibration for regression

Feature-Critic Networks for Heterogeneous Domain Generalization

Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness

Reinforcement Learning in Configurable Continuous Environments

Generative Modeling of Infinite Occluded Objects for Compositional Scene Representation

Hierarchical Decompositional Mixtures of Variational Autoencoders

A Theory of Regularized Markov Decision Processes

EMI: Exploration with Mutual Information

A Deep Reinforcement Learning Perspective on Internet Congestion Control

Model Function Based Conditional Gradient Method with Armijo-like Line Search

SelectiveNet: A Deep Neural Network with an Integrated Reject Option

Graph Convolutional Gaussian Processes

TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning

Graph Matching Networks for Learning the Similarity of Graph Structured Objects

Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction

First-Order Adversarial Vulnerability of Neural Networks and Input Dimension

A Better k-means++ Algorithm via Local Search

Graphite: Iterative Generative Modeling of Graphs

Obtaining Fairness using Optimal Transport Theory

Phase transition in PCA with missing data: Reduced signal-to-noise ratio, not sample size!

NAS-Bench-101: Towards Reproducible Neural Architecture Search

Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication

Graph Neural Network for Music Score Data and Modeling Expressive Piano Performance

Neural Network Attributions: A Causal Perspective

Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks

Fast Algorithm for Generalized Multinomial Models with Ranking Data

Learning a Prior over Intent via Meta-Inverse Reinforcement Learning

Calibrated Model-Based Deep Reinforcement Learning

QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning

Collaborative Channel Pruning for Deep Networks

Kernel-Based Reinforcement Learning in Robust Markov Decision Processes

Collaborative Evolutionary Reinforcement Learning

Bayesian Deconditional Kernel Mean Embeddings

DBSCAN++: Towards fast and scalable density clustering

Traditional and Heavy Tailed Self Regularization in Neural Network Models

Learning What and Where to Transfer

Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling

Multiplicative Weights Updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost always

Robust Inference via Generative Classifiers for Handling Noisy Labels

Dual Entangled Polynomial Code: Three-Dimensional Coding for Distributed Matrix Multiplication

Bayesian Optimization of Composite Functions

Correlated Variational Auto-Encoders

Co-manifold learning with missing data

Multi-Frequency Vector Diffusion Maps

A Dynamical Systems Perspective on Nesterov Acceleration

EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE

Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs

Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation

Non-monotone Submodular Maximization with Nearly Optimal Adaptivity and Query Complexity

Phaseless PCA: Low-Rank Matrix Recovery from Column-wise Phaseless Measurements

Bayesian Nonparametric Federated Learning of Neural Networks

MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization

Stochastic Iterative Hard Thresholding for Graph-structured Sparsity Optimization

Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem

Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning

Learning to Optimize Multigrid PDE Solvers

Stochastic Beams and Where To Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement

A Composite Randomized Incremental Gradient Method

ELF OpenGo: an analysis and open reimplementation of AlphaZero

Gauge Equivariant Convolutional Networks and the Icosahedral CNN

The Natural Language of Actions

Understanding and correcting pathologies in the training of learned optimizers

Per-Decision Option Discounting

Differentially Private Learning of Geometric Concepts

Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching

Disentangling Disentanglement in Variational Autoencoders

A Contrastive Divergence for Combining Variational Inference and MCMC

Exploiting structure of uncertainty for efficient matroid semi-bandits

Neural Logic Reinforcement Learning

Nonconvex Variance Reduced Optimization with Arbitrary Sampling

DL2: Training and Querying Neural Networks with Logic

Provably Efficient Maximum Entropy Exploration

Hierarchical Importance Weighted Autoencoders

LIT: Learned Intermediate Representation Training for Model Compression

Poission Subsampled R\'enyi Differential Privacy

Online Control with Adversarial Disturbances

Hybrid Models with Deep and Invertible Features

Toward Understanding the Importance of Noise in Training Neural Networks

On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference

Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel $k$-means Clustering

Memory-Optimal Direct Convolutions for Maximizing Classification Accuracy in Embedded Applications

Hiring Under Uncertainty

Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables

DAG-GNN: DAG Structure Learning with Graph Neural Networks

Distributional Reinforcement Learning for Efficient Exploration

Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition

Latent Normalizing Flows for Discrete Sequences

Relational Pooling for Graph Representations

Invertible Residual Networks

Data Shapley: Equitable Valuation of Data for Machine Learning

A Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein Minimization

Online Algorithms for Rent-Or-Buy with Expert Advice

Inference and Sampling of $K_{33}$-free Ising Models

Submodular Observation Selection and Information Gathering for Quadratic Models

The Evolved Transformer

Discovering Context Effects from Raw Choice Data

Remember and Forget for Experience Replay

Neuron birth-death dynamics accelerates gradient descent and converges asymptotically

Trading Redundancy for Communication: Speeding up Distributed SGD for Non-convex Optimization

Variational Annealing of GANs: A Langevin Perspective

Conditioning by adaptive sampling for robust design

Understanding Priors in Bayesian Neural Networks at the Unit Level

AUCµ: A Performance Metric for Multi-Class Machine Learning Models

Flexibly Fair Representation Learning by Disentanglement

Neurally-Guided Structure Inference

Diagnosing Bottlenecks in Deep Q-learning Algorithms

Guarantees for Spectral Clustering with Fairness Constraints

What is the Effect of Importance Weighting in Deep Learning?

An Optimal Private Stochastic-MAB Algorithm based on Optimal Private Stopping Rule

Random Walks on Hypergraphs with Edge-Dependent Vertex Weights

Using Pre-Training Can Improve Model Robustness and Uncertainty

Fair k-Center Clustering for Data Summarization

Adversarially Learned Representations for Information Obfuscation and Inference

Proportionally Fair Clustering

Katalyst: Boosting Convex Katayusha for Non-Convex Problems with a Large Condition Number

Rehashing Kernel Evaluation in High Dimensions

Wasserstein Adversarial Examples via Projected Sinkhorn Iterations

BayesNAS: A Bayesian Approach for Neural Architecture Search

On the Spectral Bias of Neural Networks

The Implicit Fairness Criterion of Unconstrained Learning

Generalized No Free Lunch Theorem for Adversarial Robustness

Bounding User Contributions: A Bias-Variance Trade-off in Differential Privacy

On the Design of Estimators for Bandit Off-Policy Evaluation

Cautious Regret Minimization: Online Optimization with Long-Term Budget Constraints

Geometry and Symmetry in Short-and-Sparse Deconvolution

On the Generalization Gap in Reparameterizable Reinforcement Learning

Learning Discrete Structures for Graph Neural Networks

$\texttt{DoubleSqueeze}$: Parallel Stochastic Gradient Descent with Double-pass Error-Compensated Compression

Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations

Distributed Weighted Matching via Randomized Composable Coresets

A Block Coordinate Descent Proximal Method for Simultaneous Filtering and Parameter Estimation

Screening rules for Lasso with non-convex Sparse Regularizers

Plug-and-Play Methods Provably Converge with Properly Trained Denoisers

DeepNose: Using artificial neural networks to represent the space of odorants

Revisiting the Softmax Bellman Operator: New Benefits and New Perspective

Contextual Memory Trees

Importance Sampling Policy Evaluation with an Estimated Behavior Policy

Learning with Bad Training Data via Iterative Trimmed Loss Minimization

Error Feedback Fixes SignSGD and other Gradient Compression Schemes

Game Theoretic Optimization via Gradient-based Nikaido-Isoda Function

Open-ended learning in symmetric zero-sum games

Curvature-Exploiting Acceleration of Elastic Net Computations

SGD: General Analysis and Improved Rates

Scalable Nonparametric Sampling from Multimodal Posteriors with the Posterior Bootstrap

Incorporating Grouping Information into Bayesian Decision Tree Ensembles

Policy Consolidation for Continual Reinforcement Learning

Deep Residual Output Layers for Neural Language Generation

Combating Label Noise in Deep Learning using Abstention

Geometric Losses for Distributional Learning

Adaptive Antithetic Sampling for Variance Reduction

Uniform Convergence Rate of the Kernel Density Estimator Adaptive to Intrinsic Volume Dimension

The Value Function Polytope in Reinforcement Learning

Faster Attend-Infer-Repeat with Tractable Probabilistic Models

Projection onto Minkowski Sums with Application to Constrained Learning

Structured agents for physical construction

Demystifying Dropout

Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computation

Target Tracking for Contextual Bandits: Application to Demand Side Management

Hyperbolic Disk Embeddings for Directed Acyclic Graphs

Kernel Normalized Cut: a Theoretical Revisit

Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models

Context-Aware Zero-Shot Learning for Object Recognition

Generalized Approximate Survey Propagation for High-Dimensional Estimation

Learning Discrete and Continuous Factors of Data via Alternating Disentanglement

Beyond the Chinese Restaurant and Pitman-Yor processes: Statistical Models with double power-law behavior

PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach

Adversarial Generation of Time-Frequency Features with application in audio synthesis

Almost surely constrained convex optimization

Exploiting Worker Correlation for Label Aggregation in Crowdsourcing

Position-aware Graph Neural Networks

Towards a Deep and Unified Understanding of Deep Neural Models in NLP

Composing Value Functions in Reinforcement Learning

Sample-Optimal Parametric Q-Learning Using Linearly Additive Features

The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study

Riemannian adaptive stochastic gradient algorithms on matrix manifolds

A Polynomial Time MCMC Method for Sampling from Continuous Determinantal Point Processes

Sublinear quantum algorithms for training linear and kernel-based classifiers

Graph Element Networks: adaptive, structured computation and memory

Improving Neural Network Quantization without Retraining using Outlier Channel Splitting

Guided evolutionary strategies: augmenting random search with surrogate gradients

Training CNNs with Selective Allocation of Channels

Predictor-Corrector Policy Optimization

SAGA with Arbitrary Sampling

Predicate Exchange: Inference with Declarative Knowledge

Learning Action Representations for Reinforcement Learning

Imitating Latent Policies from Observation

Self-Attention Graph Pooling

Optimal Auctions through Deep Learning

Teaching a black-box learner

An Instability in Variational Inference for Topic Models

Data Poisoning Attacks on Stochastic Bandits

Scalable Fair Clustering

Dynamic Learning with Frequent New Product Launches: A Sequential Multinomial Logit Bandit Problem

Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search

Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence

The Variational Predictive Natural Gradient

Composable Core-sets for Determinant Maximization: A Simple Near-Optimal Algorithm

Noisy Dual Principal Component Pursuit

Collective Model Fusion for Multiple Black-Box Experts

SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver

Dirichlet Simplex Nest and Geometric Inference

State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations

Look Ma, No Latent Variables: Accurate Cutset Networks via Compilation

Topological Data Analysis of Decision Boundaries with Application to Model Selection

Sorting Out Lipschitz Function Approximation

Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization

Generalized Linear Rule Models

Matrix-Free Preconditioning in Online Learning

Neural Joint Source-Channel Coding

Learning to Groove with Inverse Sequence Transformations

Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With Reneging

Detecting Overlapping and Correlated Communities without Pure Nodes: Identifiability and Algorithm

Submodular Streaming in All Its Glory: Tight Approximation, Minimum Memory and Low Adaptive Complexity

On Scalable and Efficient Computation of Large Scale Optimal Transport

HyperGAN: A Generative Model for Diverse, Performant Neural Networks

Incremental Randomized Sketching for Online Kernel Learning

Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems

Bayesian Optimization Meets Bayesian Optimal Stopping

Natural Analysts in Adaptive Data Analysis

On the Impact of the Activation function on Deep Neural Networks Training

Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops

Adversarial Examples Are a Natural Consequence of Test Error in Noise

Equivariant Transformer Networks

Certified Adversarial Robustness via Randomized Smoothing

Are Generative Classifiers More Robust to Adversarial Attacks?

Improving Neural Language Modeling via Adversarial Training

Nonlinear Stein Variational Gradient Descent for Learning Diversified Mixture Models

Provable Guarantees for Gradient-Based Meta-Learning

Competing Against Nash Equilibria in Adversarially Changing Zero-Sum Games

Autoregressive Energy Machines

CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network

Amortized Monte Carlo Integration

IMEXnet - A Forward Stable Deep Neural Network

LR-GLM: High-Dimensional Bayesian Inference Using Low-Rank Data Approximations

Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation

Regret Circuits: Composability of Regret Minimizers

AReS and MaRS - Adversarial and MMD-Minimizing Regression for SDEs

Efficient optimization of loops and limits with randomized telescoping sums

Fast Rates for a kNN Classifier Robust to Unknown Asymmetric Label Noise

Distributional Multivariate Policy Evaluation and Exploration with the Bellman GAN

Analyzing Federated Learning through an Adversarial Lens

Good Initializations of Variational Bayes for Deep Models

Almost Unsupervised Text to Speech and Automatic Speech Recognition

Gromov-Wasserstein Learning for Graph Matching and Node Embedding

Stable-Predictive Optimistic Counterfactual Regret Minimization

Causal Identification under Markov Equivalence: Completeness Results

Learning Classifiers for Target Domain with Limited or No Labels

Characterization of Convex Objective Functions and Optimal Expected Convergence Rates for SGD

Shallow-Deep Networks: Understanding and Mitigating Network Overthinking

Approximated Oracle Filter Pruning for Destructive CNN Width Optimization

A Personalized Affective Memory Model for Improving Emotion Recognition

Maximum Entropy-Regularized Multi-Goal Reinforcement Learning

Curiosity-Bottleneck: Exploration By Distilling Task-Specific Novelty

Towards Understanding Knowledge Distillation

A Quantitative Analysis of the Effect of Batch Normalization on Gradient Descent

Bayesian leave-one-out cross-validation for large data

Understanding and Accelerating Particle-Based Variational Inference

Robust Learning from Untrusted Sources

Co-Representation Network for Generalized Zero-Shot Learning

Distributed, Egocentric Representations of Graphs for Detecting Critical Structures

Safe Grid Search with Optimal Complexity

On the Universality of Invariant Networks

An Investigation of Model-Free Planning

Learning Linear-Quadratic Regulators Efficiently with only $\sqrt{T}$ Regret

Inferring Heterogeneous Causal Effects in Presence of Spatial Confounding

Rotation Invariant Householder Parameterization for Bayesian PCA

Sparse Extreme Multi-label Learning with Oracle Property

MASS: Masked Sequence to Sequence Pre-training for Language Generation

Optimal Algorithms for Lipschitz Bandits with Heavy-tailed Rewards

Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations

Learning to select for a predefined ranking

Large-Scale Sparse Kernel Canonical Correlation Analysis

Approximating Orthogonal Matrices with Effective Givens Factorization

The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects

Boosted Density Estimation Remastered

Distributed Learning with Sublinear Communication

Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal Iterations

Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerance

On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization

Online Learning to Rank with Features

Bilinear Bandits with Low-rank Structure

COMIC: Multi-view Clustering Without Parameter Selection

Gaining Free or Low-Cost Interpretability with Interpretable Partial Substitute

Interpreting Adversarially Trained Convolutional Neural Networks

How does Disagreement Help Generalization against Label Corruption?

Self-Attention Generative Adversarial Networks

Does Data Augmentation Lead to Positive Margin?

A Baseline for Any Order Gradient Estimation in Stochastic Computation Graphs

Replica Conditional Sequential Monte Carlo

Robust Estimation of Tree Structured Gaussian Graphical Models

Scalable Learning in Reproducing Kernel Krein Spaces

Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment

Rate Distortion For Model Compression:From Theory To Practice

Cognitive model priors for predicting human decisions

Learning Latent Dynamics for Planning from Pixels

Learning Optimal Linear Regularizers

Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design

Provably efficient RL with Rich Observations via Latent State Decoding

Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians

Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation

Learning Hawkes Processes Under Synchronization Noise

Coresets for Ordered Weighted Clustering

Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment

Deep Counterfactual Regret Minimization

Policy Certificates: Towards Accountable Reinforcement Learning

Compressed Factorization: Fast and Accurate Low-Rank Factorization of Compressively-Sensed Data

Simple Black-box Adversarial Attacks

Homomorphic Sensing

Rates of Convergence for Sparse Variational Gaussian Process Regression

Learning and Data Selection in Big Datasets

A Persistent Weisfeiler--Lehman Procedure for Graph Classification

Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning

Global Convergence of Block Coordinate Descent in Deep Learning

Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation

Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks

Lipschitz Generative Adversarial Nets

Metropolis-Hastings Generative Adversarial Networks

Accelerated Flow for Probability Distributions

Direct Uncertainty Prediction for Medical Second Opinions

Fairness without Harm: Decoupled Classifiers with Preference Guarantees

Simplifying Graph Convolutional Networks

Variational Inference for sparse network reconstruction from count data

Online Convex Optimization in Adversarial Markov Decision Processes

Composing Entropic Policies using Divergence Correction

Weakly-Supervised Temporal Localization via Occurrence Count Learning

Imputing Missing Events in Continuous-Time Event Streams

Variational Laplace Autoencoders

Molecular Hypergraph Grammar with Its Application to Molecular Optimization

Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects

Recursive Sketches for Modular Deep Learning

Random Function Priors for Correlation Modeling

The information-theoretic value of unlabeled data in semi-supervised learning

Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning

Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints

Off-Policy Deep Reinforcement Learning without Exploration

Learning Structured Decision Problems with Unawareness

A Recurrent Neural Cascade-based Model for Continuous-Time Diffusion

Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff

Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers

Adaptive Neural Trees

Sum-of-Squares Polynomial Flow

Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables

Control Regularization for Reduced Variance Reinforcement Learning

Near optimal finite time identification of arbitrary linear dynamical systems

Sublinear Time Nearest Neighbor Search over Generalized Weighted Space

The Wasserstein Transform

Nonlinear Distributional Gradient Temporal-Difference Learning

Improved Parallel Algorithms for Density-Based Network Clustering

Classification from Positive, Unlabeled and Biased Negative Data

Differentiable Dynamic Normalization for Learning Deep Representation

Geometry Aware Convolutional Filters for Omnidirectional Images Representation

A Kernel Theory of Modern Data Augmentation

Improving Adversarial Robustness via Promoting Ensemble Diversity

Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs

Kernel Mean Matching for Content Addressability of GANs

Learning to Collaborate in Markov Decision Processes

Better generalization with less data using robust gradient descent

Fast Direct Search in an Optimally Compressed Continuous Target Space for Efficient Multi-Label Active Learning

Neural Separation of Observed and Unobserved Distributions

Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels

Improved Convergence for $\ell_1$ and $\ell_\infty$ Regression via Iteratively Reweighted Least Squares

Submodular Cost Submodular Cover with an Approximate Oracle

Flat Metric Minimization with Applications in Generative Modeling

Learning Dependency Structures for Weak Supervision Models

Action Robust Reinforcement Learning and Applications in Continuous Control

HexaGAN: Generative Adversarial Nets for Real World Classification

Neural Collaborative Subspace Clustering

Revisiting precision recall definition for generative modeling

Monge blunts Bayes: Hardness Results for Adversarial Training

Band-limited Training and Inference for Convolutional Neural Networks

Anomaly Detection With Multiple-Hypotheses Predictions

Unifying Orthogonal Monte Carlo Methods

SELFIE: Refurbishing Unclean Samples for Robust Deep Learning

Statistics and Samples in Distributional Reinforcement Learning

Exploration Conscious Reinforcement Learning Revisited

Batch Policy Learning under Constraints

Training Neural Networks with Local Error Signals

Greedy Layerwise Learning Can Scale To ImageNet

Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations

Communication Complexity in Locally Private Distribution Estimation and Heavy Hitters

Linear-Complexity Data-Parallel Earth Mover's Distance Approximations

DP-GP-LVM: A Bayesian Non-Parametric Model for Learning Multivariate Dependency Structures

Sever: A Robust Meta-Algorithm for Stochastic Optimization

Unsupervised Deep Learning by Neighbourhood Discovery

Statistical Foundations of Virtual Democracy

Communication-Constrained Inference and the Role of Shared Randomness

Complexity of Linear Regions in Deep Networks

Decentralized Exploration in Multi-Armed Bandits

Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization

CAB: Continuous Adaptive Blending for Policy Evaluation and Learning

Deep Generative Learning via Variational Gradient Flow

Data Poisoning Attacks in Multi-Party Learning

Understanding MCMC Dynamics as Flows on the Wasserstein Space

Connectivity-Optimized Representation Learning via Persistent Homology

Adaptive Regret of Convex and Smooth Functions

SGD without Replacement: Sharper Rates for General Smooth Convex Functions

On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithms

Optimistic Policy Optimization via Multiple Importance Sampling

A Convergence Theory for Deep Learning via Over-Parameterization

The Kernel Interaction Trick: Fast Bayesian Discovery of Pairwise Interactions in High Dimensions

On the Computation and Communication Complexity of Parallel SGD with Dynamic Batch Sizes for Stochastic Non-Convex Optimization

Manifold Mixup: Better Representations by Interpolating Hidden States

Scalable Training of Inference Networks for Gaussian-Process Models

POLITEX: Regret Bounds for Policy Iteration using Expert Prediction

Discriminative Regularization for Latent Variable Models with Applications to Electrocardiography

Random Matrix Improved Covariance Estimation for a Large Class of Metrics

Area Attention

Online Variance Reduction with Mixtures

Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation

Fingerprint Policy Optimisation for Robust Reinforcement Learning

Ladder Capsule Network

Cross-Domain 3D Equivariant Image Embeddings

Finite-Time Analysis of Distributed TD(0) with Linear Function Approximation on Multi-Agent Reinforcement Learning

Fairness risk measures

Optimal Minimal Margin Maximization with Boosting

Spectral Approximate Inference

Beyond Adaptive Submodularity: Approximation Guarantees of Greedy Policy with Adaptive Submodularity Ratio

Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces

Invariant-Equivariant Representation Learning for Multi-Class Data

Approximation and non-parametric estimation of ResNet-type convolutional neural networks

CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning

Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning

On The Power of Curriculum Learning in Training Deep Networks

Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random

Provably Efficient Imitation Learning from Observation Alone

Model Comparison for Semantic Grouping

Breaking Inter-Layer Co-Adaptation by Classifier Anonymization

LegoNet: Efficient Convolutional Neural Networks with Lego Filters

Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models

Pareto Optimal Streaming Unsupervised Classification

Overcoming Multi-model Forgetting

RaFM: Rank-Aware Factorization Machines

Spectral Clustering of Signed Graphs via Matrix Power Means

Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group

Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits

Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?

On Symmetric Losses for Learning from Corrupted Labels

Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization

POPQORN: Quantifying Robustness of Recurrent Neural Networks

Learning Generative Models across Incomparable Spaces

CoT: Cooperative Training for Generative Modeling of Discrete Data

Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization

Validating Causal Inference Models via Influence Functions

Rademacher Complexity for Adversarially Robust Generalization

Safe Policy Improvement with Baseline Bootstrapping

Deep Factors for Forecasting

Generalized Majorization-Minimization

Stochastic Blockmodels meet Graph Neural Networks

Non-Parametric Priors For Generative Adversarial Networks

Graph U-Nets

First-Order Algorithms Converge Faster than $O(1/k)$ on Convex Problems

On the Convergence and Robustness of Adversarial Training

New results on information theoretic clustering

Bayesian Counterfactual Risk Minimization

Weak Detection of Signal in the Spiked Wigner Model

Greedy Orthogonal Pivoting Algorithm for Non-Negative Matrix Factorization

Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case

Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback

Compressing Gradient Optimizers via Count-Sketches

Learning to Prove Theorems via Interacting with Proof Assistants

Nearest Neighbor and Kernel Survival Analysis: Nonasymptotic Error Bounds and Strong Consistency Rates

LatentGNN: Learning Efficient Non-local Relations for Visual Recognition

Dead-ends and Secure Exploration in Reinforcement Learning

On Sparse Linear Regression in the Local Differential Privacy Model

Bayesian Joint Spike-and-Slab Graphical Lasso

Adversarial Online Learning with noise

Dynamic Weights in Multi-Objective Deep Reinforcement Learning

Bridging Theory and Algorithm for Domain Adaptation

Graphical-model based estimation and inference for differential privacy

Learning Distance for Sequences by Learning a Ground Metric

Imitation Learning from Imperfect Demonstration

Differentially Private Empirical Risk Minimization with Non-convex Loss Functions

Hierarchically Structured Meta-learning

Differentiable Linearized ADMM

Faster Stochastic Alternating Direction Method of Multipliers for Nonconvex Optimization

GDPP: Learning Diverse Generations using Determinantal Point Processes

Bayesian Generative Active Deep Learning

Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments

Sequential Facility Location: Approximate Submodularity and Greedy Algorithm

Understanding the Origins of Bias in Word Embeddings

Convolutional Poisson Gamma Belief Network

Neural Inverse Knitting: From Images to Manufacturing Instructions

Fast and Flexible Inference of Joint Distributions from their Marginals

SWALP : Stochastic Weight Averaging in Low Precision Training

Lossless or Quantized Boosting with Integer Arithmetic

Adaptive Monte Carlo Multiple Testing via Multi-Armed Bandits

TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning

Temporal Gaussian Mixture Layer for Videos

Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications

Probabilistic Neural Symbolic Models for Interpretable Visual Question Answering

Domain Agnostic Learning with Disentangled Representations

Stochastic Deep Networks

Automatic Classifiers as Scientific Instruments: One Step Further Away from Ground-Truth

Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions

A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks

Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI

MONK -- Outlier-Robust Mean Embedding Estimation by Median-of-Means

Fast Context Adaptation via Meta-Learning

On Medians of (Randomized) Pairwise Means

Separable value functions across time-scales

A fully differentiable beam search decoder

The advantages of multiple classes for reducing overfitting from test set reuse

Multi-Object Representation Learning with Iterative Variational Inference

Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities

Conditional Independence in Testing Bayesian Networks

Deep Compressed Sensing

Beyond Backprop: Online Alternating Minimization with Auxiliary Variables

Mixture Models for Diverse Machine Translation: Tricks of the Trade

EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis

Toward Controlling Discrimination in Online Ad Auctions

Classifying Treatment Responders Under Causal Effect Monotonicity

An Investigation into Neural Net Optimization via Hessian Eigenvalue Density

High-Fidelity Image Generation With Fewer Labels

Transferable Clean-Label Poisoning Attacks on Deep Neural Nets

Learning Optimal Fair Policies

Adversarial camera stickers: A physical camera-based attack on deep learning systems

On Learning Invariant Representations for Domain Adaptation

Learning deep kernels for exponential family densities

Supervised Hierarchical Clustering with Exponential Linkage

Multivariate Submodular Optimization

More Efficient Off-Policy Evaluation through Regularized Targeted Learning

Discovering Conditionally Salient Features with Statistical Guarantees

A Theoretical Analysis of Contrastive Unsupervised Representation Learning

Active Manifolds: A non-linear analogue to Active Subspaces

Acceleration of SVRG and Katyusha X by Inexact Preconditioning

Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models

Online learning with kernel losses

Concrete Autoencoders: Differentiable Feature Selection and Reconstruction

Insertion Transformer: Flexible Sequence Generation via Insertion Operations

AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss

Active Embedding Search via Noisy Paired Comparisons

ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation

Iterative Linearized Control: Stable Algorithms and Complexity Guarantees

Actor-Attention-Critic for Multi-Agent Reinforcement Learning

Online Meta-Learning

Adaptive Scale-Invariant Online Algorithms for Learning Linear Models

Fault Tolerance in Iterative-Convergent Machine Learning

Making Decisions that Reduce Discriminatory Impacts

Taming MAML: Efficient unbiased meta-reinforcement learning

Distributed Learning over Unreliable Networks

Open Vocabulary Learning on Source Code with a Graph-Structured Cache

On Dropout and Nuclear Norm Regularization

Lower Bounds for Smooth Nonconvex Finite-Sum Optimization

ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables

Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data

Shape Constraints for Set Functions

Faster Algorithms for Binary Matrix Factorization

Online Learning with Sleeping Experts and Feedback Graphs

Efficient learning of smooth probability functions from Bernoulli tests with guarantees

Optimal Mini-Batch and Step Sizes for SAGA

TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing

PA-GD: On the Convergence of Perturbed Alternating Gradient Descent to Second-Order Stationary Points for Structured Nonconvex Optimization

Scalable Metropolis-Hastings for Exact Bayesian Inference with Large Datasets

Voronoi Boundary Classification: A High-Dimensional Geometric Approach via Weighted Monte Carlo Integration

Task-Agnostic Dynamics Priors for Deep Reinforcement Learning

Locally Private Bayesian Inference for Count Models

DeepMDP: Learning Continuous Latent Space Models for Representation Learning

Learning interpretable continuous-time models of latent stochastic dynamical systems

Learning to bid in revenue-maximizing auctions

Trimming the $\ell_1$ Regularizer: Statistical Analysis, Optimization, and Applications to Deep Learning

Partially Linear Additive Gaussian Graphical Models

Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations

Processing Megapixel Images with Deep Attention-Sampling Models

Calibrated Approximate Bayesian Inference

Adaptive Sensor Placement for Continuous Spaces

Fair Regression: Quantitative Definitions and Reduction-Based Algorithms

Adversarial Attacks on Node Embeddings via Graph Poisoning

BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning

Exploring the Landscape of Spatial Robustness

Discovering Latent Covariance Structures for Multiple Time Series

AdaGrad stepsizes: sharp convergence over nonconvex landscapes

Complementary-Label Learning for Arbitrary Losses and Models

Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspaces

Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization

Learning Context-dependent Label Permutations for Multi-label Classification

Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation

Heterogeneous Model Reuse via Optimizing Multiparty Multiclass Margin

CompILE: Compositional Imitation Learning and Execution

On Certifying Non-Uniform Bounds against Adversarial Attacks

End-to-End Probabilistic Inference for Nonstationary Audio Analysis

Deep Gaussian Processes with Importance-Weighted Variational Inference

Optimal Continuous DR-Submodular Maximization and Applications to Provable Mean Field Inference

Fast and Stable Maximum Likelihood Estimation for Incomplete Multinomial Models

Width Provably Matters in Optimization for Deep Linear Neural Networks

On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learning

On the statistical rate of nonlinear recovery in generative models with heavy-tailed data

Adversarial examples from computational constraints

Disentangled Graph Convolutional Networks

Theoretically Principled Trade-off between Robustness and Accuracy

Compositional Fairness Constraints for Graph Embeddings

A Statistical Investigation of Long Memory in Language and Music

Doubly-Competitive Distribution Estimation

Regularization in directable environments with application to Tetris

Mallows ranking models: maximum likelihood estimate and regeneration

Lorentzian Distance Learning for Hyperbolic Representations

HOList: An Environment for Machine Learning of Higher Order Logic Theorem Proving

Bias Also Matters: Bias Attribution for Deep Neural Network Explanation

Understanding and Controlling Memory in Recurrent Neural Networks

Dropout as a Structured Shrinkage Prior

Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions

Stochastic Gradient Push for Distributed Deep Learning

Jumpout : Improved Dropout for Deep Neural Networks with ReLUs

Differential Inclusions for Modeling Nonsmooth ADMM Variants: A Continuous Limit Theory

PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits

Dimensionality Reduction for Tukey Regression

Multi-Frequency Phase Synchronization

Correlated bandits or: How to minimize mean-squared error online

Nonparametric Bayesian Deep Networks with Local Competition

Switching Linear Dynamics for Variational Bayes Filtering

Meta-Learning Neural Bloom Filters

Geometric Scattering for Graph Data Analysis

Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting

Zero-Shot Knowledge Distillation in Deep Networks

Active Learning for Probabilistic Structured Prediction of Cuts and Matchings

A Kernel Perspective for Regularizing Deep Neural Networks

Refined Complexity of PCA with Outliers

MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement

Efficient Training of BERT by Progressively Stacking

Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously

LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning

Quantile Stein Variational Gradient Descent for Batch Bayesian Optimization

Efficient On-Device Models using Neural Projections

Low Latency Privacy Preserving Inference

A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning

Gradient Descent Finds Global Minima of Deep Neural Networks

Efficient Dictionary Learning with Gradient Descent

Automated Model Selection with Bayesian Quadrature

Learning Neurosymbolic Generative Models via Program Synthesis

Robust Influence Maximization for Hyperparametric Models

Static Automatic Batching In TensorFlow