International Conference on Machine Learning (ICML) - 2019

Conference Proceedings:

Key: PC - Pseudocode, OSC - Open Source Code, OSD - Open Datasets, DS - Dataset Splits, HS - Hardware Specification, SD - Software Dependencies, ES - Experiment Setup

A Baseline for Any Order Gradient Estimation in Stochastic Computation Graphs 1
A Better k-means++ Algorithm via Local Search 3
A Block Coordinate Descent Proximal Method for Simultaneous Filtering and Parameter Estimation 2
A Composite Randomized Incremental Gradient Method 2
A Conditional-Gradient-Based Augmented Lagrangian Framework 2
A Contrastive Divergence for Combining Variational Inference and MCMC 4
A Convergence Theory for Deep Learning via Over-Parameterization 2
A Deep Reinforcement Learning Perspective on Internet Congestion Control 2
A Dynamical Systems Perspective on Nesterov Acceleration 1
A Framework for Bayesian Optimization in Embedded Subspaces 3
A Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein Minimization 3
A Kernel Perspective for Regularizing Deep Neural Networks 4
A Kernel Theory of Modern Data Augmentation 3
A Large-Scale Study on Regularization and Normalization in GANs 3
A Multitask Multiple Kernel Learning Algorithm for Survival Analysis with Application to Cancer Biology 5
A Persistent Weisfeiler-Lehman Procedure for Graph Classification 5
A Personalized Affective Memory Model for Improving Emotion Recognition 3
A Polynomial Time MCMC Method for Sampling from Continuous Determinantal Point Processes 2
A Quantitative Analysis of the Effect of Batch Normalization on Gradient Descent 2
A Recurrent Neural Cascade-based Model for Continuous-Time Diffusion 4
A Statistical Investigation of Long Memory in Language and Music 2
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks 3
A Theoretical Analysis of Contrastive Unsupervised Representation Learning 2
A Theory of Regularized Markov Decision Processes 0
A Tree-Based Method for Fast Repeated Sampling of Determinantal Point Processes 3
A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning 4
A fully differentiable beam search decoder 3
ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables 5
AReS and MaRS Adversarial and MMD-Minimizing Regression for SDEs 4
AUCμ: A Performance Metric for Multi-Class Machine Learning Models 0
Accelerated Flow for Probability Distributions 2
Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances 0
Acceleration of SVRG and Katyusha X by Inexact Preconditioning 6
Action Robust Reinforcement Learning and Applications in Continuous Control 4
Active Embedding Search via Noisy Paired Comparisons 4
Active Learning for Decision-Making from Imbalanced Observational Data 4
Active Learning for Probabilistic Structured Prediction of Cuts and Matchings 2
Active Learning with Disagreement Graphs 4
Active Manifolds: A non-linear analogue to Active Subspaces 3
Actor-Attention-Critic for Multi-Agent Reinforcement Learning 3
AdaGrad Stepsizes: Sharp Convergence Over Nonconvex Landscapes 4
Adaptive Antithetic Sampling for Variance Reduction 1
Adaptive Monte Carlo Multiple Testing via Multi-Armed Bandits 5
Adaptive Neural Trees 4
Adaptive Regret of Convex and Smooth Functions 1
Adaptive Scale-Invariant Online Algorithms for Learning Linear Models 3
Adaptive Sensor Placement for Continuous Spaces 2
Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search 7
Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspaces 2
Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment 4
Adjustment Criteria for Generalizing Experimental Findings 1
Adversarial Attacks on Node Embeddings via Graph Poisoning 3
Adversarial Examples Are a Natural Consequence of Test Error in Noise 2
Adversarial Generation of Time-Frequency Features with application in audio synthesis 4
Adversarial Online Learning with noise 1
Adversarial camera stickers: A physical camera-based attack on deep learning systems 2
Adversarial examples from computational constraints 0
Adversarially Learned Representations for Information Obfuscation and Inference 3
Agnostic Federated Learning 4
Almost Unsupervised Text to Speech and Automatic Speech Recognition 4
Almost surely constrained convex optimization 4
Alternating Minimizations Converge to Second-Order Optimal Solutions 1
Amortized Monte Carlo Integration 1
An Instability in Variational Inference for Topic Models 1
An Investigation into Neural Net Optimization via Hessian Eigenvalue Density 3
An Investigation of Model-Free Planning 3
An Optimal Private Stochastic-MAB Algorithm based on Optimal Private Stopping Rule 3
Analogies Explained: Towards Understanding Word Embeddings 1
Analyzing Federated Learning through an Adversarial Lens 3
Analyzing and Improving Representations with the Soft Nearest Neighbor Loss 4
Anomaly Detection With Multiple-Hypotheses Predictions 3
Anytime Online-to-Batch, Optimism and Acceleration 1
Approximated Oracle Filter Pruning for Destructive CNN Width Optimization 6
Approximating Orthogonal Matrices with Effective Givens Factorization 4
Approximation and non-parametric estimation of ResNet-type convolutional neural networks 0
Are Generative Classifiers More Robust to Adversarial Attacks? 3
Area Attention 6
Asynchronous Batch Bayesian Optimisation with Improved Local Penalisation 4
AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss 2
Automated Model Selection with Bayesian Quadrature 2
Automatic Classifiers as Scientific Instruments: One Step Further Away from Ground-Truth 2
Automatic Posterior Transformation for Likelihood-Free Inference 3
Autoregressive Energy Machines 4
BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning 3
Band-limited Training and Inference for Convolutional Neural Networks 3
Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case 2
Batch Policy Learning under Constraints 2
BayesNAS: A Bayesian Approach for Neural Architecture Search 5
Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning 3
Bayesian Counterfactual Risk Minimization 3
Bayesian Deconditional Kernel Mean Embeddings 1
Bayesian Generative Active Deep Learning 4
Bayesian Joint Spike-and-Slab Graphical Lasso 3
Bayesian Nonparametric Federated Learning of Neural Networks 4
Bayesian Optimization Meets Bayesian Optimal Stopping 3
Bayesian Optimization of Composite Functions 3
Bayesian leave-one-out cross-validation for large data 5
Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously 2
Benefits and Pitfalls of the Exponential Mechanism with Applications to Hilbert Spaces and Functional PCA 3
Better generalization with less data using robust gradient descent 3
Beyond Adaptive Submodularity: Approximation Guarantees of Greedy Policy with Adaptive Submodularity Ratio 3
Beyond Backprop: Online Alternating Minimization with Auxiliary Variables 4
Beyond the Chinese Restaurant and Pitman-Yor processes: Statistical Models with double power-law behavior 3
Bias Also Matters: Bias Attribution for Deep Neural Network Explanation 3
Bilinear Bandits with Low-rank Structure 2
Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables 4
Blended Conditonal Gradients 1
Boosted Density Estimation Remastered 3
Bounding User Contributions: A Bias-Variance Trade-off in Differential Privacy 3
Breaking Inter-Layer Co-Adaptation by Classifier Anonymization 3
Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities 4
Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms 4
Bridging Theory and Algorithm for Domain Adaptation 4
CAB: Continuous Adaptive Blending for Policy Evaluation and Learning 3
CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network 1
COMIC: Multi-view Clustering Without Parameter Selection 5
CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning 2
Calibrated Approximate Bayesian Inference 4
Calibrated Model-Based Deep Reinforcement Learning 5
CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration 3
Categorical Feature Compression via Submodular Optimization 3
Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models 3
Causal Identification under Markov Equivalence: Completeness Results 1
Cautious Regret Minimization: Online Optimization with Long-Term Budget Constraints 2
Certified Adversarial Robustness via Randomized Smoothing 5
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations 3
Characterization of Convex Objective Functions and Optimal Expected Convergence Rates for SGD 3
Characterizing Well-Behaved vs. Pathological Deep Neural Networks 2
Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group 4
Circuit-GNN: Graph Neural Networks for Distributed Circuit Design 3
Classification from Positive, Unlabeled and Biased Negative Data 4
Classifying Treatment Responders Under Causal Effect Monotonicity 3
Co-Representation Network for Generalized Zero-Shot Learning 3
Co-manifold learning with missing data 3
CoT: Cooperative Training for Generative Modeling of Discrete Data 4
Cognitive model priors for predicting human decisions 3
Collaborative Channel Pruning for Deep Networks 5
Collaborative Evolutionary Reinforcement Learning 4
Collective Model Fusion for Multiple Black-Box Experts 1
Combating Label Noise in Deep Learning using Abstention 3
Combining parametric and nonparametric models for off-policy evaluation 3
Communication Complexity in Locally Private Distribution Estimation and Heavy Hitters 2
Communication-Constrained Inference and the Role of Shared Randomness 0
CompILE: Compositional Imitation Learning and Execution 2
Competing Against Nash Equilibria in Adversarially Changing Zero-Sum Games 1
Complementary-Label Learning for Arbitrary Losses and Models 5
Complexity of Linear Regions in Deep Networks 2
Composable Core-sets for Determinant Maximization: A Simple Near-Optimal Algorithm 3
Composing Entropic Policies using Divergence Correction 1
Composing Value Functions in Reinforcement Learning 2
Compositional Fairness Constraints for Graph Embeddings 2
Compressed Factorization: Fast and Accurate Low-Rank Factorization of Compressively-Sensed Data 3
Compressing Gradient Optimizers via Count-Sketches 5
Concentration Inequalities for Conditional Value at Risk 1
Concrete Autoencoders: Differentiable Feature Selection and Reconstruction 5
Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator 1
Conditional Independence in Testing Bayesian Networks 3
Conditioning by adaptive sampling for robust design 3
Connectivity-Optimized Representation Learning via Persistent Homology 5
Context-Aware Zero-Shot Learning for Object Recognition 3
Contextual Memory Trees 5
Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Model 3
Control Regularization for Reduced Variance Reinforcement Learning 4
Convolutional Poisson Gamma Belief Network 5
Coresets for Ordered Weighted Clustering 3
Correlated Variational Auto-Encoders 5
Correlated bandits or: How to minimize mean-squared error online 1
Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models 2
Counterfactual Visual Explanations 4
Cross-Domain 3D Equivariant Image Embeddings 3
Curiosity-Bottleneck: Exploration By Distilling Task-Specific Novelty 4
Curvature-Exploiting Acceleration of Elastic Net Computations 3
DAG-GNN: DAG Structure Learning with Graph Neural Networks 3
DBSCAN++: Towards fast and scalable density clustering 3
DL2: Training and Querying Neural Networks with Logic 5
DP-GP-LVM: A Bayesian Non-Parametric Model for Learning Multivariate Dependency Structures 2
Data Poisoning Attacks on Stochastic Bandits 2
Data Shapley: Equitable Valuation of Data for Machine Learning 3
Dead-ends and Secure Exploration in Reinforcement Learning 4
Decentralized Exploration in Multi-Armed Bandits 2
Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication 3
Decomposing feature-level variation with Covariate Gaussian Process Latent Variable Models 3
Deep Compressed Sensing 4
Deep Counterfactual Regret Minimization 2
Deep Factors for Forecasting 4
Deep Gaussian Processes with Importance-Weighted Variational Inference 4
Deep Generative Learning via Variational Gradient Flow 2
Deep Residual Output Layers for Neural Language Generation 4
DeepMDP: Learning Continuous Latent Space Models for Representation Learning 3
DeepNose: Using artificial neural networks to represent the space of odorants 3
Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning 1
Demystifying Dropout 3
Detecting Overlapping and Correlated Communities without Pure Nodes: Identifiability and Algorithm 3
Diagnosing Bottlenecks in Deep Q-learning Algorithms 3
Differentiable Dynamic Normalization for Learning Deep Representation 3
Differentiable Linearized ADMM 3
Differential Inclusions for Modeling Nonsmooth ADMM Variants: A Continuous Limit Theory 1
Differentially Private Empirical Risk Minimization with Non-convex Loss Functions 1
Differentially Private Fair Learning 3
Differentially Private Learning of Geometric Concepts 1
Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning 4
Dimensionality Reduction for Tukey Regression 3
Direct Uncertainty Prediction for Medical Second Opinions 3
Dirichlet Simplex Nest and Geometric Inference 3
Discovering Conditionally Salient Features with Statistical Guarantees 1
Discovering Context Effects from Raw Choice Data 2
Discovering Latent Covariance Structures for Multiple Time Series 4
Discovering Options for Exploration by Minimizing Cover Time 3
Discriminative Regularization for Latent Variable Models with Applications to Electrocardiography 3
Disentangled Graph Convolutional Networks 4
Disentangling Disentanglement in Variational Autoencoders 2
Distributed Learning over Unreliable Networks 5
Distributed Learning with Sublinear Communication 1
Distributed Weighted Matching via Randomized Composable Coresets 1
Distributed, Egocentric Representations of Graphs for Detecting Critical Structures 5
Distribution calibration for regression 2
Distributional Multivariate Policy Evaluation and Exploration with the Bellman GAN 4
Distributional Reinforcement Learning for Efficient Exploration 3
Do ImageNet Classifiers Generalize to ImageNet? 3
Does Data Augmentation Lead to Positive Margin? 0
Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment 1
Domain Agnostic Learning with Disentangled Representations 3
DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-pass Error-Compensated Compression 4
Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random 4
Doubly-Competitive Distribution Estimation 0
Dropout as a Structured Shrinkage Prior 2
Dual Entangled Polynomial Code: Three-Dimensional Coding for Distributed Matrix Multiplication 2
Dynamic Learning with Frequent New Product Launches: A Sequential Multinomial Logit Bandit Problem 2
Dynamic Measurement Scheduling for Event Forecasting using Deep RL 4
Dynamic Weights in Multi-Objective Deep Reinforcement Learning 4
EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE 3
ELF OpenGo: an analysis and open reimplementation of AlphaZero 4
EMI: Exploration with Mutual Information 4
Efficient Amortised Bayesian Inference for Hierarchical and Nonlinear Dynamical Systems 2
Efficient Dictionary Learning with Gradient Descent 0
Efficient Full-Matrix Adaptive Regularization 4
Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal Iterations 5
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables 4
Efficient On-Device Models using Neural Projections 3
Efficient Training of BERT by Progressively Stacking 6
Efficient learning of smooth probability functions from Bernoulli tests with guarantees 2
Efficient optimization of loops and limits with randomized telescoping sums 5
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks 4
EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis 4
Emerging Convolutions for Generative Normalizing Flows 2
Empirical Analysis of Beam Search Performance Degradation in Neural Sequence Models 1
End-to-End Probabilistic Inference for Nonstationary Audio Analysis 3
Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs 4
Equivariant Transformer Networks 4
Error Feedback Fixes SignSGD and other Gradient Compression Schemes 4
Escaping Saddle Points with Adaptive Gradient Methods 3
Estimate Sequences for Variance-Reduced Stochastic Composite Optimization 3
Estimating Information Flow in Deep Neural Networks 2
Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation 3
Exploiting Worker Correlation for Label Aggregation in Crowdsourcing 3
Exploiting structure of uncertainty for efficient matroid semi-bandits 2
Exploration Conscious Reinforcement Learning Revisited 4
Exploring interpretable LSTM neural networks over multi-variable data 3
Exploring the Landscape of Spatial Robustness 2
Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations 5
Fair Regression: Quantitative Definitions and Reduction-Based Algorithms 3
Fair k-Center Clustering for Data Summarization 5
Fairness risk measures 3
Fairness without Harm: Decoupled Classifiers with Preference Guarantees 4
Fairness-Aware Learning for Continuous Attributes and Treatments 4
Fairwashing: the risk of rationalization 5
Fast Algorithm for Generalized Multinomial Models with Ranking Data 3
Fast Context Adaptation via Meta-Learning 5
Fast Direct Search in an Optimally Compressed Continuous Target Space for Efficient Multi-Label Active Learning 3
Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications 6
Fast Rates for a kNN Classifier Robust to Unknown Asymmetric Label Noise 1
Fast and Flexible Inference of Joint Distributions from their Marginals 4
Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations 3
Fast and Stable Maximum Likelihood Estimation for Incomplete Multinomial Models 2
Faster Algorithms for Binary Matrix Factorization 2
Faster Attend-Infer-Repeat with Tractable Probabilistic Models 3
Faster Stochastic Alternating Direction Method of Multipliers for Nonconvex Optimization 4
Fault Tolerance in Iterative-Convergent Machine Learning 3
Feature Grouping as a Stochastic Regularizer for High-Dimensional Structured Data 6
Feature-Critic Networks for Heterogeneous Domain Generalization 5
Finding Mixed Nash Equilibria of Generative Adversarial Networks 3
Finding Options that Minimize Planning Time 0
Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks 2
Fingerprint Policy Optimisation for Robust Reinforcement Learning 4
Finite-Time Analysis of Distributed TD(0) with Linear Function Approximation on Multi-Agent Reinforcement Learning 1
First-Order Adversarial Vulnerability of Neural Networks and Input Dimension 3
First-Order Algorithms Converge Faster than $O(1/k)$ on Convex Problems 0
Flat Metric Minimization with Applications in Generative Modeling 3
Flexibly Fair Representation Learning by Disentanglement 1
FloWaveNet : A Generative Flow for Raw Audio 4
Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design 4
Formal Privacy for Functional Data with Gaussian Perturbations 4
Functional Transparency for Structured Data: a Game-Theoretic Approach 2
GDPP: Learning Diverse Generations using Determinantal Point Processes 3
GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects 4
GMNN: Graph Markov Neural Networks 4
GOODE: A Gaussian Off-The-Shelf Ordinary Differential Equation Solver 3
Gaining Free or Low-Cost Interpretability with Interpretable Partial Substitute 5
Game Theoretic Optimization via Gradient-based Nikaido-Isoda Function 1
Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits 3
Gauge Equivariant Convolutional Networks and the Icosahedral CNN 3
Generalized Approximate Survey Propagation for High-Dimensional Estimation 2
Generalized Linear Rule Models 4
Generalized Majorization-Minimization 4
Generalized No Free Lunch Theorem for Adversarial Robustness 2
Generative Adversarial User Model for Reinforcement Learning Based Recommendation System 3
Generative Modeling of Infinite Occluded Objects for Compositional Scene Representation 3
Geometric Losses for Distributional Learning 4
Geometric Scattering for Graph Data Analysis 3
Geometry Aware Convolutional Filters for Omnidirectional Images Representation 3
Geometry and Symmetry in Short-and-Sparse Deconvolution 2
Global Convergence of Block Coordinate Descent in Deep Learning 3
Good Initializations of Variational Bayes for Deep Models 4
Gradient Descent Finds Global Minima of Deep Neural Networks 0
Graph Convolutional Gaussian Processes 2
Graph Element Networks: adaptive, structured computation and memory 3
Graph Matching Networks for Learning the Similarity of Graph Structured Objects 3
Graph Neural Network for Music Score Data and Modeling Expressive Piano Performance 3
Graph Resistance and Learning from Pairwise Comparisons 0
Graph U-Nets 3
Graphical-model based estimation and inference for differential privacy 2
Graphite: Iterative Generative Modeling of Graphs 2
Greedy Layerwise Learning Can Scale To ImageNet 4
Greedy Orthogonal Pivoting Algorithm for Non-Negative Matrix Factorization 4
Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI 1
Gromov-Wasserstein Learning for Graph Matching and Node Embedding 5
Guarantees for Spectral Clustering with Fairness Constraints 4
Guided evolutionary strategies: augmenting random search with surrogate gradients 3
HOList: An Environment for Machine Learning of Higher Order Logic Theorem Proving 4
Hessian Aided Policy Gradient 4
Heterogeneous Model Reuse via Optimizing Multiparty Multiclass Margin 2
HexaGAN: Generative Adversarial Nets for Real World Classification 4
Hierarchical Decompositional Mixtures of Variational Autoencoders 5
Hierarchical Importance Weighted Autoencoders 2
Hierarchically Structured Meta-learning 3
High-Fidelity Image Generation With Fewer Labels 5
Hiring Under Uncertainty 2
Homomorphic Sensing 3
How does Disagreement Help Generalization against Label Corruption? 4
Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops 4
Hybrid Models with Deep and Invertible Features 2
HyperGAN: A Generative Model for Diverse, Performant Neural Networks 3
Hyperbolic Disk Embeddings for Directed Acyclic Graphs 2
IMEXnet A Forward Stable Deep Neural Network 5
Imitating Latent Policies from Observation 3
Imitation Learning from Imperfect Demonstration 3
Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition 2
Importance Sampling Policy Evaluation with an Estimated Behavior Policy 1
Improved Convergence for $\ell_1$ and $\ell_∞$ Regression via Iteratively Reweighted Least Squares 1
Improved Dynamic Graph Learning through Fault-Tolerant Sparsification 3
Improved Parallel Algorithms for Density-Based Network Clustering 2
Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization 3
Improving Adversarial Robustness via Promoting Ensemble Diversity 5
Improving Model Selection by Employing the Test Data 2
Improving Neural Language Modeling via Adversarial Training 5
Improving Neural Network Quantization without Retraining using Outlier Channel Splitting 5
Imputing Missing Events in Continuous-Time Event Streams 5
Incorporating Grouping Information into Bayesian Decision Tree Ensembles 3
Incremental Randomized Sketching for Online Kernel Learning 5
Inference and Sampling of $K_33$-free Ising Models 1
Inferring Heterogeneous Causal Effects in Presence of Spatial Confounding 3
Infinite Mixture Prototypes for Few-shot Learning 5
Information-Theoretic Considerations in Batch Reinforcement Learning 0
Insertion Transformer: Flexible Sequence Generation via Insertion Operations 4
Interpreting Adversarially Trained Convolutional Neural Networks 3
Invariant-Equivariant Representation Learning for Multi-Class Data 3
Invertible Residual Networks 5
Iterative Linearized Control: Stable Algorithms and Complexity Guarantees 3
Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks 3
Jumpout : Improved Dropout for Deep Neural Networks with ReLUs 4
Katalyst: Boosting Convex Katayusha for Non-Convex Problems with a Large Condition Number 3
Kernel Mean Matching for Content Addressability of GANs 3
Kernel Normalized Cut: a Theoretical Revisit 2
Kernel-Based Reinforcement Learning in Robust Markov Decision Processes 3
LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning 5
LIT: Learned Intermediate Representation Training for Model Compression 4
LR-GLM: High-Dimensional Bayesian Inference Using Low-Rank Data Approximations 3
Ladder Capsule Network 4
Large-Scale Sparse Kernel Canonical Correlation Analysis 5
Latent Normalizing Flows for Discrete Sequences 3
LatentGNN: Learning Efficient Non-local Relations for Visual Recognition 4
Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting 1
Learning Action Representations for Reinforcement Learning 2
Learning Classifiers for Target Domain with Limited or No Labels 3
Learning Context-dependent Label Permutations for Multi-label Classification 4
Learning Dependency Structures for Weak Supervision Models 2
Learning Discrete Structures for Graph Neural Networks 5
Learning Discrete and Continuous Factors of Data via Alternating Disentanglement 5
Learning Distance for Sequences by Learning a Ground Metric 4
Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations 3
Learning Generative Models across Incomparable Spaces 3
Learning Hawkes Processes Under Synchronization Noise 4
Learning Latent Dynamics for Planning from Pixels 5
Learning Linear-Quadratic Regulators Efficiently with only $\sqrtT$ Regret 1
Learning Models from Data with Measurement Error: Tackling Underreporting 1
Learning Neurosymbolic Generative Models via Program Synthesis 2
Learning Novel Policies For Tasks 2
Learning Optimal Fair Policies 1
Learning Optimal Linear Regularizers 4
Learning Structured Decision Problems with Unawareness 2
Learning What and Where to Transfer 3
Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling 5
Learning a Prior over Intent via Meta-Inverse Reinforcement Learning 3
Learning and Data Selection in Big Datasets 4
Learning deep kernels for exponential family densities 5
Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems 3
Learning from a Learner 3
Learning interpretable continuous-time models of latent stochastic dynamical systems 1
Learning to Clear the Market 2
Learning to Collaborate in Markov Decision Processes 1
Learning to Convolve: A Generalized Weight-Tying Approach 3
Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs 4
Learning to Generalize from Sparse and Underspecified Rewards 4
Learning to Groove with Inverse Sequence Transformations 3
Learning to Infer Program Sketches 4
Learning to Optimize Multigrid PDE Solvers 2
Learning to Prove Theorems via Interacting with Proof Assistants 5
Learning to Route in Similarity Graphs 6
Learning to bid in revenue-maximizing auctions 3
Learning to select for a predefined ranking 4
Learning with Bad Training Data via Iterative Trimmed Loss Minimization 3
Learning-to-Learn Stochastic Gradient Descent with Biased Regularization 4
LegoNet: Efficient Convolutional Neural Networks with Lego Filters 4
Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction 5
Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models 0
Linear-Complexity Data-Parallel Earth Mover’s Distance Approximations 4
Lipschitz Generative Adversarial Nets 3
Locally Private Bayesian Inference for Count Models 2
Look Ma, No Latent Variables: Accurate Cutset Networks via Compilation 4
Lorentzian Distance Learning for Hyperbolic Representations 3
Loss Landscapes of Regularized Linear Autoencoders 4
Lossless or Quantized Boosting with Integer Arithmetic 5
Low Latency Privacy Preserving Inference 5
Lower Bounds for Smooth Nonconvex Finite-Sum Optimization 0
MASS: Masked Sequence to Sequence Pre-training for Language Generation 5
ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation 3
MIWAE: Deep Generative Modelling and Imputation of Incomplete Data Sets 3
MONK Outlier-Robust Mean Embedding Estimation by Median-of-Means 4
Making Convolutional Networks Shift-Invariant Again 3
Making Decisions that Reduce Discriminatory Impacts 3
Making Deep Q-learning methods robust to time discretization 3
Mallows ranking models: maximum likelihood estimate and regeneration 3
Manifold Mixup: Better Representations by Interpolating Hidden States 2
Matrix-Free Preconditioning in Online Learning 3
Maximum Entropy-Regularized Multi-Goal Reinforcement Learning 3
Maximum Likelihood Estimation for Learning Populations of Parameters 2
MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization 4
Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians 3
Memory-Optimal Direct Convolutions for Maximizing Classification Accuracy in Embedded Applications 4
Meta-Learning Neural Bloom Filters 4
Metric-Optimized Example Weights 5
MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement 4
Metropolis-Hastings Generative Adversarial Networks 5
Minimal Achievable Sufficient Statistic Learning 3
MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing 5
Mixture Models for Diverse Machine Translation: Tricks of the Trade 5
Model Comparison for Semantic Grouping 2
Model Function Based Conditional Gradient Method with Armijo-like Line Search 2
Model-Based Active Exploration 4
Molecular Hypergraph Grammar with Its Application to Molecular Optimization 4
Moment-Based Variational Inference for Markov Jump Processes 1
Monge blunts Bayes: Hardness Results for Adversarial Training 2
More Efficient Off-Policy Evaluation through Regularized Targeted Learning 2
Multi-Agent Adversarial Inverse Reinforcement Learning 3
Multi-Frequency Phase Synchronization 2
Multi-Frequency Vector Diffusion Maps 2
Multi-Object Representation Learning with Iterative Variational Inference 3
Multi-objective training of Generative Adversarial Networks with multiple discriminators 3
Multiplicative Weights Updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost always 0
Multivariate Submodular Optimization 0
Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching 2
Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments 3
NAS-Bench-101: Towards Reproducible Neural Architecture Search 5
NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks 4
Natural Analysts in Adaptive Data Analysis 0
Near optimal finite time identification of arbitrary linear dynamical systems 0
Nearest Neighbor and Kernel Survival Analysis: Nonasymptotic Error Bounds and Strong Consistency Rates 3
Neural Collaborative Subspace Clustering 5
Neural Inverse Knitting: From Images to Manufacturing Instructions 5
Neural Joint Source-Channel Coding 3
Neural Logic Reinforcement Learning 2
Neural Network Attributions: A Causal Perspective 3
Neural Separation of Observed and Unobserved Distributions 3
Neurally-Guided Structure Inference 5
Neuron birth-death dynamics accelerates gradient descent and converges asymptotically 2
New results on information theoretic clustering 4
Noise2Self: Blind Denoising by Self-Supervision 3
Noisy Dual Principal Component Pursuit 4
Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization 0
Non-Monotonic Sequential Text Generation 4
Non-Parametric Priors For Generative Adversarial Networks 2
Non-monotone Submodular Maximization with Nearly Optimal Adaptivity and Query Complexity 3
Nonconvex Variance Reduced Optimization with Arbitrary Sampling 3
Nonlinear Distributional Gradient Temporal-Difference Learning 3
Nonlinear Stein Variational Gradient Descent for Learning Diversified Mixture Models 5
Nonparametric Bayesian Deep Networks with Local Competition 3
Obtaining Fairness using Optimal Transport Theory 2
Off-Policy Deep Reinforcement Learning without Exploration 4
On Certifying Non-Uniform Bounds against Adversarial Attacks 5
On Connected Sublevel Sets in Deep Learning 0
On Dropout and Nuclear Norm Regularization 2
On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithms 3
On Learning Invariant Representations for Domain Adaptation 2
On Medians of (Randomized) Pairwise Means 1
On Scalable and Efficient Computation of Large Scale Optimal Transport 4
On Sparse Linear Regression in the Local Differential Privacy Model 2
On Symmetric Losses for Learning from Corrupted Labels 3
On The Power of Curriculum Learning in Training Deep Networks 5
On Variational Bounds of Mutual Information 2
On discriminative learning of prediction uncertainty 3
On the Complexity of Approximating Wasserstein Barycenters 2
On the Computation and Communication Complexity of Parallel SGD with Dynamic Batch Sizes for Stochastic Non-Convex Optimization 3
On the Connection Between Adversarial Robustness and Saliency Map Interpretability 4
On the Convergence and Robustness of Adversarial Training 3
On the Design of Estimators for Bandit Off-Policy Evaluation 2
On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference 3
On the Generalization Gap in Reparameterizable Reinforcement Learning 2
On the Impact of the Activation function on Deep Neural Networks Training 3
On the Limitations of Representing Functions on Sets 1
On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization 5
On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learning 2
On the Spectral Bias of Neural Networks 3
On the Universality of Invariant Networks 0
On the statistical rate of nonlinear recovery in generative models with heavy-tailed data 0
Online Adaptive Principal Component Analysis and Its extensions 4
Online Algorithms for Rent-Or-Buy with Expert Advice 2
Online Control with Adversarial Disturbances 1
Online Convex Optimization in Adversarial Markov Decision Processes 1
Online Learning to Rank with Features 4
Online Learning with Sleeping Experts and Feedback Graphs 2
Online Meta-Learning 3
Online Variance Reduction with Mixtures 5
Online learning with kernel losses 1
Open Vocabulary Learning on Source Code with a Graph-Structured Cache 3
Open-ended learning in symmetric zero-sum games 3
Optimal Algorithms for Lipschitz Bandits with Heavy-tailed Rewards 2
Optimal Auctions through Deep Learning 4
Optimal Continuous DR-Submodular Maximization and Applications to Provable Mean Field Inference 4
Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning 5
Optimal Mini-Batch and Step Sizes for SAGA 4
Optimal Minimal Margin Maximization with Boosting 4
Optimal Transport for structured data with application on graphs 5
Optimality Implies Kernel Sum Classifiers are Statistically Efficient 1
Optimistic Policy Optimization via Multiple Importance Sampling 4
Orthogonal Random Forest for Causal Inference 3
Overcoming Mean-Field Approximations in Recurrent Gaussian Process Models 3
Overcoming Multi-model Forgetting 4
Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path? 2
PA-GD: On the Convergence of Perturbed Alternating Gradient Descent to Second-Order Stationary Points for Structured Nonconvex Optimization 2
PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits 2
PAC Learnability of Node Functions in Networked Dynamical Systems 2
POLITEX: Regret Bounds for Policy Iteration using Expert Prediction 3
POPQORN: Quantifying Robustness of Recurrent Neural Networks 5
PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach 4
Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization 5
Parameter-Efficient Transfer Learning for NLP 4
Pareto Optimal Streaming Unsupervised Classification 2
Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization 5
Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computation 2
Partially Linear Additive Gaussian Graphical Models 2
Particle Flow Bayes’ Rule 3
Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models 2
Per-Decision Option Discounting 2
Phase transition in PCA with missing data: Reduced signal-to-noise ratio, not sample size! 3
Phaseless PCA: Low-Rank Matrix Recovery from Column-wise Phaseless Measurements 2
Plug-and-Play Methods Provably Converge with Properly Trained Denoisers 4
Poission Subsampled Rényi Differential Privacy 2
Policy Certificates: Towards Accountable Reinforcement Learning 2
Policy Consolidation for Continual Reinforcement Learning 2
Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules 6
Position-aware Graph Neural Networks 4
Power k-Means Clustering 3
Predicate Exchange: Inference with Declarative Knowledge 4
Predictor-Corrector Policy Optimization 4
Probabilistic Neural Symbolic Models for Interpretable Visual Question Answering 4
Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning 1
Processing Megapixel Images with Deep Attention-Sampling Models 3
Projection onto Minkowski Sums with Application to Constrained Learning 3
Projections for Approximate Policy Iteration Algorithms 5
Proportionally Fair Clustering 3
Provable Guarantees for Gradient-Based Meta-Learning 3
Provably Efficient Imitation Learning from Observation Alone 4
Provably Efficient Maximum Entropy Exploration 4
Provably efficient RL with Rich Observations via Latent State Decoding 3
QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning 2
Quantifying Generalization in Reinforcement Learning 2
Quantile Stein Variational Gradient Descent for Batch Bayesian Optimization 3
RaFM: Rank-Aware Factorization Machines 5
Rademacher Complexity for Adversarially Robust Generalization 2
Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation 3
Random Function Priors for Correlation Modeling 3
Random Matrix Improved Covariance Estimation for a Large Class of Metrics 4
Random Shuffling Beats SGD after Finite Epochs 0
Random Walks on Hypergraphs with Edge-Dependent Vertex Weights 3
Rao-Blackwellized Stochastic Gradients for Discrete Distributions 4
Rate Distortion For Model Compression:From Theory To Practice 2
Rates of Convergence for Sparse Variational Gaussian Process Regression 1
Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces 2
Recursive Sketches for Modular Deep Learning 1
Refined Complexity of PCA with Outliers 0
Regret Circuits: Composability of Regret Minimizers 0
Regularization in directable environments with application to Tetris 3
Rehashing Kernel Evaluation in High Dimensions 4
Reinforcement Learning in Configurable Continuous Environments 2
Relational Pooling for Graph Representations 3
Remember and Forget for Experience Replay 3
Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions 5
Replica Conditional Sequential Monte Carlo 4
Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff 1
Revisiting precision recall definition for generative modeling 3
Revisiting the Softmax Bellman Operator: New Benefits and New Perspective 3
Riemannian adaptive stochastic gradient algorithms on matrix manifolds 5
Robust Decision Trees Against Adversarial Examples 5
Robust Estimation of Tree Structured Gaussian Graphical Models 0
Robust Inference via Generative Classifiers for Handling Noisy Labels 4
Robust Influence Maximization for Hyperparametric Models 2
Robust Learning from Untrusted Sources 5
Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness 3
Rotation Invariant Householder Parameterization for Bayesian PCA 3
SAGA with Arbitrary Sampling 3
SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver 4
SELFIE: Refurbishing Unclean Samples for Robust Deep Learning 6
SGD without Replacement: Sharper Rates for General Smooth Convex Functions 1
SGD: General Analysis and Improved Rates 2
SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning 4
SWALP : Stochastic Weight Averaging in Low Precision Training 4
Safe Grid Search with Optimal Complexity 5
Safe Policy Improvement with Baseline Bootstrapping 3
Same, Same But Different: Recovering Neural Network Quantization Error Through Weight Factorization 5
Sample-Optimal Parametric Q-Learning Using Linearly Additive Features 1
Scalable Fair Clustering 4
Scalable Learning in Reproducing Kernel Krein Spaces 3
Scalable Metropolis-Hastings for Exact Bayesian Inference with Large Datasets 3
Scalable Nonparametric Sampling from Multimodal Posteriors with the Posterior Bootstrap 6
Scalable Training of Inference Networks for Gaussian-Process Models 5
Scale-free adaptive planning for deterministic dynamics & discounted rewards 2
Scaling Up Ordinal Embedding: A Landmark Approach 5
Screening rules for Lasso with non-convex Sparse Regularizers 4
SelectiveNet: A Deep Neural Network with an Integrated Reject Option 3
Self-Attention Generative Adversarial Networks 3
Self-Attention Graph Pooling 5
Self-Supervised Exploration via Disagreement 4
Self-similar Epochs: Value in arrangement 3
Semi-Cyclic Stochastic Gradient Descent 3
Sensitivity Analysis of Linear Structural Causal Models 2
Separating value functions across time-scales 3
Sequential Facility Location: Approximate Submodularity and Greedy Algorithm 3
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks 3
Sever: A Robust Meta-Algorithm for Stochastic Optimization 5
Shallow-Deep Networks: Understanding and Mitigating Network Overthinking 4
Shape Constraints for Set Functions 2
Similarity of Neural Network Representations Revisited 2
Simple Black-box Adversarial Attacks 5
Simple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization 4
Simplifying Graph Convolutional Networks 5
Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions 3
Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning 2
Sorting Out Lipschitz Function Approximation 3
Sparse Extreme Multi-label Learning with Oracle Property 4
Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data 3
Spectral Approximate Inference 3
Spectral Clustering of Signed Graphs via Matrix Power Means 3
Stable and Fair Classification 3
Stable-Predictive Optimistic Counterfactual Regret Minimization 2
State-Regularized Recurrent Neural Networks 6
State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations 2
Static Automatic Batching In TensorFlow 3
Statistical Foundations of Virtual Democracy 2
Statistics and Samples in Distributional Reinforcement Learning 3
Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With Reneging 2
Stein Point Markov Chain Monte Carlo 2
Stochastic Beams and Where To Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement 4
Stochastic Blockmodels meet Graph Neural Networks 3
Stochastic Deep Networks 3
Stochastic Gradient Push for Distributed Deep Learning 6
Stochastic Iterative Hard Thresholding for Graph-structured Sparsity Optimization 6
Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence 3
Structured agents for physical construction 1
Sublinear Space Private Algorithms Under the Sliding Window Model 1
Sublinear Time Nearest Neighbor Search over Generalized Weighted Space 2
Sublinear quantum algorithms for training linear and kernel-based classifiers 1
Submodular Cost Submodular Cover with an Approximate Oracle 2
Submodular Maximization beyond Non-negativity: Guarantees, Fast Algorithms, and Applications 5
Submodular Observation Selection and Information Gathering for Quadratic Models 2
Submodular Streaming in All Its Glory: Tight Approximation, Minimum Memory and Low Adaptive Complexity 2
Subspace Robust Wasserstein Distances 2
Sum-of-Squares Polynomial Flow 3
Supervised Hierarchical Clustering with Exponential Linkage 5
Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization 3
Switching Linear Dynamics for Variational Bayes Filtering 0
Taming MAML: Efficient unbiased meta-reinforcement learning 1
TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning 5
TarMAC: Targeted Multi-Agent Communication 2
Target Tracking for Contextual Bandits: Application to Demand Side Management 3
Target-Based Temporal-Difference Learning 2
Task-Agnostic Dynamics Priors for Deep Reinforcement Learning 3
Teaching a black-box learner 3
Temporal Gaussian Mixture Layer for Videos 4
Tensor Variable Elimination for Plated Factor Graphs 4
TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing 5
The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects 2
The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study 2
The Evolved Transformer 5
The Implicit Fairness Criterion of Unconstrained Learning 3
The Kernel Interaction Trick: Fast Bayesian Discovery of Pairwise Interactions in High Dimensions 3
The Natural Language of Actions 1
The Odds are Odd: A Statistical Test for Detecting Adversarial Examples 3
The Value Function Polytope in Reinforcement Learning 1
The Variational Predictive Natural Gradient 4
The Wasserstein Transform 2
The advantages of multiple classes for reducing overfitting from test set reuse 2
The information-theoretic value of unlabeled data in semi-supervised learning 0
Theoretically Principled Trade-off between Robustness and Accuracy 4
TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning 3
Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel $k$-means Clustering 0
Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds 1
Topological Data Analysis of Decision Boundaries with Application to Model Selection 3
Toward Controlling Discrimination in Online Ad Auctions 3
Toward Understanding the Importance of Noise in Training Neural Networks 2
Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation 5
Towards Understanding Knowledge Distillation 2
Towards a Deep and Unified Understanding of Deep Neural Models in NLP 3
Towards a Unified Analysis of Random Fourier Features 3
Trading Redundancy for Communication: Speeding up Distributed SGD for Non-convex Optimization 4
Traditional and Heavy Tailed Self Regularization in Neural Network Models 3
Trainable Decoding of Sets of Sequences for Neural Sequence Models 5
Training CNNs with Selective Allocation of Channels 4
Training Neural Networks with Local Error Signals 3
Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints 4
Trajectory-Based Off-Policy Deep Reinforcement Learning 4
Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation 4
Transfer of Samples in Policy Search via Multiple Importance Sampling 1
Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation 4
Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers 5
Transferable Clean-Label Poisoning Attacks on Deep Neural Nets 4
Trimming the $\ell_1$ Regularizer: Statistical Analysis, Optimization, and Applications to Deep Learning 4
Understanding Geometry of Encoder-Decoder CNNs 0
Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation 5
Understanding MCMC Dynamics as Flows on the Wasserstein Space 3
Understanding Priors in Bayesian Neural Networks at the Unit Level 1
Understanding and Accelerating Particle-Based Variational Inference 4
Understanding and Controlling Memory in Recurrent Neural Networks 4
Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels 5
Understanding and correcting pathologies in the training of learned optimizers 4
Understanding the Impact of Entropy on Policy Optimization 1
Understanding the Origins of Bias in Word Embeddings 4
Uniform Convergence Rate of the Kernel Density Estimator Adaptive to Intrinsic Volume Dimension 0
Unifying Orthogonal Monte Carlo Methods 2
Universal Multi-Party Poisoning Attacks 0
Unreproducible Research is Reproducible 3
Unsupervised Deep Learning by Neighbourhood Discovery 4
Unsupervised Label Noise Modeling and Loss Correction 4
Using Pre-Training Can Improve Model Robustness and Uncertainty 3
Validating Causal Inference Models via Influence Functions 3
Variational Annealing of GANs: A Langevin Perspective 4
Variational Implicit Processes 4
Variational Inference for sparse network reconstruction from count data 3
Variational Laplace Autoencoders 5
Variational Russian Roulette for Deep Bayesian Nonparametrics 4
Voronoi Boundary Classification: A High-Dimensional Geometric Approach via Weighted Monte Carlo Integration 6
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback 4
Wasserstein Adversarial Examples via Projected Sinkhorn Iterations 5
Wasserstein of Wasserstein Loss for Learning Generative Models 3
Weak Detection of Signal in the Spiked Wigner Model 1
Weakly-Supervised Temporal Localization via Occurrence Count Learning 3
What is the Effect of Importance Weighting in Deep Learning? 2
When Samples Are Strategically Selected 0
White-box vs Black-box: Bayes Optimal Strategies for Membership Inference 3
Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem 2
Width Provably Matters in Optimization for Deep Linear Neural Networks 0
Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerance 4
Zero-Shot Knowledge Distillation in Deep Networks 3
kernelPSI: a Post-Selection Inference Framework for Nonlinear Variable Selection 2