# Downloads 2019

Number of events: 822

- $\texttt{DoubleSqueeze}$: Parallel Stochastic Gradient Descent with Double-pass Error-Compensated Compression
- 6th ICML Workshop on Automated Machine Learning (AutoML 2019)
- A Baseline for Any Order Gradient Estimation in Stochastic Computation Graphs
- A Better k-means++ Algorithm via Local Search
- A Block Coordinate Descent Proximal Method for Simultaneous Filtering and Parameter Estimation
- Accelerated Flow for Probability Distributions
- Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances
- Acceleration of SVRG and Katyusha X by Inexact Preconditioning
- A Composite Randomized Incremental Gradient Method
- A Conditional-Gradient-Based Augmented Lagrangian Framework
- A Contrastive Divergence for Combining Variational Inference and MCMC
- A Convergence Theory for Deep Learning via Over-Parameterization
- Action Robust Reinforcement Learning and Applications in Continuous Control
- Active Embedding Search via Noisy Paired Comparisons
- Active Hypothesis Testing: An Information Theoretic (re)View
- Active Learning for Decision-Making from Imbalanced Observational Data
- Active Learning for Probabilistic Structured Prediction of Cuts and Matchings
- Active Learning: From Theory to Practice
- Active Learning with Disagreement Graphs
- Active Manifolds: A non-linear analogue to Active Subspaces
- Actor-Attention-Critic for Multi-Agent Reinforcement Learning
- AdaGrad stepsizes: sharp convergence over nonconvex landscapes
- Adaptive and Multitask Learning: Algorithms & Systems
- Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspaces
- Adaptive Antithetic Sampling for Variance Reduction
- Adaptive Monte Carlo Multiple Testing via Multi-Armed Bandits
- Adaptive Neural Trees
- Adaptive Regret of Convex and Smooth Functions
- Adaptive Scale-Invariant Online Algorithms for Learning Linear Models
- Adaptive Sensor Placement for Continuous Spaces
- Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search
- Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment
- A Deep Reinforcement Learning Perspective on Internet Congestion Control
- Adjustment Criteria for Generalizing Experimental Findings
- Adversarial Attacks on Node Embeddings via Graph Poisoning
- Adversarial camera stickers: A physical camera-based attack on deep learning systems
- Adversarial Examples Are a Natural Consequence of Test Error in Noise
- Adversarial examples from computational constraints
- Adversarial Generation of Time-Frequency Features with application in audio synthesis
- Adversarially Learned Representations for Information Obfuscation and Inference
- Adversarial Online Learning with noise
- A Dynamical Systems Perspective on Nesterov Acceleration
- A Framework for Bayesian Optimization in Embedded Subspaces
- A fully differentiable beam search decoder
- Agnostic Federated Learning
- A Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein Minimization
- AI For Social Good (AISG)
- AI in Finance: Applications and Infrastructure for Multi-Agent Learning
- A Kernel Perspective for Regularizing Deep Neural Networks
- A Kernel Theory of Modern Data Augmentation
- A Large-Scale Study on Regularization and Normalization in GANs
- Algorithm configuration: learning in the space of algorithm designs
- Almost surely constrained convex optimization
- Almost Unsupervised Text to Speech and Automatic Speech Recognition
- Alternating Minimizations Converge to Second-Order Optimal Solutions
- Amortized Monte Carlo Integration
- A Multitask Multiple Kernel Learning Algorithm for Survival Analysis with Application to Cancer Biology
- Analogies Explained: Towards Understanding Word Embeddings
- Analyzing and Improving Representations with the Soft Nearest Neighbor Loss
- Analyzing Federated Learning through an Adversarial Lens
- An Instability in Variational Inference for Topic Models
- An Investigation into Neural Net Optimization via Hessian Eigenvalue Density
- An Investigation of Model-Free Planning
- Anomaly Detection With Multiple-Hypotheses Predictions
- An Optimal Private Stochastic-MAB Algorithm based on Optimal Private Stopping Rule
- Anytime Online-to-Batch, Optimism and Acceleration
- A Persistent Weisfeiler--Lehman Procedure for Graph Classification
- A Personalized Affective Memory Model for Improving Emotion Recognition
- A Polynomial Time MCMC Method for Sampling from Continuous Determinantal Point Processes
- Approximated Oracle Filter Pruning for Destructive CNN Width Optimization
- Approximating Orthogonal Matrices with Effective Givens Factorization
- Approximation and non-parametric estimation of ResNet-type convolutional neural networks
- A Primer on PAC-Bayesian Learning
- A Quantitative Analysis of the Effect of Batch Normalization on Gradient Descent
- Area Attention
- A Recurrent Neural Cascade-based Model for Continuous-Time Diffusion
- Are Generative Classifiers More Robust to Adversarial Attacks?
- AReS and MaRS - Adversarial and MMD-Minimizing Regression for SDEs
- ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables
- A Statistical Investigation of Long Memory in Language and Music
- Asynchronous Batch Bayesian Optimisation with Improved Local Penalisation
- A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks
- A Theoretical Analysis of Contrastive Unsupervised Representation Learning
- A Theory of Regularized Markov Decision Processes
- A Tree-Based Method for Fast Repeated Sampling of Determinantal Point Processes
- A Tutorial on Attention in Deep Learning
- AUCµ: A Performance Metric for Multi-Class Machine Learning Models
- Automated Model Selection with Bayesian Quadrature
- Automatic Classifiers as Scientific Instruments: One Step Further Away from Ground-Truth
- Automatic Posterior Transformation for Likelihood-Free Inference
- Autoregressive Energy Machines
- AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
- A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning
- Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case
- Band-limited Training and Inference for Convolutional Neural Networks
- Batch Policy Learning under Constraints
- Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning
- Bayesian Counterfactual Risk Minimization
- Bayesian Deconditional Kernel Mean Embeddings
- Bayesian Generative Active Deep Learning
- Bayesian Joint Spike-and-Slab Graphical Lasso
- Bayesian leave-one-out cross-validation for large data
- Bayesian Nonparametric Federated Learning of Neural Networks
- Bayesian Optimization Meets Bayesian Optimal Stopping
- Bayesian Optimization of Composite Functions
- BayesNAS: A Bayesian Approach for Neural Architecture Search
- Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously
- Benefits and Pitfalls of the Exponential Mechanism with Applications to Hilbert Spaces and Functional PCA
- BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning
- Best Paper
- Best Paper
- Better generalization with less data using robust gradient descent
- Beyond Adaptive Submodularity: Approximation Guarantees of Greedy Policy with Adaptive Submodularity Ratio
- Beyond Backprop: Online Alternating Minimization with Auxiliary Variables
- Beyond the Chinese Restaurant and Pitman-Yor processes: Statistical Models with double power-law behavior
- Bias Also Matters: Bias Attribution for Deep Neural Network Explanation
- Bilinear Bandits with Low-rank Structure
- Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables
- Blended Conditonal Gradients
- Boosted Density Estimation Remastered
- Bounding User Contributions: A Bias-Variance Trade-off in Differential Privacy
- Breaking Inter-Layer Co-Adaptation by Classifier Anonymization
- Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms
- Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities
- Bridging Theory and Algorithm for Domain Adaptation
- CAB: Continuous Adaptive Blending for Policy Evaluation and Learning
- Calibrated Approximate Bayesian Inference
- Calibrated Model-Based Deep Reinforcement Learning
- CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration
- Categorical Feature Compression via Submodular Optimization
- Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models
- Causal Identification under Markov Equivalence: Completeness Results
- Causal Inference and Stable Learning
- Cautious Regret Minimization: Online Optimization with Long-Term Budget Constraints
- Certified Adversarial Robustness via Randomized Smoothing
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
- Characterization of Convex Objective Functions and Optimal Expected Convergence Rates for SGD
- Characterizing Well-Behaved vs. Pathological Deep Neural Networks
- Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group
- CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network
- Circuit-GNN: Graph Neural Networks for Distributed Circuit Design
- Classification from Positive, Unlabeled and Biased Negative Data
- Classifying Treatment Responders Under Causal Effect Monotonicity
- Climate Change: How Can AI Help?
- Coding Theory For Large-scale Machine Learning
- Cognitive model priors for predicting human decisions
- Collaborative Channel Pruning for Deep Networks
- Collaborative Evolutionary Reinforcement Learning
- Collective Model Fusion for Multiple Black-Box Experts
- Co-manifold learning with missing data
- Combating Label Noise in Deep Learning using Abstention
- Combining parametric and nonparametric models for off-policy evaluation
- COMIC: Multi-view Clustering Without Parameter Selection
- Communication Complexity in Locally Private Distribution Estimation and Heavy Hitters
- Communication-Constrained Inference and the Role of Shared Randomness
- Competing Against Nash Equilibria in Adversarially Changing Zero-Sum Games
- CompILE: Compositional Imitation Learning and Execution
- Complementary-Label Learning for Arbitrary Losses and Models
- Complexity of Linear Regions in Deep Networks
- Composable Core-sets for Determinant Maximization: A Simple Near-Optimal Algorithm
- Composing Entropic Policies using Divergence Correction
- Composing Value Functions in Reinforcement Learning
- Compositional Fairness Constraints for Graph Embeddings
- Compressed Factorization: Fast and Accurate Low-Rank Factorization of Compressively-Sensed Data
- Compressing Gradient Optimizers via Count-Sketches
- Concentration Inequalities for Conditional Value at Risk
- Concrete Autoencoders: Differentiable Feature Selection and Reconstruction
- Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator
- Conditional Independence in Testing Bayesian Networks
- Conditioning by adaptive sampling for robust design
- Connectivity-Optimized Representation Learning via Persistent Homology
- Context-Aware Zero-Shot Learning for Object Recognition
- Contextual Memory Trees
- Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Model
- Control Regularization for Reduced Variance Reinforcement Learning
- Convolutional Poisson Gamma Belief Network
- Co-Representation Network for Generalized Zero-Shot Learning
- Coresets for Ordered Weighted Clustering
- Correlated bandits or: How to minimize mean-squared error online
- Correlated Variational Auto-Encoders
- CoT: Cooperative Training for Generative Modeling of Discrete Data
- Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models
- Counterfactual Visual Explanations
- Cross-Domain 3D Equivariant Image Embeddings
- Curiosity-Bottleneck: Exploration By Distilling Task-Specific Novelty
- CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning
- Curvature-Exploiting Acceleration of Elastic Net Computations
- DAG-GNN: DAG Structure Learning with Graph Neural Networks
- Data Poisoning Attacks in Multi-Party Learning
- Data Poisoning Attacks on Stochastic Bandits
- Data Shapley: Equitable Valuation of Data for Machine Learning
- DBSCAN++: Towards fast and scalable density clustering
- Dead-ends and Secure Exploration in Reinforcement Learning
- Decentralized Exploration in Multi-Armed Bandits
- Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication
- Decomposing feature-level variation with Covariate Gaussian Process Latent Variable Models
- Deep Compressed Sensing
- Deep Counterfactual Regret Minimization
- Deep Factors for Forecasting
- Deep Gaussian Processes with Importance-Weighted Variational Inference
- Deep Generative Learning via Variational Gradient Flow
- DeepMDP: Learning Continuous Latent Space Models for Representation Learning
- DeepNose: Using artificial neural networks to represent the space of odorants
- Deep Residual Output Layers for Neural Language Generation
- Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning
- Demystifying Dropout
- Detecting Overlapping and Correlated Communities without Pure Nodes: Identifiability and Algorithm
- Diagnosing Bottlenecks in Deep Q-learning Algorithms
- Differentiable Dynamic Normalization for Learning Deep Representation
- Differentiable Linearized ADMM
- Differential Inclusions for Modeling Nonsmooth ADMM Variants: A Continuous Limit Theory
- Differentially Private Empirical Risk Minimization with Non-convex Loss Functions
- Differentially Private Fair Learning
- Differentially Private Learning of Geometric Concepts
- Dimensionality Reduction for Tukey Regression
- Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning
- Direct Uncertainty Prediction for Medical Second Opinions
- Dirichlet Simplex Nest and Geometric Inference
- Discovering Conditionally Salient Features with Statistical Guarantees
- Discovering Context Effects from Raw Choice Data
- Discovering Latent Covariance Structures for Multiple Time Series
- Discovering Options for Exploration by Minimizing Cover Time
- Discriminative Regularization for Latent Variable Models with Applications to Electrocardiography
- Disentangled Graph Convolutional Networks
- Disentangling Disentanglement in Variational Autoencoders
- Distributed, Egocentric Representations of Graphs for Detecting Critical Structures
- Distributed Learning over Unreliable Networks
- Distributed Learning with Sublinear Communication
- Distributed Weighted Matching via Randomized Composable Coresets
- Distributional Multivariate Policy Evaluation and Exploration with the Bellman GAN
- Distributional Reinforcement Learning for Efficient Exploration
- Distribution calibration for regression
- DL2: Training and Querying Neural Networks with Logic
- Does Data Augmentation Lead to Positive Margin?
- Do ImageNet Classifiers Generalize to ImageNet?
- Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment
- Domain Agnostic Learning with Disentangled Representations
- Doubly-Competitive Distribution Estimation
- Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random
- DP-GP-LVM: A Bayesian Non-Parametric Model for Learning Multivariate Dependency Structures
- Dropout as a Structured Shrinkage Prior
- Dual Entangled Polynomial Code: Three-Dimensional Coding for Distributed Matrix Multiplication
- Dynamic Learning with Frequent New Product Launches: A Sequential Multinomial Logit Bandit Problem
- Dynamic Measurement Scheduling for Event Forecasting using Deep RL
- Dynamic Weights in Multi-Objective Deep Reinforcement Learning
- EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE
- Efficient Amortised Bayesian Inference for Hierarchical and Nonlinear Dynamical Systems
- Efficient Dictionary Learning with Gradient Descent
- Efficient Full-Matrix Adaptive Regularization
- Efficient learning of smooth probability functions from Bernoulli tests with guarantees
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal Iterations
- Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
- Efficient On-Device Models using Neural Projections
- Efficient optimization of loops and limits with randomized telescoping sums
- Efficient Training of BERT by Progressively Stacking
- EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis
- ELF OpenGo: an analysis and open reimplementation of AlphaZero
- Emerging Convolutions for Generative Normalizing Flows
- EMI: Exploration with Mutual Information
- Empirical Analysis of Beam Search Performance Degradation in Neural Sequence Models
- End-to-End Probabilistic Inference for Nonstationary Audio Analysis
- Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs
- Equivariant Transformer Networks
- Error Feedback Fixes SignSGD and other Gradient Compression Schemes
- Escaping Saddle Points with Adaptive Gradient Methods
- Estimate Sequences for Variance-Reduced Stochastic Composite Optimization
- Estimating Information Flow in Deep Neural Networks
- Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation
- Exploiting structure of uncertainty for efficient matroid semi-bandits
- Exploiting Worker Correlation for Label Aggregation in Crowdsourcing
- Exploration Conscious Reinforcement Learning Revisited
- Exploration in Reinforcement Learning Workshop
- Exploring interpretable LSTM neural networks over multi-variable data
- Exploring the Landscape of Spatial Robustness
- Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations
- Fair k-Center Clustering for Data Summarization
- Fairness-Aware Learning for Continuous Attributes and Treatments
- Fairness risk measures
- Fairness without Harm: Decoupled Classifiers with Preference Guarantees
- Fair Regression: Quantitative Definitions and Reduction-Based Algorithms
- Fairwashing: the risk of rationalization
- Fast Algorithm for Generalized Multinomial Models with Ranking Data
- Fast and Flexible Inference of Joint Distributions from their Marginals
- Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations
- Fast and Stable Maximum Likelihood Estimation for Incomplete Multinomial Models
- Fast Context Adaptation via Meta-Learning
- Fast Direct Search in an Optimally Compressed Continuous Target Space for Efficient Multi-Label Active Learning
- Faster Algorithms for Binary Matrix Factorization
- Faster Attend-Infer-Repeat with Tractable Probabilistic Models
- Faster Stochastic Alternating Direction Method of Multipliers for Nonconvex Optimization
- Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications
- Fast Rates for a kNN Classifier Robust to Unknown Asymmetric Label Noise
- Fault Tolerance in Iterative-Convergent Machine Learning
- Feature-Critic Networks for Heterogeneous Domain Generalization
- Feature Grouping as a Stochastic Regularizer for High-Dimensional Structured Data
- Finding Mixed Nash Equilibria of Generative Adversarial Networks
- Finding Options that Minimize Planning Time
- Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks
- Fingerprint Policy Optimisation for Robust Reinforcement Learning
- Finite-Time Analysis of Distributed TD(0) with Linear Function Approximation on Multi-Agent Reinforcement Learning
- First-Order Adversarial Vulnerability of Neural Networks and Input Dimension
- First-Order Algorithms Converge Faster than $O(1/k)$ on Convex Problems
- Flat Metric Minimization with Applications in Generative Modeling
- Flexibly Fair Representation Learning by Disentanglement
- FloWaveNet : A Generative Flow for Raw Audio
- Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
- Formal Privacy for Functional Data with Gaussian Perturbations
- Functional Transparency for Structured Data: a Game-Theoretic Approach
- Gaining Free or Low-Cost Interpretability with Interpretable Partial Substitute
- Game Theoretic Optimization via Gradient-based Nikaido-Isoda Function
- Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits
- Gauge Equivariant Convolutional Networks and the Icosahedral CNN
- GDPP: Learning Diverse Generations using Determinantal Point Processes
- Generalized Approximate Survey Propagation for High-Dimensional Estimation
- Generalized Linear Rule Models
- Generalized Majorization-Minimization
- Generalized No Free Lunch Theorem for Adversarial Robustness
- Generative Adversarial User Model for Reinforcement Learning Based Recommendation System
- Generative Modeling and Model-Based Reasoning for Robotics and AI
- Generative Modeling of Infinite Occluded Objects for Compositional Scene Representation
- Geometric Losses for Distributional Learning
- Geometric Scattering for Graph Data Analysis
- GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
- Geometry and Symmetry in Short-and-Sparse Deconvolution
- Geometry Aware Convolutional Filters for Omnidirectional Images Representation
- Global Convergence of Block Coordinate Descent in Deep Learning
- GMNN: Graph Markov Neural Networks
- GOODE: A Gaussian Off-The-Shelf Ordinary Differential Equation Solver
- Good Initializations of Variational Bayes for Deep Models
- Gradient Descent Finds Global Minima of Deep Neural Networks
- Graph Convolutional Gaussian Processes
- Graph Element Networks: adaptive, structured computation and memory
- Graphical-model based estimation and inference for differential privacy
- Graphite: Iterative Generative Modeling of Graphs
- Graph Matching Networks for Learning the Similarity of Graph Structured Objects
- Graph Neural Network for Music Score Data and Modeling Expressive Piano Performance
- Graph Resistance and Learning from Pairwise Comparisons
- Graph U-Nets
- Greedy Layerwise Learning Can Scale To ImageNet
- Greedy Orthogonal Pivoting Algorithm for Non-Negative Matrix Factorization
- Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI
- Gromov-Wasserstein Learning for Graph Matching and Node Embedding
- Guarantees for Spectral Clustering with Fairness Constraints
- Guided evolutionary strategies: augmenting random search with surrogate gradients
- Hessian Aided Policy Gradient
- Heterogeneous Model Reuse via Optimizing Multiparty Multiclass Margin
- HexaGAN: Generative Adversarial Nets for Real World Classification
- Hierarchical Decompositional Mixtures of Variational Autoencoders
- Hierarchical Importance Weighted Autoencoders
- Hierarchically Structured Meta-learning
- High-Fidelity Image Generation With Fewer Labels
- Hiring Under Uncertainty
- HOList: An Environment for Machine Learning of Higher Order Logic Theorem Proving
- Homomorphic Sensing
- How does Disagreement Help Generalization against Label Corruption?
- Human In the Loop Learning (HILL)
- Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops
- Hybrid Models with Deep and Invertible Features
- Hyperbolic Disk Embeddings for Directed Acyclic Graphs
- HyperGAN: A Generative Model for Diverse, Performant Neural Networks
- ICML 2019 Time Series Workshop
- ICML 2019 Workshop on Computational Biology
- ICML Workshop on Imitation, Intent, and Interaction (I3)
- Identifying and Understanding Deep Learning Phenomena
- IMEXnet - A Forward Stable Deep Neural Network
- Imitating Latent Policies from Observation
- Imitation Learning from Imperfect Demonstration
- Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
- Importance Sampling Policy Evaluation with an Estimated Behavior Policy
- Improved Convergence for $\ell_1$ and $\ell_\infty$ Regression via Iteratively Reweighted Least Squares
- Improved Dynamic Graph Learning through Fault-Tolerant Sparsification
- Improved Parallel Algorithms for Density-Based Network Clustering
- Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization
- Improving Adversarial Robustness via Promoting Ensemble Diversity
- Improving Model Selection by Employing the Test Data
- Improving Neural Language Modeling via Adversarial Training
- Improving Neural Network Quantization without Retraining using Outlier Channel Splitting
- Imputing Missing Events in Continuous-Time Event Streams
- Incorporating Grouping Information into Bayesian Decision Tree Ensembles
- Incremental Randomized Sketching for Online Kernel Learning
- Inference and Sampling of $K_{33}$-free Ising Models
- Inferring Heterogeneous Causal Effects in Presence of Spatial Confounding
- Infinite Mixture Prototypes for Few-shot Learning
- Information-Theoretic Considerations in Batch Reinforcement Learning
- Insertion Transformer: Flexible Sequence Generation via Insertion Operations
- Interpreting Adversarially Trained Convolutional Neural Networks
- Invariant-Equivariant Representation Learning for Multi-Class Data
- Invertible Neural Networks and Normalizing Flows
- Invertible Residual Networks
- Iterative Linearized Control: Stable Algorithms and Complexity Guarantees
- Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks
- Joint Workshop on On-Device Machine Learning & Compact Deep Neural Network Representations (ODML-CDNNR)
- Jumpout : Improved Dropout for Deep Neural Networks with ReLUs
- Katalyst: Boosting Convex Katayusha for Non-Convex Problems with a Large Condition Number
- Kernel-Based Reinforcement Learning in Robust Markov Decision Processes
- Kernel Mean Matching for Content Addressability of GANs
- Kernel Normalized Cut: a Theoretical Revisit
- kernelPSI: a Post-Selection Inference Framework for Nonlinear Variable Selection
- Ladder Capsule Network
- Large-Scale Sparse Kernel Canonical Correlation Analysis
- LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
- Latent Normalizing Flows for Discrete Sequences
- Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling
- Learning Action Representations for Reinforcement Learning
- Learning and Data Selection in Big Datasets
- Learning and Reasoning with Graph-Structured Representations
- Learning a Prior over Intent via Meta-Inverse Reinforcement Learning
- Learning Classifiers for Target Domain with Limited or No Labels
- Learning Context-dependent Label Permutations for Multi-label Classification
- Learning deep kernels for exponential family densities
- Learning Dependency Structures for Weak Supervision Models
- Learning Discrete and Continuous Factors of Data via Alternating Disentanglement
- Learning Discrete Structures for Graph Neural Networks
- Learning Distance for Sequences by Learning a Ground Metric
- Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations
- Learning from a Learner
- Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems
- Learning Generative Models across Incomparable Spaces
- Learning Hawkes Processes Under Synchronization Noise
- Learning interpretable continuous-time models of latent stochastic dynamical systems
- Learning Latent Dynamics for Planning from Pixels
- Learning Linear-Quadratic Regulators Efficiently with only $\sqrt{T}$ Regret
- Learning Models from Data with Measurement Error: Tackling Underreporting
- Learning Neurosymbolic Generative Models via Program Synthesis
- Learning Novel Policies For Tasks
- Learning Optimal Fair Policies
- Learning Optimal Linear Regularizers
- Learning Structured Decision Problems with Unawareness
- Learning to bid in revenue-maximizing auctions
- Learning to Clear the Market
- Learning to Collaborate in Markov Decision Processes
- Learning to Convolve: A Generalized Weight-Tying Approach
- Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs
- Learning to Generalize from Sparse and Underspecified Rewards
- Learning to Groove with Inverse Sequence Transformations
- Learning to Infer Program Sketches
- Learning-to-Learn Stochastic Gradient Descent with Biased Regularization
- Learning to Optimize Multigrid PDE Solvers
- Learning to Prove Theorems via Interacting with Proof Assistants
- Learning to Route in Similarity Graphs
- Learning to select for a predefined ranking
- Learning What and Where to Transfer
- Learning with Bad Training Data via Iterative Trimmed Loss Minimization
- Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting
- LegoNet: Efficient Convolutional Neural Networks with Lego Filters
- Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction
- Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models
- LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning
- Linear-Complexity Data-Parallel Earth Mover's Distance Approximations
- Lipschitz Generative Adversarial Nets
- LIT: Learned Intermediate Representation Training for Model Compression
- Locally Private Bayesian Inference for Count Models
- Look Ma, No Latent Variables: Accurate Cutset Networks via Compilation
- Lorentzian Distance Learning for Hyperbolic Representations
- Loss Landscapes of Regularized Linear Autoencoders
- Lossless or Quantized Boosting with Integer Arithmetic
- Lower Bounds for Smooth Nonconvex Finite-Sum Optimization
- Low Latency Privacy Preserving Inference
- LR-GLM: High-Dimensional Bayesian Inference Using Low-Rank Data Approximations
- Machine Learning for Music Discovery
- Machine learning for robots to think fast
- Making Convolutional Networks Shift-Invariant Again
- Making Decisions that Reduce Discriminatory Impacts
- Making Deep Q-learning methods robust to time discretization
- Mallows ranking models: maximum likelihood estimate and regeneration
- Manifold Mixup: Better Representations by Interpolating Hidden States
- MASS: Masked Sequence to Sequence Pre-training for Language Generation
- Matrix-Free Preconditioning in Online Learning
- Maximum Entropy-Regularized Multi-Goal Reinforcement Learning
- Maximum Likelihood Estimation for Learning Populations of Parameters
- MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians
- Memory-Optimal Direct Convolutions for Maximizing Classification Accuracy in Embedded Applications
- ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation
- Meta-Learning: from Few-Shot Learning to Rapid Reinforcement Learning
- Meta-Learning Neural Bloom Filters
- MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement
- Metric-Optimized Example Weights
- Metropolis-Hastings Generative Adversarial Networks
- Minimal Achievable Sufficient Statistic Learning
- MIWAE: Deep Generative Modelling and Imputation of Incomplete Data Sets
- MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
- Mixture Models for Diverse Machine Translation: Tricks of the Trade
- Model-Based Active Exploration
- Model Comparison for Semantic Grouping
- Model Function Based Conditional Gradient Method with Armijo-like Line Search
- Molecular Hypergraph Grammar with Its Application to Molecular Optimization
- Moment-Based Variational Inference for Markov Jump Processes
- Monge blunts Bayes: Hardness Results for Adversarial Training
- MONK -- Outlier-Robust Mean Embedding Estimation by Median-of-Means
- More Efficient Off-Policy Evaluation through Regularized Targeted Learning
- Multi-Agent Adversarial Inverse Reinforcement Learning
- Multi-Frequency Phase Synchronization
- Multi-Frequency Vector Diffusion Maps
- Multi-objective training of Generative Adversarial Networks with multiple discriminators
- Multi-Object Representation Learning with Iterative Variational Inference
- Multiplicative Weights Updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost always
- Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching
- Multivariate Submodular Optimization
- Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments
- NAS-Bench-101: Towards Reproducible Neural Architecture Search
- NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks
- Natural Analysts in Adaptive Data Analysis
- Nearest Neighbor and Kernel Survival Analysis: Nonasymptotic Error Bounds and Strong Consistency Rates
- Near optimal finite time identification of arbitrary linear dynamical systems
- Negative Dependence: Theory and Applications in Machine Learning
- Neural Approaches to Conversational AI
- Neural Collaborative Subspace Clustering
- Neural Inverse Knitting: From Images to Manufacturing Instructions
- Neural Joint Source-Channel Coding
- Neural Logic Reinforcement Learning
- Neurally-Guided Structure Inference
- Neural Network Attributions: A Causal Perspective
- Neural Separation of Observed and Unobserved Distributions
- Neuron birth-death dynamics accelerates gradient descent and converges asymptotically
- Never-Ending Learning
- New results on information theoretic clustering
- Noise2Self: Blind Denoising by Self-Supervision
- Noisy Dual Principal Component Pursuit
- Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization
- Nonconvex Variance Reduced Optimization with Arbitrary Sampling
- Nonlinear Distributional Gradient Temporal-Difference Learning
- Nonlinear Stein Variational Gradient Descent for Learning Diversified Mixture Models
- Non-monotone Submodular Maximization with Nearly Optimal Adaptivity and Query Complexity
- Non-Monotonic Sequential Text Generation
- Nonparametric Bayesian Deep Networks with Local Competition
- Non-Parametric Priors For Generative Adversarial Networks
- Obtaining Fairness using Optimal Transport Theory
- Off-Policy Deep Reinforcement Learning without Exploration
- On Certifying Non-Uniform Bounds against Adversarial Attacks
- On Connected Sublevel Sets in Deep Learning
- On discriminative learning of prediction uncertainty
- On Dropout and Nuclear Norm Regularization
- On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithms
- On Learning Invariant Representations for Domain Adaptation
- Online Adaptive Principal Component Analysis and Its extensions
- Online Algorithms for Rent-Or-Buy with Expert Advice
- Online Control with Adversarial Disturbances
- Online Convex Optimization in Adversarial Markov Decision Processes
- Online Dictionary Learning for Sparse Coding
- Online Learning to Rank with Features
- Online learning with kernel losses
- Online Learning with Sleeping Experts and Feedback Graphs
- Online Meta-Learning
- Online Variance Reduction with Mixtures
- On Medians of (Randomized) Pairwise Means
- On Scalable and Efficient Computation of Large Scale Optimal Transport
- On Sparse Linear Regression in the Local Differential Privacy Model
- On Symmetric Losses for Learning from Corrupted Labels
- On the Complexity of Approximating Wasserstein Barycenters
- On the Computation and Communication Complexity of Parallel SGD with Dynamic Batch Sizes for Stochastic Non-Convex Optimization
- On the Connection Between Adversarial Robustness and Saliency Map Interpretability
- On the Convergence and Robustness of Adversarial Training
- On the Design of Estimators for Bandit Off-Policy Evaluation
- On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference
- On the Generalization Gap in Reparameterizable Reinforcement Learning
- On the Impact of the Activation function on Deep Neural Networks Training
- On the Limitations of Representing Functions on Sets
- On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization
- On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learning
- On The Power of Curriculum Learning in Training Deep Networks
- On the Spectral Bias of Neural Networks
- On the statistical rate of nonlinear recovery in generative models with heavy-tailed data
- On the Universality of Invariant Networks
- On Variational Bounds of Mutual Information
- Open-ended learning in symmetric zero-sum games
- Open Vocabulary Learning on Source Code with a Graph-Structured Cache
- Optimal Algorithms for Lipschitz Bandits with Heavy-tailed Rewards
- Optimal Auctions through Deep Learning
- Optimal Continuous DR-Submodular Maximization and Applications to Provable Mean Field Inference
- Optimality Implies Kernel Sum Classifiers are Statistically Efficient
- Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning
- Optimal Mini-Batch and Step Sizes for SAGA
- Optimal Minimal Margin Maximization with Boosting
- Optimal Transport for structured data with application on graphs
- Optimistic Policy Optimization via Multiple Importance Sampling
- Orthogonal Random Forest for Causal Inference
- Overcoming Mean-Field Approximations in Recurrent Gaussian Process Models
- Overcoming Multi-model Forgetting
- Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?
- PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits
- PAC Learnability of Node Functions in Networked Dynamical Systems
- PA-GD: On the Convergence of Perturbed Alternating Gradient Descent to Second-Order Stationary Points for Structured Nonconvex Optimization
- Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization
- Parameter-Efficient Transfer Learning for NLP
- Pareto Optimal Streaming Unsupervised Classification
- Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization
- Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computation
- Partially Linear Additive Gaussian Graphical Models
- Particle Flow Bayes' Rule
- Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models
- Per-Decision Option Discounting
- Phaseless PCA: Low-Rank Matrix Recovery from Column-wise Phaseless Measurements
- Phase transition in PCA with missing data: Reduced signal-to-noise ratio, not sample size!
- Plug-and-Play Methods Provably Converge with Properly Trained Denoisers
- Poission Subsampled R\'enyi Differential Privacy
- Policy Certificates: Towards Accountable Reinforcement Learning
- Policy Consolidation for Continual Reinforcement Learning
- POLITEX: Regret Bounds for Policy Iteration using Expert Prediction
- POPQORN: Quantifying Robustness of Recurrent Neural Networks
- Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
- Position-aware Graph Neural Networks
- Power k-Means Clustering
- Predicate Exchange: Inference with Declarative Knowledge
- Predictor-Corrector Policy Optimization
- Probabilistic Neural Symbolic Models for Interpretable Visual Question Answering
- Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning
- Processing Megapixel Images with Deep Attention-Sampling Models
- Projection onto Minkowski Sums with Application to Constrained Learning
- Projections for Approximate Policy Iteration Algorithms
- Proportionally Fair Clustering
- Provable Guarantees for Gradient-Based Meta-Learning
- Provably Efficient Imitation Learning from Observation Alone
- Provably Efficient Maximum Entropy Exploration
- Provably efficient RL with Rich Observations via Latent State Decoding
- PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach
- QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning
- Quantifying Generalization in Reinforcement Learning
- Quantile Stein Variational Gradient Descent for Batch Bayesian Optimization
- Rademacher Complexity for Adversarially Robust Generalization
- RaFM: Rank-Aware Factorization Machines
- Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation
- Random Function Priors for Correlation Modeling
- Random Matrix Improved Covariance Estimation for a Large Class of Metrics
- Random Shuffling Beats SGD after Finite Epochs
- Random Walks on Hypergraphs with Edge-Dependent Vertex Weights
- Rao-Blackwellized Stochastic Gradients for Discrete Distributions
- Rate Distortion For Model Compression:From Theory To Practice
- Rates of Convergence for Sparse Variational Gaussian Process Regression
- Real-world Sequential Decision Making: Reinforcement Learning and Beyond
- Recent Advances in Population-Based Search for Deep Neural Networks: Quality Diversity, Indirect Encodings, and Open-Ended Algorithms
- Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces
- Recursive Sketches for Modular Deep Learning
- Refined Complexity of PCA with Outliers
- Regret Circuits: Composability of Regret Minimizers
- Regularization in directable environments with application to Tetris
- Rehashing Kernel Evaluation in High Dimensions
- Reinforcement Learning for Real Life
- Reinforcement Learning in Configurable Continuous Environments
- Relational Pooling for Graph Representations
- Remember and Forget for Experience Replay
- Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions
- Replica Conditional Sequential Monte Carlo
- Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff
- Revisiting precision recall definition for generative modeling
- Revisiting the Softmax Bellman Operator: New Benefits and New Perspective
- Riemannian adaptive stochastic gradient algorithms on matrix manifolds
- Robust Decision Trees Against Adversarial Examples
- Robust Estimation of Tree Structured Gaussian Graphical Models
- Robust Inference via Generative Classifiers for Handling Noisy Labels
- Robust Influence Maximization for Hyperparametric Models
- Robust Learning from Untrusted Sources
- Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness
- Rotation Invariant Householder Parameterization for Bayesian PCA
- Safe Grid Search with Optimal Complexity
- Safe Machine Learning
- Safe Policy Improvement with Baseline Bootstrapping
- SAGA with Arbitrary Sampling
- Same, Same But Different: Recovering Neural Network Quantization Error Through Weight Factorization
- Sample-Optimal Parametric Q-Learning Using Linearly Additive Features
- SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver
- Scalable Fair Clustering
- Scalable Learning in Reproducing Kernel Krein Spaces
- Scalable Metropolis-Hastings for Exact Bayesian Inference with Large Datasets
- Scalable Nonparametric Sampling from Multimodal Posteriors with the Posterior Bootstrap
- Scalable Training of Inference Networks for Gaussian-Process Models
- Scale-free adaptive planning for deterministic dynamics & discounted rewards
- Scaling Up Ordinal Embedding: A Landmark Approach
- Screening rules for Lasso with non-convex Sparse Regularizers
- SelectiveNet: A Deep Neural Network with an Integrated Reject Option
- Self-Attention Generative Adversarial Networks
- Self-Attention Graph Pooling
- SELFIE: Refurbishing Unclean Samples for Robust Deep Learning
- Self-similar Epochs: Value in arrangement
- Self-Supervised Exploration via Disagreement
- Semi-Cyclic Stochastic Gradient Descent
- Sensitivity Analysis of Linear Structural Causal Models
- Separable value functions across time-scales
- Sequential Facility Location: Approximate Submodularity and Greedy Algorithm
- Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
- Sever: A Robust Meta-Algorithm for Stochastic Optimization
- SGD: General Analysis and Improved Rates
- SGD without Replacement: Sharper Rates for General Smooth Convex Functions
- Shallow-Deep Networks: Understanding and Mitigating Network Overthinking
- Shape Constraints for Set Functions
- Similarity of Neural Network Representations Revisited
- Simple Black-box Adversarial Attacks
- Simple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization
- Simplifying Graph Convolutional Networks
- Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions
- Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
- SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning
- Sorting Out Lipschitz Function Approximation
- Sparse Extreme Multi-label Learning with Oracle Property
- Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data
- Spectral Approximate Inference
- Spectral Clustering of Signed Graphs via Matrix Power Means
- Stable and Fair Classification
- Stable-Predictive Optimistic Counterfactual Regret Minimization
- State-Regularized Recurrent Neural Networks
- State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
- Static Automatic Batching In TensorFlow
- Statistical Foundations of Virtual Democracy
- Statistics and Samples in Distributional Reinforcement Learning
- Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With Reneging
- Stein Point Markov Chain Monte Carlo
- Stein’s Method for Machine Learning and Statistics
- Stochastic Beams and Where To Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement
- Stochastic Blockmodels meet Graph Neural Networks
- Stochastic Deep Networks
- Stochastic Gradient Push for Distributed Deep Learning
- Stochastic Iterative Hard Thresholding for Graph-structured Sparsity Optimization
- Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence
- Structured agents for physical construction
- Sublinear quantum algorithms for training linear and kernel-based classifiers
- Sublinear Space Private Algorithms Under the Sliding Window Model
- Sublinear Time Nearest Neighbor Search over Generalized Weighted Space
- Submodular Cost Submodular Cover with an Approximate Oracle
- Submodular Maximization beyond Non-negativity: Guarantees, Fast Algorithms, and Applications
- Submodular Observation Selection and Information Gathering for Quadratic Models
- Submodular Streaming in All Its Glory: Tight Approximation, Minimum Memory and Low Adaptive Complexity
- Subspace Robust Wasserstein Distances
- Sum-of-Squares Polynomial Flow
- Supervised Hierarchical Clustering with Exponential Linkage
- Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization
- SWALP : Stochastic Weight Averaging in Low Precision Training
- Switching Linear Dynamics for Variational Bayes Filtering
- Synthetic Realities: Deep Learning for Detecting AudioVisual Fakes
- Taming MAML: Efficient unbiased meta-reinforcement learning
- TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning
- Target-Based Temporal-Difference Learning
- Target Tracking for Contextual Bandits: Application to Demand Side Management
- TarMAC: Targeted Multi-Agent Communication
- Task-Agnostic Dynamics Priors for Deep Reinforcement Learning
- Teaching a black-box learner
- Temporal Gaussian Mixture Layer for Videos
- TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing
- Tensor Variable Elimination for Plated Factor Graphs
- Test of Time Award
- The advantages of multiple classes for reducing overfitting from test set reuse
- The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects
- The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study
- The Evolved Transformer
- The How2 Challenge: New Tasks for Vision & Language
- The Implicit Fairness Criterion of Unconstrained Learning
- The information-theoretic value of unlabeled data in semi-supervised learning
- The Kernel Interaction Trick: Fast Bayesian Discovery of Pairwise Interactions in High Dimensions
- The Natural Language of Actions
- The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
- Theoretically Principled Trade-off between Robustness and Accuracy
- Theoretical Physics for Deep Learning
- The Third Workshop On Tractable Probabilistic Modeling (TPM)
- The U.S. Census Bureau Tries to be a Good Data Steward in the 21st Century
- The Value Function Polytope in Reinforcement Learning
- The Variational Predictive Natural Gradient
- The Wasserstein Transform
- TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning
- Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds
- Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel $k$-means Clustering
- Topological Data Analysis of Decision Boundaries with Application to Model Selection
- Toward Controlling Discrimination in Online Ad Auctions
- Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation
- Towards a Deep and Unified Understanding of Deep Neural Models in NLP
- Towards a Unified Analysis of Random Fourier Features
- Towards Understanding Knowledge Distillation
- Toward Understanding the Importance of Noise in Training Neural Networks
- Trading Redundancy for Communication: Speeding up Distributed SGD for Non-convex Optimization
- Traditional and Heavy Tailed Self Regularization in Neural Network Models
- Trainable Decoding of Sets of Sequences for Neural Sequence Models
- Training CNNs with Selective Allocation of Channels
- Training Neural Networks with Local Error Signals
- Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints
- Trajectory-Based Off-Policy Deep Reinforcement Learning
- Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation
- Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers
- Transferable Clean-Label Poisoning Attacks on Deep Neural Nets
- Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation
- Transfer of Samples in Policy Search via Multiple Importance Sampling
- Trimming the $\ell_1$ Regularizer: Statistical Analysis, Optimization, and Applications to Deep Learning
- Uncertainty and Robustness in Deep Learning
- Understanding and Accelerating Particle-Based Variational Inference
- Understanding and Controlling Memory in Recurrent Neural Networks
- Understanding and correcting pathologies in the training of learned optimizers
- Understanding and Improving Generalization in Deep Learning
- Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
- Understanding Geometry of Encoder-Decoder CNNs
- Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation
- Understanding MCMC Dynamics as Flows on the Wasserstein Space
- Understanding Priors in Bayesian Neural Networks at the Unit Level
- Understanding the Impact of Entropy on Policy Optimization
- Understanding the Origins of Bias in Word Embeddings
- Uniform Convergence Rate of the Kernel Density Estimator Adaptive to Intrinsic Volume Dimension
- Unifying Orthogonal Monte Carlo Methods
- Unreproducible Research is Reproducible
- Unsupervised Deep Learning by Neighbourhood Discovery
- Unsupervised Label Noise Modeling and Loss Correction
- Using Pre-Training Can Improve Model Robustness and Uncertainty
- Validating Causal Inference Models via Influence Functions
- Variational Annealing of GANs: A Langevin Perspective
- Variational Implicit Processes
- Variational Inference for sparse network reconstruction from count data
- Variational Laplace Autoencoders
- Variational Russian Roulette for Deep Bayesian Nonparametrics
- Voronoi Boundary Classification: A High-Dimensional Geometric Approach via Weighted Monte Carlo Integration
- Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback
- Wasserstein Adversarial Examples via Projected Sinkhorn Iterations
- Wasserstein of Wasserstein Loss for Learning Generative Models
- Weak Detection of Signal in the Spiked Wigner Model
- Weakly-Supervised Temporal Localization via Occurrence Count Learning
- What 4 year olds can do and AI can’t (yet)
- What is the Effect of Importance Weighting in Deep Learning?
- When Samples Are Strategically Selected
- White-box vs Black-box: Bayes Optimal Strategies for Membership Inference
- Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem
- Width Provably Matters in Optimization for Deep Linear Neural Networks
- Workshop on AI for autonomous driving
- Workshop on Multi-Task and Lifelong Reinforcement Learning
- Workshop on Self-Supervised Learning
- Workshop on the Security and Privacy of Machine Learning
- Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerance
- Zero-Shot Knowledge Distillation in Deep Networks