icml 2019 论文列表
Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA.
|
Natural Analysts in Adaptive Data Analysis.
Fast Context Adaptation via Meta-Learning.
Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously.
Latent Normalizing Flows for Discrete Sequences.
Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization.
The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects.
Learning Classifiers for Target Domain with Limited or No Labels.
Poission Subsampled Rényi Differential Privacy.
Improved Dynamic Graph Learning through Fault-Tolerant Sparsification.
Transferable Clean-Label Poisoning Attacks on Deep Neural Nets.
BayesNAS: A Bayesian Approach for Neural Architecture Search.
Toward Understanding the Importance of Noise in Training Neural Networks.
Lipschitz Generative Adversarial Nets.
Lower Bounds for Smooth Nonconvex Finite-Sum Optimization.
Stochastic Iterative Hard Thresholding for Graph-structured Sparsity Optimization.
Maximum Entropy-Regularized Multi-Goal Reinforcement Learning.
Improving Neural Network Quantization without Retraining using Outlier Channel Splitting.
Metric-Optimized Example Weights.
On Learning Invariant Representations for Domain Adaptation.
Adaptive Monte Carlo Multiple Testing via Multi-Armed Bandits.
Interpreting Adversarially Trained Convolutional Neural Networks.
Greedy Orthogonal Pivoting Algorithm for Non-Negative Matrix Factorization.
Learning Novel Policies For Tasks.
Theoretically Principled Trade-off between Robustness and Accuracy.
Fast and Stable Maximum Likelihood Estimation for Incomplete Multinomial Models.
A Composite Randomized Incremental Gradient Method.
SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning.
Co-Representation Network for Generalized Zero-Shot Learning.
Random Function Priors for Correlation Modeling.
Adaptive Regret of Convex and Smooth Functions.
Bridging Theory and Algorithm for Domain Adaptation.
Incremental Randomized Sketching for Online Kernel Learning.
Neural Collaborative Subspace Clustering.
LatentGNN: Learning Efficient Non-local Relations for Visual Recognition.
Circuit-GNN: Graph Neural Networks for Distributed Circuit Design.
Self-Attention Generative Adversarial Networks.
When Samples Are Strategically Selected.
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback.
Making Convolutional Networks Shift-Invariant Again.
Global Convergence of Block Coordinate Descent in Deep Learning.
Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds.
Context-Aware Zero-Shot Learning for Object Recognition.
Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator.
A Conditional-Gradient-Based Augmented Lagrangian Framework.
Dirichlet Simplex Nest and Geometric Inference.
Bayesian Nonparametric Federated Learning of Neural Networks.
Trimming the $\ell_1$ Regularizer: Statistical Analysis, Optimization, and Applications to Deep Learning.
Differential Inclusions for Modeling Nonsmooth ADMM Variants: A Continuous Limit Theory.
Generative Modeling of Infinite Occluded Objects for Compositional Scene Representation.
Online Adaptive Principal Component Analysis and Its extensions.
Distributed Learning over Unreliable Networks.
Multi-Agent Adversarial Inverse Reinforcement Learning.
On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization.
On the Computation and Communication Complexity of Parallel SGD with Dynamic Batch Sizes for Stochastic Non-Convex Optimization.
How does Disagreement Help Generalization against Label Corruption?
DAG-GNN: DAG Structure Learning with Graph Neural Networks.
Learning Neurosymbolic Generative Models via Program Synthesis.
Position-aware Graph Neural Networks.
Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation.
TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning.
NAS-Bench-101: Towards Reproducible Neural Architecture Search.
ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables.
Rademacher Complexity for Adversarially Robust Generalization.
Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning.
Understanding Geometry of Encoder-Decoder CNNs.
Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel $k$-means Clustering.
Hierarchically Structured Meta-learning.
Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal Iterations.
ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation.
SWALP : Stochastic Weight Averaging in Low Precision Training.
LegoNet: Efficient Convolutional Neural Networks with Lego Filters.
Sample-Optimal Parametric Q-Learning Using Linearly Additive Features.
Learning to Prove Theorems via Interacting with Proof Assistants.
Supervised Hierarchical Clustering with Exponential Linkage.
Variational Russian Roulette for Deep Bayesian Nonparametrics.
Learning a Prior over Intent via Meta-Inverse Reinforcement Learning.
Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence.
Gromov-Wasserstein Learning for Graph Matching and Node Embedding.
Power k-Means Clustering.
Calibrated Approximate Bayesian Inference.
Differentiable Linearized ADMM.
Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerance.
On Scalable and Efficient Computation of Large Scale Optimal Transport.
Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment.
Simplifying Graph Convolutional Networks.
Deep Compressed Sensing.
Heterogeneous Model Reuse via Optimizing Multiparty Multiclass Margin.
Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling.
Imitation Learning from Imperfect Demonstration.
Wasserstein Adversarial Examples via Projected Sinkhorn Iterations.
Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computation.
Fairness risk measures.
End-to-End Probabilistic Inference for Nonstationary Audio Analysis.
Moment-Based Variational Inference for Markov Jump Processes.
Automatic Classifiers as Scientific Instruments: One Step Further Away from Ground-Truth.
Improving Model Selection by Employing the Test Data.
Learning deep kernels for exponential family densities.
PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach.
Non-Monotonic Sequential Text Generation.
CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration.
On the statistical rate of nonlinear recovery in generative models with heavy-tailed data.
Generalized Linear Rule Models.
AdaGrad stepsizes: sharp convergence over nonconvex landscapes.
Jumpout : Improved Dropout for Deep Neural Networks with ReLUs.
Bias Also Matters: Bias Attribution for Deep Neural Network Explanation.
On the Generalization Gap in Reparameterizable Reinforcement Learning.
Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random.
On Sparse Linear Regression in the Local Differential Privacy Model.
Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions.
Deep Factors for Forecasting.
State-Regularized Recurrent Neural Networks.
On the Convergence and Robustness of Adversarial Training.
Nonlinear Stein Variational Gradient Descent for Learning Diversified Mixture Models.
EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis.
Improving Neural Language Modeling via Adversarial Training.
SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver.
Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation.
Differentially Private Empirical Risk Minimization with Non-convex Loss Functions.
Convolutional Poisson Gamma Belief Network.
Gaining Free or Low-Cost Interpretability with Interpretable Partial Substitute.
Graph Convolutional Gaussian Processes.
On the Limitations of Representing Functions on Sets.
Learning to select for a predefined ranking.
On the Design of Estimators for Bandit Off-Policy Evaluation.
Understanding Priors in Bayesian Neural Networks at the Unit Level.
Maximum Likelihood Estimation for Learning Populations of Parameters.
Manifold Mixup: Better Representations by Interpolating Hidden States.
Probabilistic Neural Symbolic Models for Interpretable Visual Question Answering.
Learning Dependency Structures for Weak Supervision Models.
Model Comparison for Semantic Grouping.
Composing Value Functions in Reinforcement Learning.
Characterization of Convex Objective Functions and Optimal Expected Convergence Rates for SGD.
Large-Scale Sparse Kernel Canonical Correlation Analysis.
Fairness without Harm: Decoupled Classifiers with Preference Guarantees.
Sublinear Space Private Algorithms Under the Sliding Window Model.
Distributed, Egocentric Representations of Graphs for Detecting Critical Structures.
Metropolis-Hastings Generative Adversarial Networks.
Homomorphic Sensing.
Learning Hawkes Processes Under Synchronization Noise.
LR-GLM: High-Dimensional Bayesian Inference Using Low-Rank Data Approximations.
DeepNose: Using artificial neural networks to represent the space of odorants.
Bayesian Generative Active Deep Learning.
Discovering Latent Covariance Structures for Multiple Time Series.
Optimal Transport for structured data with application on graphs.
Transfer of Samples in Policy Search via Multiple Importance Sampling.
Random Matrix Improved Covariance Estimation for a Large Class of Metrics.
ELF OpenGo: an analysis and open reimplementation of AlphaZero.
Combating Label Noise in Deep Learning using Abstention.
Concentration Inequalities for Conditional Value at Risk.
Action Robust Reinforcement Learning and Applications in Continuous Control.
Kernel Normalized Cut: a Theoretical Revisit.
The Natural Language of Actions.
Predicate Exchange: Inference with Declarative Knowledge.
Variational Annealing of GANs: A Langevin Perspective.
Adaptive Neural Trees.
DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-pass Error-Compensated Compression.
The Variational Predictive Natural Gradient.
Correlated Variational Auto-Encoders.
Mallows ranking models: maximum likelihood estimate and regeneration.
Hierarchical Decompositional Mixtures of Variational Autoencoders.
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks.
Making Deep Q-learning methods robust to time discretization.
Equivariant Transformer Networks.
Accelerated Flow for Probability Distributions.
Hyperbolic Disk Embeddings for Directed Acyclic Graphs.
Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness.
Active Learning for Decision-Making from Imbalanced Observational Data.
Provably Efficient Imitation Learning from Observation Alone.
Contextual Memory Trees.
Learning Distance for Sequences by Learning a Ground Metric.
CAB: Continuous Adaptive Blending for Policy Evaluation and Learning.
Learning Optimal Linear Regularizers.
BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning.
Insertion Transformer: Flexible Sequence Generation via Insertion Operations.
Faster Attend-Infer-Repeat with Tractable Probabilistic Models.
Escaping Saddle Points with Adaptive Gradient Methods.
Compressing Gradient Optimizers via Count-Sketches.
Dual Entangled Polynomial Code: Three-Dimensional Coding for Distributed Matrix Multiplication.
MASS: Masked Sequence to Sequence Pre-training for Language Generation.
Revisiting the Softmax Bellman Operator: New Benefits and New Perspective.
SELFIE: Refurbishing Unclean Samples for Robust Deep Learning.
Distribution calibration for regression.
QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning.
The Evolved Transformer.
GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects.
kernelPSI: a Post-Selection Inference Framework for Nonlinear Variable Selection.
Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation.
Non-Parametric Priors For Generative Adversarial Networks.
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks.
Refined Complexity of PCA with Outliers.
First-Order Adversarial Vulnerability of Neural Networks and Input Dimension.
Revisiting precision recall definition for generative modeling.
Rehashing Kernel Evaluation in High Dimensions.
Model-Based Active Exploration.
Fast Direct Search in an Optimally Compressed Continuous Target Space for Efficient Multi-Label Active Learning.
Scalable Training of Inference Networks for Gaussian-Process Models.
Replica Conditional Sequential Monte Carlo.
Learning with Bad Training Data via Iterative Trimmed Loss Minimization.
Hessian Aided Policy Gradient.
Mixture Models for Diverse Machine Translation: Tricks of the Trade.
Learning to Clear the Market.
Conditional Independence in Testing Bayesian Networks.
Compressed Factorization: Fast and Accurate Low-Rank Factorization of Compressively-Sensed Data.
Exploration Conscious Reinforcement Learning Revisited.
On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference.
Discovering Context Effects from Raw Choice Data.
Weakly-Supervised Temporal Localization via Occurrence Count Learning.
Locally Private Bayesian Inference for Count Models.
A Theoretical Analysis of Contrastive Unsupervised Representation Learning.
Breaking Inter-Layer Co-Adaptation by Classifier Anonymization.
Near optimal finite time identification of arbitrary linear dynamical systems.
Multivariate Submodular Optimization.
Deep Gaussian Processes with Importance-Weighted Variational Inference.
An Optimal Private Stochastic-MAB Algorithm based on Optimal Private Stopping Rule.
Tractable n-Metrics for Multiple Graphs.
White-box vs Black-box: Bayes Optimal Strategies for Membership Inference.
Plug-and-Play Methods Provably Converge with Properly Trained Denoisers.
A Contrastive Divergence for Combining Variational Inference and MCMC.
Statistics and Samples in Distributional Reinforcement Learning.
Iterative Linearized Control: Stable Algorithms and Complexity Guarantees.
Neuron birth-death dynamics accelerates gradient descent and converges asymptotically.
The Odds are Odd: A Statistical Test for Detecting Adversarial Examples.
Good Initializations of Variational Bayes for Deep Models.
Online Convex Optimization in Adversarial Markov Decision Processes.
Separable value functions across time-scales.
Efficient learning of smooth probability functions from Bernoulli tests with guarantees.
A Persistent Weisfeiler-Lehman Procedure for Graph Classification.
A Polynomial Time MCMC Method for Sampling from Continuous Determinantal Point Processes.
Adversarial Online Learning with noise.
Adaptive Antithetic Sampling for Variance Reduction.
Almost Unsupervised Text to Speech and Automatic Speech Recognition.
Fast Rates for a kNN Classifier Robust to Unknown Asymmetric Label Noise.
Do ImageNet Classifiers Generalize to ImageNet?
A Block Coordinate Descent Proximal Method for Simultaneous Filtering and Parameter Estimation.
Efficient On-Device Models using Neural Projections.
HyperGAN: A Generative Model for Diverse, Performant Neural Networks.
Topological Data Analysis of Decision Boundaries with Application to Model Selection.
Screening rules for Lasso with non-convex Sparse Regularizers.
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables.
Does Data Augmentation Lead to Positive Margin?
Look Ma, No Latent Variables: Accurate Cutset Networks via Compilation.
On the Spectral Bias of Neural Networks.
Game Theoretic Optimization via Gradient-based Nikaido-Isoda Function.
Direct Uncertainty Prediction for Medical Second Opinions.
Meta-Learning Neural Bloom Filters.
Learning to Collaborate in Markov Decision Processes.
Nonlinear Distributional Gradient Temporal-Difference Learning.
GMNN: Graph Markov Neural Networks.
Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition.
Fault Tolerance in Iterative-Convergent Machine Learning.
AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss.
SGD with Arbitrary Sampling: General Analysis and Improved Rates.
SAGA with Arbitrary Sampling.
Hiring Under Uncertainty.
On Variational Bounds of Mutual Information.
Voronoi Boundary Classification: A High-Dimensional Geometric Approach via Weighted Monte Carlo Integration.
Temporal Gaussian Mixture Layer for Videos.
Towards Understanding Knowledge Distillation.
Cognitive model priors for predicting human decisions.
Exploiting structure of uncertainty for efficient matroid semi-bandits.
Collaborative Channel Pruning for Deep Networks.
Domain Agnostic Learning with Disentangled Representations.
COMIC: Multi-view Clustering Without Parameter Selection.
Fingerprint Policy Optimisation for Robust Reinforcement Learning.
Subspace Robust Wasserstein Distances.
Self-Supervised Exploration via Disagreement.
Spectral Approximate Inference.
The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study.
Variational Laplace Autoencoders.
Generalized Majorization-Minimization.
Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians.
Deep Residual Output Layers for Neural Language Generation.
Optimistic Policy Optimization via Multiple Importance Sampling.
Nonparametric Bayesian Deep Networks with Local Competition.
Improving Adversarial Robustness via Promoting Ensemble Diversity.
Multiplicative Weights Updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost always.
Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?
Inferring Heterogeneous Causal Effects in Presence of Spatial Confounding.
Orthogonal Random Forest for Causal Inference.
Approximation and non-parametric estimation of ResNet-type convolutional neural networks.
Scalable Learning in Reproducing Kernel Krein Spaces.
TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing.
Model Function Based Conditional Gradient Method with Armijo-like Line Search.
Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models.
Tensor Variable Elimination for Plated Factor Graphs.
Learning to Infer Program Sketches.
Remember and Forget for Experience Replay.
Training Neural Networks with Local Error Signals.
Lossless or Quantized Boosting with Integer Arithmetic.
Rotation Invariant Householder Parameterization for Bayesian PCA.
Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization.
Anomaly Detection With Multiple-Hypotheses Predictions.
On Connected Sublevel Sets in Deep Learning.
Learning to bid in revenue-maximizing auctions.
Safe Grid Search with Optimal Complexity.
Phaseless PCA: Low-Rank Matrix Recovery from Column-wise Phaseless Measurements.
A Framework for Bayesian Optimization in Embedded Subspaces.
Zero-Shot Knowledge Distillation in Deep Networks.
Learning Context-dependent Label Permutations for Multi-label Classification.
Hybrid Models with Deep and Invertible Features.
Dropout as a Structured Shrinkage Prior.
SGD without Replacement: Sharper Rates for General Smooth Convex Functions.
A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning.
Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models.
Learning Optimal Fair Policies.
Relational Pooling for Graph Representations.
A Dynamical Systems Perspective on Nesterov Acceleration.
Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization.
Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization.
Flat Metric Minimization with Applications in Generative Modeling.
Agnostic Federated Learning.
Co-manifold learning with missing data.
Formal Privacy for Functional Data with Gaussian Perturbations.
Discriminative Regularization for Latent Variable Models with Applications to Electrocardiography.
On Dropout and Nuclear Norm Regularization.
Optimality Implies Kernel Sum Classifiers are Statistically Efficient.
Understanding and correcting pathologies in the training of learned optimizers.
Reinforcement Learning in Configurable Continuous Environments.
Simple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization.
Spectral Clustering of Signed Graphs via Matrix Power Means.
Geometric Losses for Distributional Learning.
Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks.
The Wasserstein Transform.
Same, Same But Different: Recovering Neural Network Quantization Error Through Weight Factorization.
Imputing Missing Events in Continuous-Time Event Streams.
Stochastic Blockmodels meet Graph Neural Networks.
Toward Controlling Discrimination in Online Ad Auctions.
Efficient Amortised Bayesian Inference for Hierarchical and Nonlinear Dynamical Systems.
Graphical-model based estimation and inference for differential privacy.
Distributional Reinforcement Learning for Efficient Exploration.
MIWAE: Deep Generative Modelling and Imputation of Incomplete Data Sets.
Disentangling Disentanglement in Variational Autoencoders.
Optimal Minimal Margin Maximization with Boosting.
Fairness-Aware Learning for Continuous Attributes and Treatments.
Decomposing feature-level variation with Covariate Gaussian Process Latent Variable Models.
On the Universality of Invariant Networks.
Adversarial Generation of Time-Frequency Features with application in audio synthesis.
A Baseline for Any Order Gradient Estimation in Stochastic Computation Graphs.
Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models.
Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems.
Calibrated Model-Based Deep Reinforcement Learning.
Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms.
Curvature-Exploiting Acceleration of Elastic Net Computations.
Traditional and Heavy Tailed Self Regularization in Neural Network Models.
Data Poisoning Attacks in Multi-Party Learning.
Guided evolutionary strategies: augmenting random search with surrogate gradients.
Composable Core-sets for Determinant Maximization: A Simple Near-Optimal Algorithm.
Bayesian leave-one-out cross-validation for large data.
EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE.
Variational Implicit Processes.
Disentangled Graph Convolutional Networks.
Differentiable Dynamic Normalization for Learning Deep Representation.
Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction.
High-Fidelity Image Generation With Fewer Labels.
Generalized Approximate Survey Propagation for High-Dimensional Estimation.
CoT: Cooperative Training for Generative Modeling of Discrete Data.
Optimal Algorithms for Lipschitz Bandits with Heavy-tailed Rewards.
Neurally-Guided Structure Inference.
PA-GD: On the Convergence of Perturbed Alternating Gradient Descent to Second-Order Stationary Points for Structured Nonconvex Optimization.
Bayesian Counterfactual Risk Minimization.
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations.
Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions.
Understanding MCMC Dynamics as Flows on the Wasserstein Space.
Understanding and Accelerating Particle-Based Variational Inference.
On Certifying Non-Uniform Bounds against Adversarial Attacks.
Taming MAML: Efficient unbiased meta-reinforcement learning.
The Implicit Fairness Criterion of Unconstrained Learning.
Data Poisoning Attacks on Stochastic Bandits.
Sparse Extreme Multi-label Learning with Oracle Property.
Rao-Blackwellized Stochastic Gradients for Discrete Distributions.
Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers.
Acceleration of SVRG and Katyusha X by Inexact Preconditioning.
Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations.
On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithms.
Kernel-Based Reinforcement Learning in Robust Markov Decision Processes.
Inference and Sampling of $K_33$-free Ising Models.
Regularization in directable environments with application to Tetris.
Cautious Regret Minimization: Online Optimization with Long-Term Budget Constraints.
Alternating Minimizations Converge to Second-Order Optimal Solutions.
Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting.
Feature-Critic Networks for Heterogeneous Domain Generalization.
Towards a Unified Analysis of Random Fourier Features.
Adversarial camera stickers: A physical camera-based attack on deep learning systems.
Exploiting Worker Correlation for Label Aggregation in Crowdsourcing.
Bayesian Joint Spike-and-Slab Graphical Lasso.
NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks.
Online Learning to Rank with Features.
Area Attention.
Graph Matching Networks for Learning the Similarity of Graph Structured Objects.
LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning.
Sublinear quantum algorithms for training linear and kernel-based classifiers.
Are Generative Classifiers More Robust to Adversarial Attacks?
Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group.
MONK Outlier-Robust Mean Embedding Estimation by Median-of-Means.
Sublinear Time Nearest Neighbor Search over Generalized Weighted Space.
Robust Inference via Generative Classifiers for Handling Noisy Labels.
First-Order Algorithms Converge Faster than $O(1/k)$ on Convex Problems.
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks.
Self-Attention Graph Pooling.
Functional Transparency for Structured Data: a Game-Theoretic Approach.
Target-Based Temporal-Difference Learning.
Batch Policy Learning under Constraints.
POLITEX: Regret Bounds for Policy Iteration using Expert Prediction.
DP-GP-LVM: A Bayesian Non-Parametric Model for Learning Multivariate Dependency Structures.
Lorentzian Distance Learning for Hyperbolic Representations.
A Better k-means++ Algorithm via Local Search.
Safe Policy Improvement with Baseline Bootstrapping.
Projection onto Minkowski Sums with Application to Constrained Learning.
A Recurrent Neural Cascade-based Model for Continuous-Time Diffusion.
State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations.
Characterizing Well-Behaved vs. Pathological Deep Neural Networks.
Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits.
Making Decisions that Reduce Discriminatory Impacts.
A Large-Scale Study on Regularization and Normalization in GANs.
Geometry and Symmetry in Short-and-Sparse Deconvolution.
Loss Landscapes of Regularized Linear Autoencoders.
Faster Algorithms for Binary Matrix Factorization.
Estimate Sequences for Variance-Reduced Stochastic Composite Optimization.
On the Complexity of Approximating Wasserstein Barycenters.
Similarity of Neural Network Representations Revisited.
LIT: Learned Intermediate Representation Training for Model Compression.
Stochastic Beams and Where To Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement.
Robust Learning from Untrusted Sources.
Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication.
POPQORN: Quantifying Robustness of Recurrent Neural Networks.
Guarantees for Spectral Clustering with Fairness Constraints.
Fair k-Center Clustering for Data Summarization.
AUCμ: A Performance Metric for Multi-Class Machine Learning Models.
Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspaces.
CompILE: Compositional Imitation Learning and Execution.
Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables.
Uniform Convergence Rate of the Kernel Density Estimator Adaptive to Intrinsic Volume Dimension.
Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Model.
Curiosity-Bottleneck: Exploration By Distilling Task-Specific Novelty.
FloWaveNet : A Generative Flow for Raw Audio.
EMI: Exploration with Mutual Information.
Geometry Aware Convolutional Filters for Omnidirectional Images Representation.
Collaborative Evolutionary Reinforcement Learning.
CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network.
Adaptive Scale-Invariant Online Algorithms for Learning Linear Models.
Submodular Streaming in All Its Glory: Tight Approximation, Minimum Memory and Low Adaptive Complexity.
Shallow-Deep Networks: Understanding and Mitigating Network Overthinking.
Robust Estimation of Tree Structured Gaussian Graphical Models.
Processing Megapixel Images with Deep Attention-Sampling Models.
Neural Inverse Knitting: From Images to Manufacturing Instructions.
Riemannian adaptive stochastic gradient algorithms on matrix manifolds.
Error Feedback Fixes SignSGD and other Gradient Compression Schemes.
Policy Consolidation for Continual Reinforcement Learning.
Differentially Private Learning of Geometric Concepts.
Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments.
Trainable Decoding of Sets of Sequences for Neural Sequence Models.
Classifying Treatment Responders Under Causal Effect Monotonicity.
Robust Influence Maximization for Hyperparametric Models.
Molecular Hypergraph Grammar with Its Application to Molecular Optimization.
Statistical Foundations of Virtual Democracy.
Bilinear Bandits with Low-rank Structure.
GOODE: A Gaussian Off-The-Shelf Ordinary Differential Equation Solver.
Kernel Mean Matching for Content Addressability of GANs.
Discovering Options for Exploration by Minimizing Cover Time.
Finding Options that Minimize Planning Time.
Neural Logic Reinforcement Learning.
Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization.
Learning Discrete and Continuous Factors of Data via Alternating Disentanglement.
Training CNNs with Selective Allocation of Channels.
Ladder Capsule Network.
Graph Neural Network for Music Score Data and Modeling Expressive Piano Performance.
A Deep Reinforcement Learning Perspective on Internet Congestion Control.
Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning.
Learning What and Where to Transfer.
DBSCAN++: Towards fast and scalable density clustering.
Sum-of-Squares Polynomial Flow.
Differentially Private Fair Learning.
Learning from a Learner.
Causal Identification under Markov Equivalence: Completeness Results.
Complementary-Label Learning for Arbitrary Losses and Models.
Actor-Attention-Critic for Multi-Agent Reinforcement Learning.
Phase transition in PCA with missing data: Reduced signal-to-noise ratio, not sample size!
Learning Structured Decision Problems with Unawareness.
Overcoming Mean-Field Approximations in Recurrent Gaussian Process Models.
HexaGAN: Generative Adversarial Nets for Real World Classification.
Composing Entropic Policies using Divergence Correction.
Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models.
Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment.
Stable and Fair Classification.
Hierarchical Importance Weighted Autoencoders.
Detecting Overlapping and Correlated Communities without Pure Nodes: Identifiability and Algorithm.
Unsupervised Deep Learning by Neighbourhood Discovery.
Faster Stochastic Alternating Direction Method of Multipliers for Nonconvex Optimization.
Bayesian Deconditional Kernel Mean Embeddings.
Classification from Positive, Unlabeled and Biased Negative Data.
Finding Mixed Nash Equilibria of Generative Adversarial Networks.
Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With Reneging.
Parameter-Efficient Transfer Learning for NLP.
Nonconvex Variance Reduced Optimization with Arbitrary Sampling.
Emerging Convolutions for Generative Normalizing Flows.
Better generalization with less data using robust gradient descent.
Connectivity-Optimized Representation Learning via Persistent Homology.
Collective Model Fusion for Multiple Black-Box Experts.
Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules.
Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design.
Using Pre-Training Can Improve Model Robustness and Uncertainty.
Graph Resistance and Learning from Pairwise Comparisons.
On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learning.
Provably Efficient Maximum Entropy Exploration.
On the Impact of the Activation function on Deep Neural Networks Training.
Understanding and Controlling Memory in Recurrent Neural Networks.
Submodular Observation Selection and Information Gathering for Quadratic Models.
Per-Decision Option Discounting.
Submodular Maximization beyond Non-negativity: Guarantees, Fast Algorithms, and Applications.
Random Shuffling Beats SGD after Finite Epochs.
Doubly-Competitive Distribution Estimation.
Importance Sampling Policy Evaluation with an Estimated Behavior Policy.
Complexity of Linear Regions in Deep Networks.
Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning.
Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI.
Neural Separation of Observed and Unobserved Distributions.
Learning Latent Dynamics for Planning from Pixels.
Trading Redundancy for Communication: Speeding up Distributed SGD for Non-convex Optimization.
On The Power of Curriculum Learning in Training Deep Networks.
IMEXnet A Forward Stable Deep Neural Network.
Memory-Optimal Direct Convolutions for Maximizing Classification Accuracy in Embedded Applications.
Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs.
Exploring interpretable LSTM neural networks over multi-variable data.
Simple Black-box Adversarial Attacks.
Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops.
An Investigation of Model-Free Planning.
Towards a Deep and Unified Understanding of Deep Neural Models in NLP.
Fast Algorithm for Generalized Multinomial Models with Ranking Data.
Graphite: Iterative Generative Modeling of Graphs.
Multi-Object Representation Learning with Iterative Variational Inference.
Learning to Optimize Multigrid PDE Solvers.
Automatic Posterior Transformation for Likelihood-Free Inference.
A Statistical Investigation of Long Memory in Language and Music.
Adaptive Sensor Placement for Continuous Spaces.
Counterfactual Visual Explanations.
Combining parametric and nonparametric models for off-policy evaluation.
Obtaining Fairness using Optimal Transport Theory.
Quantile Stein Variational Gradient Descent for Batch Bayesian Optimization.
Efficient Training of BERT by Progressively Stacking.
The information-theoretic value of unlabeled data in semi-supervised learning.
Online Algorithms for Rent-Or-Buy with Expert Advice.
Amortized Monte Carlo Integration.
Estimating Information Flow in Deep Neural Networks.
Discovering Conditionally Salient Features with Statistical Guarantees.
Adversarial Examples Are a Natural Consequence of Test Error in Noise.
Learning to Groove with Inverse Sequence Transformations.
A Tree-Based Method for Fast Repeated Sampling of Determinantal Point Processes.
Efficient Dictionary Learning with Gradient Descent.
Data Shapley: Equitable Valuation of Data for Machine Learning.
An Investigation into Neural Net Optimization via Hessian Eigenvalue Density.
An Instability in Variational Inference for Topic Models.
Recursive Sketches for Modular Deep Learning.
Improved Parallel Algorithms for Density-Based Network Clustering.
Learning and Data Selection in Big Datasets.
Partially Linear Additive Gaussian Graphical Models.
DeepMDP: Learning Continuous Latent Space Models for Representation Learning.
A Theory of Regularized Markov Decision Processes.
SelectiveNet: A Deep Neural Network with an Integrated Reject Option.
Optimal Mini-Batch and Step Sizes for SAGA.
Multi-Frequency Phase Synchronization.
Geometric Scattering for Graph Data Analysis.
Demystifying Dropout.
Rate Distortion For Model Compression: From Theory To Practice.
Deep Generative Learning via Variational Gradient Flow.
Graph U-Nets.
Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities.
Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation.
Off-Policy Deep Reinforcement Learning without Exploration.
Beyond Adaptive Submodularity: Approximation Guarantees of Greedy Policy with Adaptive Submodularity Ratio.
MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement.
Diagnosing Bottlenecks in Deep Q-learning Algorithms.
Analyzing and Improving Representations with the Soft Nearest Neighbor Loss.
Fast and Flexible Inference of Joint Distributions from their Marginals.
Approximating Orthogonal Matrices with Effective Givens Factorization.
Distributional Multivariate Policy Evaluation and Exploration with the Bellman GAN.
Learning Discrete Structures for Graph Neural Networks.
On discriminative learning of prediction uncertainty.
Scalable Nonparametric Sampling from Multimodal Posteriors with the Posterior Bootstrap.
Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning.
DL2: Training and Querying Neural Networks with Logic.
Online Meta-Learning.
Almost surely constrained convex optimization.
Decentralized Exploration in Multi-Armed Bandits.
The advantages of multiple classes for reducing overfitting from test set reuse.
Invariant-Equivariant Representation Learning for Multi-Class Data.
Dead-ends and Secure Exploration in Reinforcement Learning.
Regret Circuits: Composability of Regret Minimizers.
Stable-Predictive Optimistic Counterfactual Regret Minimization.
Multi-Frequency Vector Diffusion Maps.
Non-monotone Submodular Maximization with Nearly Optimal Adaptivity and Query Complexity.
On the Connection Between Adversarial Robustness and Saliency Map Interpretability.
Cross-Domain 3D Equivariant Image Embeddings.
Exploring the Landscape of Spatial Robustness.
Improved Convergence for $\ell_1$ and $\ell_∞$ Regression via Iteratively Reweighted Least Squares.
Sequential Facility Location: Approximate Submodularity and Greedy Algorithm.
GDPP: Learning Diverse Generations using Determinantal Point Processes.
Semi-Cyclic Stochastic Gradient Descent.
Imitating Latent Policies from Observation.
Band-limited Training and Inference for Convolutional Neural Networks.
Autoregressive Energy Machines.
Learning interpretable continuous-time models of latent stochastic dynamical systems.
Wasserstein of Wasserstein Loss for Learning Generative Models.
Optimal Auctions through Deep Learning.
Task-Agnostic Dynamics Priors for Deep Reinforcement Learning.
Incorporating Grouping Information into Bayesian Decision Tree Ensembles.
Gradient Descent Finds Global Minima of Deep Neural Networks.
Provably efficient RL with Rich Observations via Latent State Decoding.
Width Provably Matters in Optimization for Deep Linear Neural Networks.
Generalized No Free Lunch Theorem for Adversarial Robustness.
Trajectory-Based Off-Policy Deep Reinforcement Learning.
Finite-Time Analysis of Distributed TD(0) with Linear Function Approximation on Multi-Agent Reinforcement Learning.
Noisy Dual Principal Component Pursuit.
Approximated Oracle Filter Pruning for Destructive CNN Width Optimization.
Sever: A Robust Meta-Algorithm for Stochastic Optimization.
Learning to Convolve: A Generalized Weight-Tying Approach.
A Multitask Multiple Kernel Learning Algorithm for Survival Analysis with Application to Cancer Biology.
Learning-to-Learn Stochastic Gradient Descent with Biased Regularization.
Stochastic Deep Networks.
Teaching a black-box learner.
TarMAC: Targeted Multi-Agent Communication.
A Kernel Theory of Modern Data Augmentation.
Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations.
Policy Certificates: Towards Accountable Reinforcement Learning.
Bayesian Optimization Meets Bayesian Optimal Stopping.
The Value Function Polytope in Reinforcement Learning.
Open Vocabulary Learning on Source Code with a Graph-Structured Cache.
Minimal Achievable Sufficient Statistic Learning.
Matrix-Free Preconditioning in Online Learning.
Anytime Online-to-Batch, Optimism and Acceleration.
Flexibly Fair Representation Learning by Disentanglement.
Submodular Cost Submodular Cover with an Approximate Oracle.
Boosted Density Estimation Remastered.
Monge blunts Bayes: Hardness Results for Adversarial Training.
Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints.
Shape Constraints for Set Functions.
Active Learning with Disagreement Graphs.
Online Learning with Sleeping Experts and Feedback Graphs.
Adjustment Criteria for Generalizing Experimental Findings.
Scalable Metropolis-Hastings for Exact Bayesian Inference with Large Datasets.
A fully differentiable beam search decoder.
CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning.
Gauge Equivariant Convolutional Networks and the Icosahedral CNN.
Certified Adversarial Robustness via Randomized Smoothing.
Learning Linear-Quadratic Regulators Efficiently with only √T Regret.
Empirical Analysis of Beam Search Performance Degradation in Neural Sequence Models.
Quantifying Generalization in Reinforcement Learning.
On Medians of (Randomized) Pairwise Means.
Dimensionality Reduction for Tukey Regression.
Sensitivity Analysis of Linear Structural Causal Models.
New results on information theoretic clustering.
Weak Detection of Signal in the Spiked Wigner Model.
MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization.
Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning.
Unifying Orthogonal Monte Carlo Methods.
Beyond Backprop: Online Alternating Minimization with Auxiliary Variables.
Neural Joint Source-Channel Coding.
Random Walks on Hypergraphs with Edge-Dependent Vertex Weights.
Variational Inference for sparse network reconstruction from count data.
Predictor-Corrector Policy Optimization.
Control Regularization for Reduced Variance Reinforcement Learning.
RaFM: Rank-Aware Factorization Machines.
Robust Decision Trees Against Adversarial Examples.
Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching.
Katalyst: Boosting Convex Katayusha for Non-Convex Problems with a Large Condition Number.
Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications.
Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation.
A Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein Minimization.
Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels.
Generative Adversarial User Model for Reinforcement Learning Based Recommendation System.
Information-Theoretic Considerations in Batch Reinforcement Learning.
Proportionally Fair Clustering.
Particle Flow Bayes' Rule.
Stein Point Markov Chain Monte Carlo.
Nearest Neighbor and Kernel Survival Analysis: Nonasymptotic Error Bounds and Strong Consistency Rates.
PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits.
Neural Network Attributions: A Causal Perspective.
Online learning with kernel losses.
On Symmetric Losses for Learning from Corrupted Labels.
Dynamic Measurement Scheduling for Event Forecasting using Deep RL.
Learning Action Representations for Reinforcement Learning.
Automated Model Selection with Bayesian Quadrature.
Competing Against Nash Equilibria in Adversarially Changing Zero-Sum Games.
Dynamic Learning with Frequent New Product Launches: A Sequential Multinomial Logit Bandit Problem.
Active Embedding Search via Noisy Paired Comparisons.
Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances.
A Quantitative Analysis of the Effect of Batch Normalization on Gradient Descent.
What is the Effect of Importance Weighting in Deep Learning?
Rates of Convergence for Sparse Variational Gaussian Process Regression.
Learning Generative Models across Incomparable Spaces.
Self-similar Epochs: Value in arrangement.
Adversarial examples from computational constraints.
Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem.
Low Latency Privacy Preserving Inference.
Understanding the Origins of Bias in Word Embeddings.
Deep Counterfactual Regret Minimization.
Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations.
Conditioning by adaptive sampling for robust design.
Active Manifolds: A non-linear analogue to Active Subspaces.
Target Tracking for Contextual Bandits: Application to Demand Side Management.
Coresets for Ordered Weighted Clustering.
Blended Conditonal Gradients.
Unreproducible Research is Reproducible.
Compositional Fairness Constraints for Graph Embeddings.
Online Variance Reduction with Mixtures.
Adversarial Attacks on Node Embeddings via Graph Poisoning.
Correlated bandits or: How to minimize mean-squared error online.
Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff.
A Kernel Perspective for Regularizing Deep Neural Networks.
More Efficient Off-Policy Evaluation through Regularized Targeted Learning.
Optimal Continuous DR-Submodular Maximization and Applications to Provable Mean Field Inference.
Analyzing Federated Learning through an Adversarial Lens.
Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case.
Adversarially Learned Representations for Information Obfuscation and Inference.
Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning.
Overcoming Multi-model Forgetting.
Greedy Layerwise Learning Can Scale To ImageNet.
Invertible Residual Networks.
Active Learning for Probabilistic Structured Prediction of Cuts and Matchings.
Switching Linear Dynamics for Variational Bayes Filtering.
Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces.
Efficient optimization of loops and limits with randomized telescoping sums.
Noise2Self: Blind Denoising by Self-Supervision.
Categorical Feature Compression via Submodular Optimization.
Pareto Optimal Streaming Unsupervised Classification.
Scale-free adaptive planning for deterministic dynamics & discounted rewards.
A Personalized Affective Memory Model for Improving Emotion Recognition.
Learning to Route in Similarity Graphs.
Structured agents for physical construction.
HOList: An Environment for Machine Learning of Higher Order Logic Theorem Proving.
Concrete Autoencoders: Differentiable Feature Selection and Reconstruction.
Open-ended learning in symmetric zero-sum games.
Provable Guarantees for Gradient-Based Meta-Learning.
Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs.
Scalable Fair Clustering.
Beyond the Chinese Restaurant and Pitman-Yor processes: Statistical Models with double power-law behavior.
Feature Grouping as a Stochastic Regularizer for High-Dimensional Structured Data.
Benefits and Pitfalls of the Exponential Mechanism with Applications to Hilbert Spaces and Functional PCA.
Linear-Complexity Data-Parallel Earth Mover's Distance Approximations.
Bayesian Optimization of Composite Functions.
Stochastic Gradient Push for Distributed Deep Learning.
Distributed Weighted Matching via Randomized Composable Coresets.
Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks.
Unsupervised Label Noise Modeling and Loss Correction.
Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data.
Sorting Out Lipschitz Function Approximation.
Scaling Up Ordinal Embedding: A Landmark Approach.
Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation.
Bounding User Contributions: A Bias-Variance Trade-off in Differential Privacy.
Asynchronous Batch Bayesian Optimisation with Improved Local Penalisation.
A Convergence Theory for Deep Learning via Over-Parameterization.
Infinite Mixture Prototypes for Few-shot Learning.
Analogies Explained: Towards Understanding Word Embeddings.
Graph Element Networks: adaptive, structured computation and memory.
Multi-objective training of Generative Adversarial Networks with multiple discriminators.
Validating Causal Inference Models via Influence Functions.
Projections for Approximate Policy Iteration Algorithms.
Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search.
Fairwashing: the risk of rationalization.
Understanding the Impact of Entropy on Policy Optimization.
The Kernel Interaction Trick: Fast Bayesian Discovery of Pairwise Interactions in High Dimensions.
Learning to Generalize from Sparse and Underspecified Rewards.
Fair Regression: Quantitative Definitions and Reduction-Based Algorithms.
Online Control with Adversarial Disturbances.
Efficient Full-Matrix Adaptive Regularization.
Static Automatic Batching In TensorFlow.
PAC Learnability of Node Functions in Networked Dynamical Systems.
TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning.
Learning Models from Data with Measurement Error: Tackling Underreporting.
Communication Complexity in Locally Private Distribution Estimation and Heavy Hitters.
Distributed Learning with Sublinear Communication.
Communication-Constrained Inference and the Role of Shared Randomness.
MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing.
Dynamic Weights in Multi-Objective Deep Reinforcement Learning.
AReS and MaRS Adversarial and MMD-Minimizing Regression for SDEs.
