AIConfPaper
← All conferences

ICML 2019 Accepted Papers

The full list of 773 papers accepted at ICML 2019 (International Conference on Machine Learning). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

Oral: 772
  1. EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksOral28,829 citations
  2. Self-Attention Generative Adversarial NetworksOral5,274 citations
  3. Parameter-Efficient Transfer Learning for NLPOral5,271 citations
  4. Simplifying Graph Convolutional NetworksOral4,182 citations
  5. Theoretically Principled Trade-off between Robustness and AccuracyOral3,190 citations
  6. Certified Adversarial Robustness via Randomized SmoothingOral2,480 citations
  7. Do ImageNet Classifiers Generalize to ImageNet?Oral2,201 citations
  8. Off-Policy Deep Reinforcement Learning without ExplorationOral1,958 citations
  9. On the Spectral Bias of Neural NetworksOral1,826 citations
  10. Learning Latent Dynamics for Planning from PixelsOral1,823 citations
  11. A Convergence Theory for Deep Learning via Over-ParameterizationOral1,811 citations
  12. Challenging Common Assumptions in the Unsupervised Learning of Disentangled RepresentationsOral1,772 citations
  13. Similarity of Neural Network Representations RevisitedOral1,704 citations
  14. Manifold Mixup: Better Representations by Interpolating Hidden StatesOral1,641 citations
  15. Set Transformer: A Framework for Attention-based Permutation-Invariant Neural NetworksOral1,601 citations
  16. Graph U-NetsOral1,567 citations
  17. Self-Attention Graph PoolingOral1,542 citations
  18. Gradient Descent Finds Global Minima of Deep Neural NetworksOral1,501 citations
  19. Analyzing Federated Learning through an Adversarial LensOral1,470 citations
  20. MASS: Masked Sequence to Sequence Pre-training for Language GenerationOral1,237 citations
  21. MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood MixingOral1,185 citations
  22. Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural NetworksOral1,183 citations
  23. Agnostic Federated LearningOral1,180 citations
  24. QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement LearningOral1,087 citations
  25. Data Shapley: Equitable Valuation of Data for Machine LearningOral1,067 citations
  26. Making Convolutional Networks Shift-Invariant AgainOral1,056 citations
  27. Actor-Attention-Critic for Multi-Agent Reinforcement LearningOral1,031 citations
  28. On Variational Bounds of Mutual InformationOral1,008 citations
  29. How does Disagreement Help Generalization against Label Corruption?Oral975 citations
  30. Using Pre-Training Can Improve Model Robustness and UncertaintyOral952 citations
  31. Bridging Theory and Algorithm for Domain AdaptationOral945 citations
  32. A Theoretical Analysis of Contrastive Unsupervised Representation LearningOral933 citations
  33. Bayesian Nonparametric Federated Learning of Neural NetworksOral932 citations
  34. NAS-Bench-101: Towards Reproducible Neural Architecture SearchOral905 citations
  35. Noise2Self: Blind Denoising by Self-SupervisionOral877 citations
  36. Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context VariablesOral838 citations
  37. Quantifying Generalization in Reinforcement LearningOral831 citations
  38. Unsupervised Label Noise Modeling and Loss CorrectionOral790 citations
  39. Graph Matching Networks for Learning the Similarity of Graph Structured ObjectsOral779 citations
  40. On Learning Invariant Representations for Domain AdaptationOral769 citations
  41. Invertible Residual NetworksOral759 citations
  42. Simple Black-box Adversarial AttacksOral740 citations
  43. Counterfactual Visual ExplanationsOral672 citations
  44. Position-aware Graph Neural NetworksOral634 citations
  45. AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder LossOral632 citations
  46. Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain AdaptationOral629 citations
  47. DAG-GNN: DAG Structure Learning with Graph Neural NetworksOral622 citations
  48. Error Feedback Fixes SignSGD and other Gradient Compression SchemesOral616 citations
  49. Decentralized Stochastic Optimization and Gossip Algorithms with Compressed CommunicationOral609 citations
  50. What is the Effect of Importance Weighting in Deep Learning?Oral606 citations
  51. Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement LearningOral603 citations
  52. The Evolved TransformerOral580 citations
  53. Online Meta-LearningOral576 citations
  54. Multi-Object Representation Learning with Iterative Variational InferenceOral565 citations
  55. On The Power of Curriculum Learning in Training Deep NetworksOral558 citations
  56. SGD: General Analysis and Improved RatesOral557 citations
  57. Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture DesignOral553 citations
  58. Exploring the Landscape of Spatial RobustnessOral552 citations
  59. Population Based Augmentation: Efficient Learning of Augmentation Policy SchedulesOral547 citations
  60. Improving Adversarial Robustness via Promoting Ensemble DiversityOral544 citations
  61. TarMAC: Targeted Multi-Agent CommunicationOral536 citations
  62. Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic ForgettingOral531 citations
  63. Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech RecognitionOral526 citations
  64. Learning Discrete Structures for Graph Neural NetworksOral526 citations
  65. SELFIE: Refurbishing Unclean Samples for Robust Deep LearningOral522 citations
  66. Gauge Equivariant Convolutional Networks and the Icosahedral CNNOral512 citations
  67. Understanding and Utilizing Deep Neural Networks Trained with Noisy LabelsOral488 citations
  68. Self-Supervised Exploration via DisagreementOral485 citations
  69. Fast Context Adaptation via Meta-LearningOral480 citations
  70. Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from ObservationsOral469 citations
  71. Plug-and-Play Methods Provably Converge with Properly Trained DenoisersOral469 citations
  72. On the Convergence and Robustness of Adversarial TrainingOral456 citations
  73. Information-Theoretic Considerations in Batch Reinforcement LearningOral453 citations
  74. On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex OptimizationOral452 citations
  75. Stochastic Gradient Push for Distributed Deep LearningOral437 citations
  76. White-box vs Black-box: Bayes Optimal Strategies for Membership InferenceOral432 citations
  77. Flexibly Fair Representation Learning by DisentanglementOral430 citations
  78. Disentangled Graph Convolutional NetworksOral426 citations
  79. AdaGrad Stepsizes: Sharp Convergence Over Nonconvex LandscapesOral420 citations
  80. SelectiveNet: A Deep Neural Network with an Integrated Reject OptionOral420 citations
  81. Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterizationOral416 citations
  82. MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech EnhancementOral413 citations
  83. TensorFuzz: Debugging Neural Networks with Coverage-Guided FuzzingOral413 citations
  84. Sorting Out Lipschitz Function ApproximationOral407 citations
  85. A Deep Reinforcement Learning Perspective on Internet Congestion ControlOral404 citations
  86. Towards Understanding Knowledge DistillationOral398 citations
  87. Batch Policy Learning under ConstraintsOral396 citations
  88. Automatic Posterior Transformation for Likelihood-Free InferenceOral392 citations
  89. Improving Neural Network Quantization without Retraining using Outlier Channel SplittingOral392 citations
  90. Adversarial Attacks on Node Embeddings via Graph PoisoningOral391 citations
  91. A Theory of Regularized Markov Decision ProcessesOral385 citations
  92. An Investigation into Neural Net Optimization via Hessian Eigenvalue DensityOral383 citations
  93. Transferable Clean-Label Poisoning Attacks on Deep Neural NetsOral380 citations
  94. DeepMDP: Learning Continuous Latent Space Models for Representation LearningOral378 citations
  95. Sample-Optimal Parametric Q-Learning Using Linearly Additive FeaturesOral377 citations
  96. Rethinking Lossy Compression: The Rate-Distortion-Perception TradeoffOral375 citations
  97. COMIC: Multi-view Clustering Without Parameter SelectionOral374 citations
  98. Provably Efficient Maximum Entropy ExplorationOral370 citations
  99. Shallow-Deep Networks: Understanding and Mitigating Network OverthinkingOral368 citations
  100. Graphite: Iterative Generative Modeling of GraphsOral367 citations
  101. Fair Regression: Quantitative Definitions and Reduction-Based AlgorithmsOral366 citations
  102. Disentangling Disentanglement in Variational AutoencodersOral361 citations
  103. MIWAE: Deep Generative Modelling and Imputation of Incomplete Data SetsOral356 citations
  104. Sever: A Robust Meta-Algorithm for Stochastic OptimizationOral355 citations
  105. GMNN: Graph Markov Neural NetworksOral350 citations
  106. Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-toleranceOral346 citations
  107. Domain Agnostic Learning with Disentangled RepresentationsOral343 citations
  108. Learning to Exploit Long-term Relational Dependencies in Knowledge GraphsOral343 citations
  109. Rademacher Complexity for Adversarially Robust GeneralizationOral341 citations
  110. SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solverOral335 citations
  111. TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot LearningOral331 citations
  112. Infinite Mixture Prototypes for Few-shot LearningOral329 citations
  113. Compositional Fairness Constraints for Graph EmbeddingsOral328 citations
  114. Learning with Bad Training Data via Iterative Trimmed Loss MinimizationOral327 citations
  115. Feature-Critic Networks for Heterogeneous Domain GeneralizationOral326 citations
  116. Low Latency Privacy Preserving InferenceOral325 citations
  117. Relational Pooling for Graph RepresentationsOral325 citations
  118. Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function BoundsOral325 citations
  119. BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task LearningOral324 citations
  120. Gromov-Wasserstein Learning for Graph Matching and Node EmbeddingOral323 citations
  121. SOLAR: Deep Structured Representations for Model-Based Reinforcement LearningOral321 citations
  122. Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value ApproximationOral319 citations
  123. Transferable Adversarial Training: A General Approach to Adapting Deep ClassifiersOral314 citations
  124. NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural NetworksOral308 citations
  125. Understanding the Impact of Entropy on Policy OptimizationOral306 citations
  126. Zero-Shot Knowledge Distillation in Deep NetworksOral306 citations
  127. On the Impact of the Activation function on Deep Neural Networks TrainingOral304 citations
  128. Deep Counterfactual Regret MinimizationOral302 citations
  129. Provably efficient RL with Rich Observations via Latent State DecodingOral293 citations
  130. Complexity of Linear Regions in Deep NetworksOral292 citations
  131. On the Universality of Invariant NetworksOral292 citations
  132. Understanding the Origins of Bias in Word EmbeddingsOral290 citations
  133. A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural NetworksOral289 citations
  134. DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-pass Error-Compensated CompressionOral289 citations
  135. Action Robust Reinforcement Learning and Applications in Continuous ControlOral284 citations
  136. Doubly Robust Joint Learning for Recommendation on Data Missing Not at RandomOral282 citations
  137. Generative Adversarial User Model for Reinforcement Learning Based Recommendation SystemOral280 citations
  138. Online Control with Adversarial DisturbancesOral280 citations
  139. Training Neural Networks with Local Error SignalsOral279 citations
  140. Scalable Fair ClusteringOral277 citations
  141. Wasserstein Adversarial Examples via Projected Sinkhorn IterationsOral275 citations
  142. Optimal Auctions through Deep LearningOral273 citations
  143. Insertion Transformer: Flexible Sequence Generation via Insertion OperationsOral270 citations
  144. Hierarchically Structured Meta-learningOral265 citations
  145. Stochastic Beams and Where To Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without ReplacementOral265 citations
  146. The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization EffectsOral265 citations
  147. Adversarial examples from computational constraintsOral262 citations
  148. Conditioning by adaptive sampling for robust designOral260 citations
  149. Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary GroupOral256 citations
  150. MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive SummarizationOral254 citations
  151. Safe Policy Improvement with Baseline BootstrappingOral252 citations
  152. A Kernel Theory of Modern Data AugmentationOral250 citations
  153. Deep Factors for ForecastingOral247 citations
  154. Exploring interpretable LSTM neural networks over multi-variable dataOral242 citations
  155. Model-Based Active ExplorationOral242 citations
  156. BayesNAS: A Bayesian Approach for Neural Architecture SearchOral236 citations
  157. DL2: Training and Querying Neural Networks with LogicOral231 citations
  158. Dynamic Weights in Multi-Objective Deep Reinforcement LearningOral231 citations
  159. Near optimal finite time identification of arbitrary linear dynamical systemsOral231 citations
  160. On the Limitations of Representing Functions on SetsOral229 citations
  161. Combating Label Noise in Deep Learning using AbstentionOral228 citations
  162. Learning Action Representations for Reinforcement LearningOral228 citations
  163. The Odds are Odd: A Statistical Test for Detecting Adversarial ExamplesOral228 citations
  164. Greedy Layerwise Learning Can Scale To ImageNetOral227 citations
  165. A Large-Scale Study on Regularization and Normalization in GANsOral225 citations
  166. Obtaining Fairness using Optimal Transport TheoryOral225 citations
  167. Learning Linear-Quadratic Regulators Efficiently with only $\sqrtT$ RegretOral224 citations
  168. Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?Oral223 citations
  169. ME-Net: Towards Effective Adversarial Robustness with Matrix EstimationOral222 citations
  170. Adaptive Neural TreesOral221 citations
  171. FloWaveNet : A Generative Flow for Raw AudioOral221 citations
  172. Open-ended learning in symmetric zero-sum gamesOral220 citations
  173. Fair k-Center Clustering for Data SummarizationOral219 citations
  174. Guarantees for Spectral Clustering with Fairness ConstraintsOral219 citations
  175. CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement LearningOral218 citations
  176. Deep Compressed SensingOral218 citations
  177. Rates of Convergence for Sparse Variational Gaussian Process RegressionOral218 citations
  178. Fairwashing: the risk of rationalizationOral212 citations
  179. Adversarial camera stickers: A physical camera-based attack on deep learning systemsOral209 citations
  180. Optimal Transport for structured data with application on graphsOral207 citations
  181. Analogies Explained: Towards Understanding Word EmbeddingsOral206 citations
  182. Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural NetworksOral206 citations
  183. Proportionally Fair ClusteringOral205 citations
  184. Adversarial Examples Are a Natural Consequence of Test Error in NoiseOral202 citations
  185. Differentially Private Fair LearningOral202 citations
  186. Imitation Learning from Imperfect DemonstrationOral201 citations
  187. A Framework for Bayesian Optimization in Embedded SubspacesOral200 citations
  188. Bayesian Action Decoder for Deep Multi-Agent Reinforcement LearningOral200 citations
  189. Collaborative Channel Pruning for Deep NetworksOral198 citations
  190. Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional SubspacesOral194 citations
  191. HOList: An Environment for Machine Learning of Higher Order Logic Theorem ProvingOral194 citations
  192. Concrete Autoencoders: Differentiable Feature Selection and ReconstructionOral193 citations
  193. Graphical-model based estimation and inference for differential privacyOral192 citations
  194. Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional RobustnessOral192 citations
  195. Interpreting Adversarially Trained Convolutional Neural NetworksOral191 citations
  196. Analyzing and Improving Representations with the Soft Nearest Neighbor LossOral190 citations
  197. Multi-Agent Adversarial Inverse Reinforcement LearningOral188 citations
  198. Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal ModelsOral187 citations
  199. Provable Guarantees for Gradient-Based Meta-LearningOral186 citations
  200. Subspace Robust Wasserstein DistancesOral185 citations
  201. Unsupervised Deep Learning by Neighbourhood DiscoveryOral185 citations
  202. High-Fidelity Image Generation With Fewer LabelsOral183 citations
  203. Learning What and Where to TransferOral183 citations
  204. Learning to Prove Theorems via Interacting with Proof AssistantsOral183 citations
  205. On the Connection Between Adversarial Robustness and Saliency Map InterpretabilityOral182 citations
  206. Bayesian Generative Active Deep LearningOral181 citations
  207. Estimating Information Flow in Deep Neural NetworksOral181 citations
  208. Neural Network Attributions: A Causal PerspectiveOral181 citations
  209. Diagnosing Bottlenecks in Deep Q-learning AlgorithmsOral180 citations
  210. Efficient Training of BERT by Progressively StackingOral179 citations
  211. Fairness risk measuresOral177 citations
  212. Understanding and correcting pathologies in the training of learned optimizersOral177 citations
  213. Policy Certificates: Towards Accountable Reinforcement LearningOral176 citations
  214. Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial OptimizationOral173 citations
  215. Robust Inference via Generative Classifiers for Handling Noisy LabelsOral173 citations
  216. Domain Adaptation with Asymmetrically-Relaxed Distribution AlignmentOral172 citations
  217. Imitating Latent Policies from ObservationOral172 citations
  218. Towards Accurate Model Selection in Deep Unsupervised Domain AdaptationOral172 citations
  219. Direct Uncertainty Prediction for Medical Second OpinionsOral171 citations
  220. Finite-Time Analysis of Distributed TD(0) with Linear Function Approximation on Multi-Agent Reinforcement LearningOral170 citations
  221. POLITEX: Regret Bounds for Policy Iteration using Expert PredictionOral169 citations
  222. Online Convex Optimization in Adversarial Markov Decision ProcessesOral168 citations
  223. Sum-of-Squares Polynomial FlowOral167 citations
  224. Online Algorithms for Rent-Or-Buy with Expert AdviceOral166 citations
  225. CompILE: Compositional Imitation Learning and ExecutionOral163 citations
  226. EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAEOral163 citations
  227. Fairness without Harm: Decoupled Classifiers with Preference GuaranteesOral163 citations
  228. Fairness-Aware Learning for Continuous Attributes and TreatmentsOral163 citations
  229. Circuit-GNN: Graph Neural Networks for Distributed Circuit DesignOral162 citations
  230. Robust Decision Trees Against Adversarial ExamplesOral162 citations
  231. Towards a Unified Analysis of Random Fourier FeaturesOral162 citations
  232. On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent AlgorithmsOral160 citations
  233. Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and DiffusionsOral159 citations
  234. Latent Normalizing Flows for Discrete SequencesOral158 citations
  235. Collaborative Evolutionary Reinforcement LearningOral157 citations
  236. Learning to Optimize Multigrid PDE SolversOral154 citations
  237. Mixture Models for Diverse Machine Translation: Tricks of the TradeOral153 citations
  238. Approximated Oracle Filter Pruning for Destructive CNN Width OptimizationOral151 citations
  239. Geometric Scattering for Graph Data AnalysisOral151 citations
  240. EigenDamage: Structured Pruning in the Kronecker-Factored EigenbasisOral149 citations
  241. A Dynamical Systems Perspective on Nesterov AccelerationOral147 citations
  242. A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based LearningOral147 citations
  243. Orthogonal Random Forest for Causal InferenceOral145 citations
  244. Poission Subsampled Rényi Differential PrivacyOral145 citations
  245. Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image TranslationOral145 citations
  246. Random Walks on Hypergraphs with Edge-Dependent Vertex WeightsOral144 citations
  247. Learning-to-Learn Stochastic Gradient Descent with Biased RegularizationOral143 citations
  248. Neural Joint Source-Channel CodingOral142 citations
  249. Distribution calibration for regressionOral140 citations
  250. Towards a Deep and Unified Understanding of Deep Neural Models in NLPOral139 citations
  251. ELF OpenGo: an analysis and open reimplementation of AlphaZeroOral137 citations
  252. Learning to Groove with Inverse Sequence TransformationsOral136 citations
  253. LGM-Net: Learning to Generate Matching Networks for Few-Shot LearningOral134 citations
  254. Learning Fast Algorithms for Linear Transforms Using Butterfly FactorizationsOral134 citations
  255. Learning Generative Models across Incomparable SpacesOral134 citations
  256. Non-Monotonic Sequential Text GenerationOral134 citations
  257. Semi-Cyclic Stochastic Gradient DescentOral134 citations
  258. Submodular Maximization beyond Non-negativity: Guarantees, Fast Algorithms, and ApplicationsOral134 citations
  259. Random Shuffling Beats SGD after Finite EpochsOral133 citations
  260. Data Poisoning Attacks on Stochastic BanditsOral132 citations
  261. Almost Unsupervised Text to Speech and Automatic Speech RecognitionOral131 citations
  262. Defending Against Saddle Point Attack in Byzantine-Robust Distributed LearningOral131 citations
  263. EMI: Exploration with Mutual InformationOral131 citations
  264. Lorentzian Distance Learning for Hyperbolic RepresentationsOral131 citations
  265. Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature SpacesOral131 citations
  266. First-Order Adversarial Vulnerability of Neural Networks and Input DimensionOral130 citations
  267. Complementary-Label Learning for Arbitrary Losses and ModelsOral129 citations
  268. Remember and Forget for Experience ReplayOral129 citations
  269. Learning to Infer Program SketchesOral128 citations
  270. Molecular Hypergraph Grammar with Its Application to Molecular OptimizationOral128 citations
  271. Cognitive model priors for predicting human decisionsOral127 citations
  272. Metropolis-Hastings Generative Adversarial NetworksOral127 citations
  273. Unreproducible Research is ReproducibleOral127 citations
  274. Learning Optimal Fair PoliciesOral126 citations
  275. Structured agents for physical constructionOral126 citations
  276. POPQORN: Quantifying Robustness of Recurrent Neural NetworksOral125 citations
  277. Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent ConstraintsOral125 citations
  278. Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent VariablesOral124 citations
  279. Emerging Convolutions for Generative Normalizing FlowsOral124 citations
  280. On the Complexity of Approximating Wasserstein BarycentersOral124 citations
  281. Validating Causal Inference Models via Influence FunctionsOral124 citations
  282. Improving Neural Language Modeling via Adversarial TrainingOral123 citations
  283. Bayesian Optimization of Composite FunctionsOral122 citations
  284. On Symmetric Losses for Learning from Corrupted LabelsOral122 citations
  285. Same, Same But Different: Recovering Neural Network Quantization Error Through Weight FactorizationOral122 citations
  286. Graph Element Networks: adaptive, structured computation and memoryOral121 citations
  287. On Connected Sublevel Sets in Deep LearningOral121 citations
  288. SWALP : Stochastic Weight Averaging in Low Precision TrainingOral121 citations
  289. Submodular Streaming in All Its Glory: Tight Approximation, Minimum Memory and Low Adaptive ComplexityOral120 citations
  290. Statistics and Samples in Distributional Reinforcement LearningOral119 citations
  291. A Persistent Weisfeiler-Lehman Procedure for Graph ClassificationOral118 citations
  292. Learning to Generalize from Sparse and Underspecified RewardsOral118 citations
  293. Loss Landscapes of Regularized Linear AutoencodersOral118 citations
  294. Temporal Gaussian Mixture Layer for VideosOral116 citations
  295. Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture SearchOral115 citations
  296. Making Deep Q-learning methods robust to time discretizationOral114 citations
  297. Provably Efficient Imitation Learning from Observation AloneOral114 citations
  298. Power k-Means ClusteringOral113 citations
  299. Understanding Geometry of Encoder-Decoder CNNsOral113 citations
  300. Are Generative Classifiers More Robust to Adversarial Attacks?Oral112 citations
  301. Distributional Reinforcement Learning for Efficient ExplorationOral112 citations
  302. CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational NetworkOral111 citations
  303. Stochastic Blockmodels meet Graph Neural NetworksOral111 citations
  304. Understanding and Accelerating Particle-Based Variational InferenceOral111 citations
  305. GEOMetrics: Exploiting Geometric Structure for Graph-Encoded ObjectsOral110 citations
  306. Hybrid Models with Deep and Invertible FeaturesOral110 citations
  307. Maximum Entropy-Regularized Multi-Goal Reinforcement LearningOral110 citations
  308. Global Convergence of Block Coordinate Descent in Deep LearningOral109 citations
  309. Guided evolutionary strategies: augmenting random search with surrogate gradientsOral109 citations
  310. PROVEN: Verifying Robustness of Neural Networks with a Probabilistic ApproachOral109 citations
  311. Probabilistic Neural Symbolic Models for Interpretable Visual Question AnsweringOral109 citations
  312. Variational Inference for sparse network reconstruction from count dataOral109 citations
  313. An Investigation of Model-Free PlanningOral108 citations
  314. Neural Logic Reinforcement LearningOral108 citations
  315. Taming MAML: Efficient unbiased meta-reinforcement learningOral108 citations
  316. Lipschitz Generative Adversarial NetsOral107 citations
  317. Hessian Aided Policy GradientOral106 citations
  318. Toward Understanding the Importance of Noise in Training Neural NetworksOral106 citations
  319. Width Provably Matters in Optimization for Deep Linear Neural NetworksOral106 citations
  320. Differentially Private Empirical Risk Minimization with Non-convex Loss FunctionsOral105 citations
  321. Finding Mixed Nash Equilibria of Generative Adversarial NetworksOral105 citations
  322. Co-Representation Network for Generalized Zero-Shot LearningOral104 citations
  323. Escaping Saddle Points with Adaptive Gradient MethodsOral104 citations
  324. The Implicit Fairness Criterion of Unconstrained LearningOral103 citations
  325. Classification from Positive, Unlabeled and Biased Negative DataOral102 citations
  326. Control Regularization for Reduced Variance Reinforcement LearningOral101 citations
  327. Beating Stochastic and Adversarial Semi-bandits Optimally and SimultaneouslyOral100 citations
  328. Causal Identification under Markov Equivalence: Completeness ResultsOral100 citations
  329. Connectivity-Optimized Representation Learning via Persistent HomologyOral100 citations
  330. DBSCAN++: Towards fast and scalable density clusteringOral100 citations
  331. Equivariant Transformer NetworksOral100 citations
  332. Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR ProblemOral100 citations
  333. Addressing the Loss-Metric Mismatch with Adaptive Loss AlignmentOral99 citations
  334. Adversarial Generation of Time-Frequency Features with application in audio synthesisOral98 citations
  335. Anomaly Detection With Multiple-Hypotheses PredictionsOral96 citations
  336. Understanding Priors in Bayesian Neural Networks at the Unit LevelOral96 citations
  337. LatentGNN: Learning Efficient Non-local Relations for Visual RecognitionOral95 citations
  338. Repairing without Retraining: Avoiding Disparate Impact with Counterfactual DistributionsOral95 citations
  339. Causal Discovery and Forecasting in Nonstationary Environments with State-Space ModelsOral94 citations
  340. Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex OptimizationOral94 citations
  341. Learning deep kernels for exponential family densitiesOral94 citations
  342. Learning interpretable continuous-time models of latent stochastic dynamical systemsOral94 citations
  343. Stable and Fair ClassificationOral94 citations
  344. Bounding User Contributions: A Bias-Variance Trade-off in Differential PrivacyOral93 citations
  345. Neural Collaborative Subspace ClusteringOral93 citations
  346. Empirical Analysis of Beam Search Performance Degradation in Neural Sequence ModelsOral92 citations
  347. A Contrastive Divergence for Combining Variational Inference and MCMCOral91 citations
  348. On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social LearningOral91 citations
  349. SGD without Replacement: Sharper Rates for General Smooth Convex FunctionsOral91 citations
  350. Trading Redundancy for Communication: Speeding up Distributed SGD for Non-convex OptimizationOral90 citations
  351. Generalized No Free Lunch Theorem for Adversarial RobustnessOral89 citations
  352. Multi-objective training of Generative Adversarial Networks with multiple discriminatorsOral89 citations
  353. Cautious Regret Minimization: Online Optimization with Long-Term Budget ConstraintsOral88 citations
  354. Learning a Prior over Intent via Meta-Inverse Reinforcement LearningOral88 citations
  355. Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous DataOral88 citations
  356. Exploiting Worker Correlation for Label Aggregation in CrowdsourcingOral87 citations
  357. Importance Sampling Policy Evaluation with an Estimated Behavior PolicyOral87 citations
  358. Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet HessiansOral87 citations
  359. CAB: Continuous Adaptive Blending for Policy Evaluation and LearningOral86 citations
  360. HyperGAN: A Generative Model for Diverse, Performant Neural NetworksOral86 citations
  361. Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep ModelsOral86 citations
  362. Robust Learning from Untrusted SourcesOral86 citations
  363. Sublinear quantum algorithms for training linear and kernel-based classifiersOral86 citations
  364. Variational Implicit ProcessesOral86 citations
  365. Approximation and non-parametric estimation of ResNet-type convolutional neural networksOral85 citations
  366. Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed BanditsOral85 citations
  367. Generalized Linear Rule ModelsOral85 citations
  368. A Kernel Perspective for Regularizing Deep Neural NetworksOral84 citations
  369. GDPP: Learning Diverse Generations using Determinantal Point ProcessesOral82 citations
  370. On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward InferenceOral81 citations
  371. LIT: Learned Intermediate Representation Training for Model CompressionOral80 citations
  372. Revisiting the Softmax Bellman Operator: New Benefits and New PerspectiveOral80 citations
  373. Learning Dependency Structures for Weak Supervision ModelsOral79 citations
  374. Random Expert Distillation: Imitation Learning via Expert Policy Support EstimationOral79 citations
  375. Adversarially Learned Representations for Information Obfuscation and InferenceOral78 citations
  376. Beyond Backprop: Online Alternating Minimization with Auxiliary VariablesOral78 citations
  377. Distributed Learning over Unreliable NetworksOral78 citations
  378. Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family ApproximationsOral78 citations
  379. Graph Neural Network for Music Score Data and Modeling Expressive Piano PerformanceOral78 citations
  380. Processing Megapixel Images with Deep Attention-Sampling ModelsOral78 citations
  381. Differentiable Linearized ADMMOral77 citations
  382. A Better k-means++ Algorithm via Local SearchOral76 citations
  383. Bilinear Bandits with Low-rank StructureOral76 citations
  384. Traditional and Heavy Tailed Self Regularization in Neural Network ModelsOral76 citations
  385. Alternating Minimizations Converge to Second-Order Optimal SolutionsOral74 citations
  386. Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AIOral72 citations
  387. Sensitivity Analysis of Linear Structural Causal ModelsOral72 citations
  388. Stein Point Markov Chain Monte CarloOral72 citations
  389. Anytime Online-to-Batch, Optimism and AccelerationOral71 citations
  390. Bayesian Optimization Meets Bayesian Optimal StoppingOral71 citations
  391. Gaining Free or Low-Cost Interpretability with Interpretable Partial SubstituteOral71 citations
  392. Learning a Compressed Sensing Measurement Matrix via Gradient UnrollingOral71 citations
  393. Calibrated Model-Based Deep Reinforcement LearningOral70 citations
  394. Efficient Full-Matrix Adaptive RegularizationOral70 citations
  395. Policy Consolidation for Continual Reinforcement LearningOral70 citations
  396. Riemannian adaptive stochastic gradient algorithms on matrix manifoldsOral70 citations
  397. Safe Grid Search with Optimal ComplexityOral70 citations
  398. The Natural Language of ActionsOral70 citations
  399. Autoregressive Energy MachinesOral69 citations
  400. Communication Complexity in Locally Private Distribution Estimation and Heavy HittersOral69 citations
  401. Topological Data Analysis of Decision Boundaries with Application to Model SelectionOral69 citations
  402. Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor ModelsOral67 citations
  403. Switching Linear Dynamics for Variational Bayes FilteringOral65 citations
  404. Asynchronous Batch Bayesian Optimisation with Improved Local PenalisationOral64 citations
  405. Discovering Options for Exploration by Minimizing Cover TimeOral64 citations
  406. Faster Attend-Infer-Repeat with Tractable Probabilistic ModelsOral64 citations
  407. Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning InterpretationOral64 citations
  408. Composing Value Functions in Reinforcement LearningOral63 citations
  409. Conditional Gradient Methods via Stochastic Path-Integrated Differential EstimatorOral63 citations
  410. On the Computation and Communication Complexity of Parallel SGD with Dynamic Batch Sizes for Stochastic Non-Convex OptimizationOral63 citations
  411. On Sparse Linear Regression in the Local Differential Privacy ModelOral62 citations
  412. Open Vocabulary Learning on Source Code with a Graph-Structured CacheOral62 citations
  413. Band-limited Training and Inference for Convolutional Neural NetworksOral61 citations
  414. Toward Controlling Discrimination in Online Ad AuctionsOral61 citations
  415. Deep Gaussian Processes with Importance-Weighted Variational InferenceOral60 citations
  416. Imputing Missing Events in Continuous-Time Event StreamsOral60 citations
  417. An Optimal Private Stochastic-MAB Algorithm based on Optimal Private Stopping RuleOral59 citations
  418. LegoNet: Efficient Convolutional Neural Networks with Lego FiltersOral59 citations
  419. Bias Also Matters: Bias Attribution for Deep Neural Network ExplanationOral58 citations
  420. Curiosity-Bottleneck: Exploration By Distilling Task-Specific NoveltyOral58 citations
  421. HexaGAN: Generative Adversarial Nets for Real World ClassificationOral58 citations
  422. Teaching a black-box learnerOral58 citations
  423. Fault Tolerance in Iterative-Convergent Machine LearningOral57 citations
  424. Hyperbolic Disk Embeddings for Directed Acyclic GraphsOral57 citations
  425. IMEXnet A Forward Stable Deep Neural NetworkOral57 citations
  426. Non-monotone Submodular Maximization with Nearly Optimal Adaptivity and Query ComplexityOral57 citations
  427. The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical StudyOral57 citations
  428. Geometry and Symmetry in Short-and-Sparse DeconvolutionOral56 citations
  429. Improved Parallel Algorithms for Density-Based Network ClusteringOral56 citations
  430. Lower Bounds for Smooth Nonconvex Finite-Sum OptimizationOral56 citations
  431. Blended Conditonal GradientsOral55 citations
  432. Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein DistancesOral54 citations
  433. Deep Generative Learning via Variational Gradient FlowOral54 citations
  434. Homomorphic SensingOral54 citations
  435. Spectral Clustering of Signed Graphs via Matrix Power MeansOral54 citations
  436. Universal Multi-Party Poisoning Attacks54 citations
  437. Optimal Algorithms for Lipschitz Bandits with Heavy-tailed RewardsOral53 citations
  438. Adaptive Regret of Convex and Smooth FunctionsOral51 citations
  439. Linear-Complexity Data-Parallel Earth Mover’s Distance ApproximationsOral51 citations
  440. Maximum Likelihood Estimation for Learning Populations of ParametersOral51 citations
  441. Scalable Nonparametric Sampling from Multimodal Posteriors with the Posterior BootstrapOral51 citations
  442. The Value Function Polytope in Reinforcement LearningOral51 citations
  443. Faster Stochastic Alternating Direction Method of Multipliers for Nonconvex OptimizationOral50 citations
  444. Finding Options that Minimize Planning TimeOral50 citations
  445. Large-Scale Sparse Kernel Canonical Correlation AnalysisOral50 citations
  446. State-Regularized Recurrent Neural NetworksOral50 citations
  447. Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic ConvergenceOral50 citations
  448. Task-Agnostic Dynamics Priors for Deep Reinforcement LearningOral50 citations
  449. Wasserstein of Wasserstein Loss for Learning Generative ModelsOral50 citations
  450. A Conditional-Gradient-Based Augmented Lagrangian FrameworkOral49 citations
  451. Dropout as a Structured Shrinkage PriorOral49 citations
  452. Nonconvex Variance Reduced Optimization with Arbitrary SamplingOral49 citations
  453. Statistical Foundations of Virtual DemocracyOral49 citations
  454. Does Data Augmentation Lead to Positive Margin?Oral48 citations
  455. Learning Discrete and Continuous Factors of Data via Alternating DisentanglementOral48 citations
  456. On the Generalization Gap in Reparameterizable Reinforcement LearningOral48 citations
  457. Rao-Blackwellized Stochastic Gradients for Discrete DistributionsOral48 citations
  458. Rehashing Kernel Evaluation in High DimensionsOral48 citations
  459. An Instability in Variational Inference for Topic ModelsOral47 citations
  460. Concentration Inequalities for Conditional Value at RiskOral47 citations
  461. Optimal Continuous DR-Submodular Maximization and Applications to Provable Mean Field InferenceOral47 citations
  462. Heterogeneous Model Reuse via Optimizing Multiparty Multiclass MarginOral46 citations
  463. Learning from a LearnerOral46 citations
  464. Meta-Learning Neural Bloom FiltersOral46 citations
  465. Optimal Mini-Batch and Step Sizes for SAGAOral46 citations
  466. A fully differentiable beam search decoderOral45 citations
  467. Competing Against Nash Equilibria in Adversarially Changing Zero-Sum GamesOral45 citations
  468. Distributed Learning with Sublinear CommunicationOral45 citations
  469. Learning to Route in Similarity GraphsOral45 citations
  470. Nonparametric Bayesian Deep Networks with Local CompetitionOral45 citations
  471. Overcoming Multi-model ForgettingOral45 citations
  472. Stable-Predictive Optimistic Counterfactual Regret MinimizationOral45 citations
  473. Bayesian Counterfactual Risk MinimizationOral44 citations
  474. Optimistic Policy Optimization via Multiple Importance SamplingOral44 citations
  475. Target-Based Temporal-Difference LearningOral44 citations
  476. A Quantitative Analysis of the Effect of Batch Normalization on Gradient DescentOral43 citations
  477. Bayesian leave-one-out cross-validation for large dataOral43 citations
  478. Context-Aware Zero-Shot Learning for Object RecognitionOral43 citations
  479. Learning Neurosymbolic Generative Models via Program SynthesisOral43 citations
  480. Locally Private Bayesian Inference for Count ModelsOral43 citations
  481. AUCμ: A Performance Metric for Multi-Class Machine Learning ModelsOral42 citations
  482. More Efficient Off-Policy Evaluation through Regularized Targeted LearningOral42 citations
  483. Collective Model Fusion for Multiple Black-Box ExpertsOral41 citations
  484. Graph Convolutional Gaussian ProcessesOral41 citations
  485. Learning to Collaborate in Markov Decision ProcessesOral41 citations
  486. Regret Circuits: Composability of Regret MinimizersOral41 citations
  487. Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit FeedbackOral41 citations
  488. Combining parametric and nonparametric models for off-policy evaluationOral40 citations
  489. Composing Entropic Policies using Divergence CorrectionOral40 citations
  490. Compressing Gradient Optimizers via Count-SketchesOral40 citations
  491. Efficient Dictionary Learning with Gradient DescentOral40 citations
  492. MONK Outlier-Robust Mean Embedding Estimation by Median-of-MeansOral40 citations
  493. Making Decisions that Reduce Discriminatory ImpactsOral40 citations
  494. Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian ComputationOral40 citations
  495. Uniform Convergence Rate of the Kernel Density Estimator Adaptive to Intrinsic Volume DimensionOral40 citations
  496. Neural Inverse Knitting: From Images to Manufacturing InstructionsOral39 citations
  497. Online Learning to Rank with FeaturesOral39 citations
  498. Active Learning for Decision-Making from Imbalanced Observational DataOral38 citations
  499. Adaptive Scale-Invariant Online Algorithms for Learning Linear ModelsOral38 citations
  500. Dimensionality Reduction for Tukey RegressionOral38 citations
  501. Overcoming Mean-Field Approximations in Recurrent Gaussian Process ModelsOral38 citations
  502. Quantile Stein Variational Gradient Descent for Batch Bayesian OptimizationOral38 citations
  503. Submodular Cost Submodular Cover with an Approximate OracleOral38 citations
  504. The advantages of multiple classes for reducing overfitting from test set reuseOral38 citations
  505. A Composite Randomized Incremental Gradient MethodOral37 citations
  506. A Personalized Affective Memory Model for Improving Emotion RecognitionOral37 citations
  507. Benefits and Pitfalls of the Exponential Mechanism with Applications to Hilbert Spaces and Functional PCAOral37 citations
  508. Rate Distortion For Model Compression:From Theory To PracticeOral37 citations
  509. ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical VariablesOral36 citations
  510. Bayesian Joint Spike-and-Slab Graphical LassoOral36 citations
  511. Faster Algorithms for Binary Matrix FactorizationOral36 citations
  512. Ladder Capsule NetworkOral36 citations
  513. Learning Novel Policies For TasksOral36 citations
  514. Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex OptimizationOral36 citations
  515. On the Design of Estimators for Bandit Off-Policy EvaluationOral36 citations
  516. Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement LearningOral36 citations
  517. Transfer of Samples in Policy Search via Multiple Importance SamplingOral36 citations
  518. Understanding and Controlling Memory in Recurrent Neural NetworksOral36 citations
  519. Accelerated Flow for Probability DistributionsOral35 citations
  520. Coresets for Ordered Weighted ClusteringOral35 citations
  521. Learning to bid in revenue-maximizing auctionsOral35 citations
  522. Memory-Optimal Direct Convolutions for Maximizing Classification Accuracy in Embedded ApplicationsOral35 citations
  523. CoT: Cooperative Training for Generative Modeling of Discrete DataOral34 citations
  524. Discovering Context Effects from Raw Choice DataOral34 citations
  525. On Dropout and Nuclear Norm RegularizationOral34 citations
  526. A Statistical Investigation of Long Memory in Language and MusicOral33 citations
  527. Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient AlgorithmsOral33 citations
  528. Good Initializations of Variational Bayes for Deep ModelsOral33 citations
  529. On Scalable and Efficient Computation of Large Scale Optimal TransportOral33 citations
  530. Supervised Hierarchical Clustering with Exponential LinkageOral33 citations
  531. Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and ApplicationsOral32 citations
  532. Fast Rates for a kNN Classifier Robust to Unknown Asymmetric Label NoiseOral32 citations
  533. Incremental Randomized Sketching for Online Kernel LearningOral32 citations
  534. Kernel-Based Reinforcement Learning in Robust Markov Decision ProcessesOral32 citations
  535. The Kernel Interaction Trick: Fast Bayesian Discovery of Pairwise Interactions in High DimensionsOral32 citations
  536. Unifying Orthogonal Monte Carlo MethodsOral32 citations
  537. Variational Laplace AutoencodersOral32 citations
  538. A Tree-Based Method for Fast Repeated Sampling of Determinantal Point ProcessesOral31 citations
  539. Area AttentionOral31 citations
  540. Nonlinear Stein Variational Gradient Descent for Learning Diversified Mixture ModelsOral31 citations
  541. On the statistical rate of nonlinear recovery in generative models with heavy-tailed dataOral31 citations
  542. Trimming the $\ell_1$ Regularizer: Statistical Analysis, Optimization, and Applications to Deep LearningOral31 citations
  543. Active Embedding Search via Noisy Paired ComparisonsOral30 citations
  544. Decentralized Exploration in Multi-Armed BanditsOral30 citations
  545. Detecting Overlapping and Correlated Communities without Pure Nodes: Identifiability and AlgorithmOral30 citations
  546. Efficient On-Device Models using Neural ProjectionsOral30 citations
  547. Estimate Sequences for Variance-Reduced Stochastic Composite OptimizationOral30 citations
  548. Improved Convergence for $\ell_1$ and $\ell_∞$ Regression via Iteratively Reweighted Least SquaresOral30 citations
  549. PAC Identification of Many Good Arms in Stochastic Multi-Armed BanditsOral30 citations
  550. Scalable Metropolis-Hastings for Exact Bayesian Inference with Large DatasetsOral30 citations
  551. Screening rules for Lasso with non-convex Sparse RegularizersOral30 citations
  552. Stochastic Deep NetworksOral30 citations
  553. Mallows ranking models: maximum likelihood estimate and regenerationOral29 citations
  554. Myopic Posterior Sampling for Adaptive Goal Oriented Design of ExperimentsOral29 citations
  555. On discriminative learning of prediction uncertaintyOral29 citations
  556. Optimal Kronecker-Sum Approximation of Real Time Recurrent LearningOral29 citations
  557. Recursive Sketches for Modular Deep LearningOral29 citations
  558. Revisiting precision recall definition for generative modelingOral29 citations
  559. Separating value functions across time-scalesOral29 citations
  560. Submodular Observation Selection and Information Gathering for Quadratic ModelsOral29 citations
  561. Active Learning with Disagreement GraphsOral28 citations
  562. Active Manifolds: A non-linear analogue to Active SubspacesOral28 citations
  563. Cross-Domain 3D Equivariant Image EmbeddingsOral28 citations
  564. Differentiable Dynamic Normalization for Learning Deep RepresentationOral28 citations
  565. Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement LearningOral28 citations
  566. Efficient optimization of loops and limits with randomized telescoping sumsOral28 citations
  567. Learning Hawkes Processes Under Synchronization NoiseOral28 citations
  568. Neural Separation of Observed and Unobserved DistributionsOral28 citations
  569. SAGA with Arbitrary SamplingOral28 citations
  570. Scalable Learning in Reproducing Kernel Krein SpacesOral28 citations
  571. Almost surely constrained convex optimizationOral27 citations
  572. CapsAndRuns: An Improved Method for Approximately Optimal Algorithm ConfigurationOral27 citations
  573. Efficient Amortised Bayesian Inference for Hierarchical and Nonlinear Dynamical SystemsOral27 citations
  574. Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANsOral27 citations
  575. Fingerprint Policy Optimisation for Robust Reinforcement LearningOral27 citations
  576. Iterative Linearized Control: Stable Algorithms and Complexity GuaranteesOral27 citations
  577. Multi-Frequency Phase SynchronizationOral27 citations
  578. Sublinear Space Private Algorithms Under the Sliding Window ModelOral27 citations
  579. Tensor Variable Elimination for Plated Factor GraphsOral27 citations
  580. Adaptive Monte Carlo Multiple Testing via Multi-Armed BanditsOral26 citations
  581. Approximating Orthogonal Matrices with Effective Givens FactorizationOral26 citations
  582. Beyond Adaptive Submodularity: Approximation Guarantees of Greedy Policy with Adaptive Submodularity RatioOral26 citations
  583. Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal IterationsOral26 citations
  584. Formal Privacy for Functional Data with Gaussian PerturbationsOral26 citations
  585. Predictor-Corrector Policy OptimizationOral26 citations
  586. Understanding MCMC Dynamics as Flows on the Wasserstein SpaceOral26 citations
  587. Dead-ends and Secure Exploration in Reinforcement LearningOral25 citations
  588. Demystifying DropoutOral25 citations
  589. Hierarchical Importance Weighted AutoencodersOral25 citations
  590. On Certifying Non-Uniform Bounds against Adversarial AttacksOral25 citations
  591. Online learning with kernel lossesOral25 citations
  592. PA-GD: On the Convergence of Perturbed Alternating Gradient Descent to Second-Order Stationary Points for Structured Nonconvex OptimizationOral25 citations
  593. Shape Constraints for Set FunctionsOral25 citations
  594. Adversarial Online Learning with noiseOral24 citations
  595. Better generalization with less data using robust gradient descentOral24 citations
  596. Game Theoretic Optimization via Gradient-based Nikaido-Isoda FunctionOral24 citations
  597. Hiring Under UncertaintyOral24 citations
  598. Noisy Dual Principal Component PursuitOral24 citations
  599. Sublinear Time Nearest Neighbor Search over Generalized Weighted SpaceOral24 citations
  600. Adaptive Antithetic Sampling for Variance ReductionOral23 citations
  601. Categorical Feature Compression via Submodular OptimizationOral23 citations
  602. Composable Core-sets for Determinant Maximization: A Simple Near-Optimal AlgorithmOral23 citations
  603. Correlated Variational Auto-EncodersOral23 citations
  604. Functional Transparency for Structured Data: a Game-Theoretic ApproachOral23 citations
  605. Generalized Majorization-MinimizationOral23 citations
  606. Generative Modeling of Infinite Occluded Objects for Compositional Scene RepresentationOral23 citations
  607. Phaseless PCA: Low-Rank Matrix Recovery from Column-wise Phaseless MeasurementsOral23 citations
  608. Simple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized OptimizationOral23 citations
  609. Variational Annealing of GANs: A Langevin PerspectiveOral23 citations
  610. DeepNose: Using artificial neural networks to represent the space of odorantsOral22 citations
  611. Dynamic Measurement Scheduling for Event Forecasting using Deep RLOral22 citations
  612. Geometric Losses for Distributional LearningOral22 citations
  613. Jumpout : Improved Dropout for Deep Neural Networks with ReLUsOral22 citations
  614. Learning Context-dependent Label Permutations for Multi-label ClassificationOral22 citations
  615. Nearest Neighbor and Kernel Survival Analysis: Nonasymptotic Error Bounds and Strong Consistency RatesOral22 citations
  616. Robust Influence Maximization for Hyperparametric ModelsOral22 citations
  617. Distributional Multivariate Policy Evaluation and Exploration with the Bellman GANOral21 citations
  618. Exploiting structure of uncertainty for efficient matroid semi-banditsOral21 citations
  619. Learning to Convolve: A Generalized Weight-Tying ApproachOral21 citations
  620. Metric-Optimized Example WeightsOral21 citations
  621. Monge blunts Bayes: Hardness Results for Adversarial TrainingOral21 citations
  622. Natural Analysts in Adaptive Data AnalysisOral21 citations
  623. Neuron birth-death dynamics accelerates gradient descent and converges asymptoticallyOral21 citations
  624. Variational Russian Roulette for Deep Bayesian NonparametricsOral21 citations
  625. A Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein MinimizationOral20 citations
  626. Adaptive Sensor Placement for Continuous SpacesOral20 citations
  627. Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearitiesOral20 citations
  628. Classifying Treatment Responders Under Causal Effect MonotonicityOral20 citations
  629. Multiplicative Weights Updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost alwaysOral20 citations
  630. Online Learning with Sleeping Experts and Feedback GraphsOral20 citations
  631. Scalable Training of Inference Networks for Gaussian-Process ModelsOral20 citations
  632. A Recurrent Neural Cascade-based Model for Continuous-Time DiffusionOral19 citations
  633. Co-manifold learning with missing dataOral19 citations
  634. Compressed Factorization: Fast and Accurate Low-Rank Factorization of Compressively-Sensed DataOral19 citations
  635. Dual Entangled Polynomial Code: Three-Dimensional Coding for Distributed Matrix MultiplicationOral19 citations
  636. Exploration Conscious Reinforcement Learning RevisitedOral19 citations
  637. Learning Distance for Sequences by Learning a Ground MetricOral19 citations
  638. Multi-Frequency Vector Diffusion MapsOral19 citations
  639. Nonlinear Distributional Gradient Temporal-Difference LearningOral19 citations
  640. Refined Complexity of PCA with OutliersOral19 citations
  641. Reinforcement Learning in Configurable Continuous EnvironmentsOral19 citations
  642. Weak Detection of Signal in the Spiked Wigner ModelOral19 citations
  643. Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable CaseOral18 citations
  644. Contextual Multi-armed Bandit Algorithm for Semiparametric Reward ModelOral18 citations
  645. Convolutional Poisson Gamma Belief NetworkOral18 citations
  646. Discovering Conditionally Salient Features with Statistical GuaranteesOral18 citations
  647. Doubly-Competitive Distribution EstimationOral18 citations
  648. Geometry Aware Convolutional Filters for Omnidirectional Images RepresentationOral18 citations
  649. Greedy Orthogonal Pivoting Algorithm for Non-Negative Matrix FactorizationOral18 citations
  650. Learning Models from Data with Measurement Error: Tackling UnderreportingOral18 citations
  651. Projection onto Minkowski Sums with Application to Constrained LearningOral18 citations
  652. Random Matrix Improved Covariance Estimation for a Large Class of MetricsOral18 citations
  653. Voronoi Boundary Classification: A High-Dimensional Geometric Approach via Weighted Monte Carlo IntegrationOral18 citations
  654. A Polynomial Time MCMC Method for Sampling from Continuous Determinantal Point ProcessesOral17 citations
  655. Beyond the Chinese Restaurant and Pitman-Yor processes: Statistical Models with double power-law behaviorOral17 citations
  656. Discovering Latent Covariance Structures for Multiple Time SeriesOral17 citations
  657. Learning and Data Selection in Big DatasetsOral17 citations
  658. Matrix-Free Preconditioning in Online LearningOral17 citations
  659. Moment-Based Variational Inference for Markov Jump ProcessesOral17 citations
  660. Non-Parametric Priors For Generative Adversarial NetworksOral17 citations
  661. Projections for Approximate Policy Iteration AlgorithmsOral17 citations
  662. Static Automatic Batching In TensorFlowOral17 citations
  663. Weakly-Supervised Temporal Localization via Occurrence Count LearningOral17 citations
  664. When Samples Are Strategically SelectedOral17 citations
  665. A Multitask Multiple Kernel Learning Algorithm for Survival Analysis with Application to Cancer BiologyOral16 citations
  666. Automated Model Selection with Bayesian QuadratureOral16 citations
  667. Characterizing Well-Behaved vs. Pathological Deep Neural NetworksOral16 citations
  668. Distributed, Egocentric Representations of Graphs for Detecting Critical StructuresOral16 citations
  669. Fast and Flexible Inference of Joint Distributions from their MarginalsOral16 citations
  670. Hierarchical Decompositional Mixtures of Variational AutoencodersOral16 citations
  671. Humor in Word Embeddings: Cockamamie Gobbledegook for NincompoopsOral16 citations
  672. On Medians of (Randomized) Pairwise MeansOral16 citations
  673. Online Variance Reduction with MixturesOral16 citations
  674. Training CNNs with Selective Allocation of ChannelsOral16 citations
  675. Boosted Density Estimation RemasteredOral15 citations
  676. GOODE: A Gaussian Off-The-Shelf Ordinary Differential Equation SolverOral15 citations
  677. Graph Resistance and Learning from Pairwise ComparisonsOral15 citations
  678. Learning Classifiers for Target Domain with Limited or No LabelsOral15 citations
  679. Learning from Delayed Outcomes via Proxies with Applications to Recommender SystemsOral15 citations
  680. Leveraging Low-Rank Relations Between Surrogate Tasks in Structured PredictionOral15 citations
  681. Minimal Achievable Sufficient Statistic LearningOral15 citations
  682. A Baseline for Any Order Gradient Estimation in Stochastic Computation GraphsOral14 citations
  683. AReS and MaRS Adversarial and MMD-Minimizing Regression for SDEsOral14 citations
  684. Contextual Memory TreesOral14 citations
  685. Decomposing feature-level variation with Covariate Gaussian Process Latent Variable ModelsOral14 citations
  686. LR-GLM: High-Dimensional Bayesian Inference Using Low-Rank Data ApproximationsOral14 citations
  687. Partially Linear Additive Gaussian Graphical ModelsOral14 citations
  688. RaFM: Rank-Aware Factorization MachinesOral14 citations
  689. Rotation Invariant Householder Parameterization for Bayesian PCAOral14 citations
  690. Sparse Extreme Multi-label Learning with Oracle PropertyOral14 citations
  691. Target Tracking for Contextual Bandits: Application to Demand Side ManagementOral14 citations
  692. Generalized Approximate Survey Propagation for High-Dimensional EstimationOral13 citations
  693. Look Ma, No Latent Variables: Accurate Cutset Networks via CompilationOral13 citations
  694. Particle Flow Bayes’ RuleOral13 citations
  695. Robust Estimation of Tree Structured Gaussian Graphical ModelsOral13 citations
  696. The information-theoretic value of unlabeled data in semi-supervised learningOral13 citations
  697. Improving Model Selection by Employing the Test DataOral12 citations
  698. Incorporating Grouping Information into Bayesian Decision Tree EnsemblesOral12 citations
  699. Kernel Mean Matching for Content Addressability of GANsOral12 citations
  700. PAC Learnability of Node Functions in Networked Dynamical SystemsOral12 citations
  701. Scaling Up Ordinal Embedding: A Landmark ApproachOral12 citations
  702. Sequential Facility Location: Approximate Submodularity and Greedy AlgorithmOral12 citations
  703. Acceleration of SVRG and Katyusha X by Inexact PreconditioningOral11 citations
  704. Differential Inclusions for Modeling Nonsmooth ADMM Variants: A Continuous Limit TheoryOral11 citations
  705. Multivariate Submodular OptimizationOral11 citations
  706. Neurally-Guided Structure InferenceOral11 citations
  707. Stochastic Iterative Hard Thresholding for Graph-structured Sparsity OptimizationOral11 citations
  708. The Wasserstein TransformOral11 citations
  709. Adjustment Criteria for Generalizing Experimental FindingsOral10 citations
  710. Bayesian Deconditional Kernel Mean EmbeddingsOral10 citations
  711. End-to-End Probabilistic Inference for Nonstationary Audio AnalysisOral10 citations
  712. Feature Grouping as a Stochastic Regularizer for High-Dimensional Structured DataOral10 citations
  713. Lossless or Quantized Boosting with Integer ArithmeticOral10 citations
  714. New results on information theoretic clusteringOral10 citations
  715. Regularization in directable environments with application to TetrisOral10 citations
  716. kernelPSI: a Post-Selection Inference Framework for Nonlinear Variable SelectionOral10 citations
  717. Amortized Monte Carlo IntegrationOral9 citations
  718. Calibrated Approximate Bayesian InferenceOral9 citations
  719. Conditional Independence in Testing Bayesian NetworksOral9 citations
  720. Discriminative Regularization for Latent Variable Models with Applications to ElectrocardiographyOral9 citations
  721. Invariant-Equivariant Representation Learning for Multi-Class DataOral9 citations
  722. Per-Decision Option DiscountingOral9 citations
  723. Active Learning for Probabilistic Structured Prediction of Cuts and MatchingsOral8 citations
  724. Deep Residual Output Layers for Neural Language GenerationOral8 citations
  725. Differentially Private Learning of Geometric ConceptsOral8 citations
  726. Fast Direct Search in an Optimally Compressed Continuous Target Space for Efficient Multi-Label Active LearningOral8 citations
  727. Inferring Heterogeneous Causal Effects in Presence of Spatial ConfoundingOral8 citations
  728. Online Adaptive Principal Component Analysis and Its extensionsOral8 citations
  729. Optimal Minimal Margin Maximization with BoostingOral8 citations
  730. Phase transition in PCA with missing data: Reduced signal-to-noise ratio, not sample size!Oral8 citations
  731. The Variational Predictive Natural GradientOral8 citations
  732. Breaking Inter-Layer Co-Adaptation by Classifier AnonymizationOral7 citations
  733. Characterization of Convex Objective Functions and Optimal Expected Convergence Rates for SGDOral7 citations
  734. Communication-Constrained Inference and the Role of Shared RandomnessOral7 citations
  735. Distributed Weighted Matching via Randomized Composable CoresetsOral7 citations
  736. Kernel Normalized Cut: a Theoretical RevisitOral7 citations
  737. Learning to select for a predefined rankingOral7 citations
  738. Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution MatchingOral7 citations
  739. Scale-free adaptive planning for deterministic dynamics & discounted rewardsOral7 citations
  740. Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex OptimizationOral7 citations
  741. Trajectory-Based Off-Policy Deep Reinforcement LearningOral7 citations
  742. Dirichlet Simplex Nest and Geometric InferenceOral6 citations
  743. Learning Optimal Linear RegularizersOral6 citations
  744. Model Function Based Conditional Gradient Method with Armijo-like Line SearchOral6 citations
  745. State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden RepresentationsOral6 citations
  746. Correlated bandits or: How to minimize mean-squared error onlineOral5 citations
  747. DP-GP-LVM: A Bayesian Non-Parametric Model for Learning Multivariate Dependency StructuresOral5 citations
  748. Flat Metric Minimization with Applications in Generative ModelingOral5 citations
  749. Improved Dynamic Graph Learning through Fault-Tolerant SparsificationOral5 citations
  750. Inference and Sampling of $K_33$-free Ising ModelsOral5 citations
  751. Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With RenegingOral5 citations
  752. Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel $k$-means ClusteringOral5 citations
  753. A Block Coordinate Descent Proximal Method for Simultaneous Filtering and Parameter EstimationOral4 citations
  754. Fast Algorithm for Generalized Multinomial Models with Ranking DataOral4 citations
  755. Katalyst: Boosting Convex Katayusha for Non-Convex Problems with a Large Condition NumberOral4 citations
  756. Learning Structured Decision Problems with UnawarenessOral4 citations
  757. Pareto Optimal Streaming Unsupervised ClassificationOral4 citations
  758. Predicate Exchange: Inference with Declarative KnowledgeOral4 citations
  759. Spectral Approximate InferenceOral4 citations
  760. Efficient learning of smooth probability functions from Bernoulli tests with guaranteesOral3 citations
  761. Random Function Priors for Correlation ModelingOral3 citations
  762. Replica Conditional Sequential Monte CarloOral3 citations
  763. Self-similar Epochs: Value in arrangementOral3 citations
  764. Trainable Decoding of Sets of Sequences for Neural Sequence ModelsOral3 citations
  765. Automatic Classifiers as Scientific Instruments: One Step Further Away from Ground-TruthOral2 citations
  766. Dynamic Learning with Frequent New Product Launches: A Sequential Multinomial Logit Bandit ProblemOral2 citations
  767. TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement LearningOral2 citations
  768. Model Comparison for Semantic GroupingOral1 citations
  769. Optimality Implies Kernel Sum Classifiers are Statistically EfficientOral1 citations
  770. Curvature-Exploiting Acceleration of Elastic Net ComputationsOral
  771. Fast and Stable Maximum Likelihood Estimation for Incomplete Multinomial ModelsOral
  772. First-Order Algorithms Converge Faster than $O(1/k)$ on Convex ProblemsOral
  773. Learning to Clear the MarketOral

ICML accepted papers in other years

ICML 2026 (6,634)ICML 2025 (3,333)ICML 2024 (2,610)ICML 2023 (1,828)ICML 2022 (1,228)ICML 2021 (1,181)ICML 2020 (1,082)ICML 2018 (620)ICML 2017 (433)ICML 2016 (322)ICML 2015 (270)

Looking for submission deadlines instead? See the conference deadline calendar.