ICML 2021 Accepted Papers

The full list of 1,181 papers accepted at ICML 2021 (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.

1. Learning Transferable Visual Models From Natural Language SupervisionOral35,305 citations
2. Training data-efficient image transformers & distillation through attentionSpotlight8,716 citations
3. Zero-Shot Text-to-Image GenerationSpotlight6,333 citations
4. Scaling Up Visual and Vision-Language Representation Learning With Noisy Text SupervisionOral4,467 citations
5. Improved Denoising Diffusion Probabilistic ModelsSpotlight4,295 citations
6. EfficientNetV2: Smaller Models and Faster TrainingSpotlight4,128 citations
7. Barlow Twins: Self-Supervised Learning via Redundancy ReductionSpotlight2,939 citations
8. Is Space-Time Attention All You Need for Video Understanding?Spotlight2,678 citations
9. ViLT: Vision-and-Language Transformer Without Convolution or Region SupervisionOral2,071 citations
10. WILDS: A Benchmark of in-the-Wild Distribution ShiftsOral1,715 citations
11. SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural NetworksSpotlight1,685 citations
12. Calibrate Before Use: Improving Few-shot Performance of Language ModelsOral1,480 citations
13. E(n) Equivariant Graph Neural NetworksSpotlight1,237 citations
14. Perceiver: General Perception with Iterative AttentionSpotlight1,234 citations
15. Ditto: Fair and Robust Federated Learning Through PersonalizationSpotlight1,178 citations
16. Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-SpeechSpotlight1,105 citations
17. Out-of-Distribution Generalization via Risk Extrapolation (REx)Oral1,103 citations
18. ConViT: Improving Vision Transformers with Soft Convolutional Inductive BiasesSpotlight1,025 citations
19. Exploiting Shared Representations for Personalized Federated LearningSpotlight966 citations
20. Data-Free Knowledge Distillation for Heterogeneous Federated LearningSpotlight888 citations
21. MSA TransformerSpotlight754 citations
22. Equivariant message passing for the prediction of tensorial properties and molecular spectraSpotlight724 citations
23. High-Performance Large-Scale Image Recognition Without NormalizationSpotlight668 citations
24. Grad-TTS: A Diffusion Probabilistic Model for Text-to-SpeechSpotlight635 citations
25. Just Train Twice: Improving Group Robustness without Training Group InformationOral630 citations
26. Label-Only Membership Inference AttacksSpotlight620 citations
27. Graph Contrastive Learning AutomatedOral612 citations
28. Unifying Vision-and-Language Tasks via Text GenerationSpotlight601 citations
29. Rethinking Rotated Object Detection with Gaussian Wasserstein Distance LossSpotlight560 citations
30. Neural Architecture Search without TrainingOral538 citations
31. On Explainability of Graph Neural Networks via Subgraph ExplorationsSpotlight523 citations
32. What Are Bayesian Neural Network Posteriors Really Like?Oral515 citations
33. Is Pessimism Provably Efficient for Offline RL?Spotlight499 citations
34. Towards Understanding and Mitigating Social Biases in Language ModelsSpotlight490 citations
35. Attention is not all you need: pure attention loses rank doubly exponentially with depthOral475 citations
36. Environment Inference for Invariant LearningSpotlight460 citations
37. Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series ForecastingSpotlight439 citations
38. I-BERT: Integer-only BERT QuantizationOral429 citations
39. Synthesizer: Rethinking Self-Attention for Transformer ModelsSpotlight426 citations
40. Personalized Federated Learning using HypernetworksSpotlight421 citations
41. Delving into Deep Imbalanced RegressionOral415 citations
42. Decoupling Representation Learning from Reinforcement LearningSpotlight403 citations
43. ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural NetworksSpotlight385 citations
44. Whitening for Self-Supervised Representation LearningSpotlight378 citations
45. Domain Generalization using Causal MatchingOral377 citations
46. Dataset Condensation with Differentiable Siamese AugmentationSpotlight375 citations
47. Offline Reinforcement Learning with Fisher Divergence Critic RegularizationSpotlight364 citations
48. GRAND: Graph Neural DiffusionSpotlight352 citations
49. Understanding self-supervised learning dynamics without contrastive pairsOral349 citations
50. PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-trainingOral343 citations
51. Weisfeiler and Lehman Go Topological: Message Passing Simplicial NetworksSpotlight342 citations
52. Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution GeneralizationSpotlight333 citations
53. Dash: Semi-Supervised Learning with Dynamic ThresholdingOral314 citations
54. HAWQ-V3: Dyadic Neural Network QuantizationSpotlight309 citations
55. Training Graph Neural Networks with 1000 LayersSpotlight308 citations
56. Bilevel Optimization: Convergence Analysis and Enhanced DesignSpotlight299 citations
57. Revisiting Point Cloud Shape Classification with a Simple and Effective BaselineSpotlight295 citations
58. BASE Layers: Simplifying Training of Large, Sparse ModelsSpotlight293 citations
59. The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure AggregationSpotlight288 citations
60. SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement LearningSpotlight284 citations
61. Reinforcement Learning with Prototypical RepresentationsSpotlight279 citations
62. Memory-Efficient Pipeline-Parallel DNN TrainingSpotlight274 citations
63. Contrastive Learning Inverts the Data Generating ProcessSpotlight269 citations
64. Self-supervised Graph-level Representation Learning with Local and Global StructureSpotlight268 citations
65. GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model TrainingSpotlight267 citations
66. Linear Transformers Are Secretly Fast Weight ProgrammersSpotlight265 citations
67. Federated Continual Learning with Weighted Inter-client TransferSpotlight262 citations
68. Tensor Programs IV: Feature Learning in Infinite-Width Neural NetworksSpotlight261 citations
69. Learning Gradient Fields for Molecular Conformation GenerationOral258 citations
70. Bilinear Classes: A Structural Framework for Provable Generalization in RLOral256 citations
71. Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated LearningSpotlight255 citations
72. CRFL: Certifiably Robust Federated Learning against Backdoor AttacksSpotlight243 citations
73. Multi-Task Reinforcement Learning with Context-based RepresentationsSpotlight242 citations
74. Generative Adversarial TransformersSpotlight240 citations
75. Learning from History for Byzantine Robust OptimizationSpotlight240 citations
76. A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks CalibrationSpotlight235 citations
77. Descending through a Crowded Valley - Benchmarking Deep Learning OptimizersSpotlight232 citations
78. Neural Symbolic Regression that scalesSpotlight232 citations
79. LogME: Practical Assessment of Pre-trained Models for Transfer LearningSpotlight231 citations
80. Provable Meta-Learning of Linear RepresentationsSpotlight231 citations
81. GraphNorm: A Principled Approach to Accelerating Graph Neural Network TrainingSpotlight230 citations
82. GraphDF: A Discrete Flow Model for Molecular Graph GenerationSpotlight229 citations
83. A Unified Lottery Ticket Hypothesis for Graph Neural NetworksSpotlight227 citations
84. Practical and Private (Deep) Learning Without Sampling or ShufflingSpotlight226 citations
85. Directional Graph NetworksOral225 citations
86. To be Robust or to be Fair: Towards Fairness in Adversarial TrainingSpotlight225 citations
87. Uncertainty Weighted Actor-Critic for Offline Reinforcement LearningSpotlight224 citations
88. CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and PatientsSpotlight222 citations
89. Generative Causal Explanations for Graph Neural NetworksSpotlight221 citations
90. Generating images with sparse representationsOral219 citations
91. A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix GroupsOral217 citations
92. Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning AttacksSpotlight214 citations
93. Phasic Policy GradientOral214 citations
94. Accurate Post Training Quantization With Small Calibration SetsSpotlight212 citations
95. Machine Unlearning for Random ForestsSpotlight207 citations
96. Adversarial Purification with Score-based Generative ModelsSpotlight202 citations
97. Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech GenerationSpotlight202 citations
98. GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical EmbeddingsSpotlight201 citations
99. Neural SDEs as Infinite-Dimensional GANsSpotlight201 citations
100. Group Fisher Pruning for Practical Network CompressionSpotlight200 citations
101. Heterogeneity for the Win: One-Shot Federated ClusteringSpotlight199 citations
102. The Lipschitz Constant of Self-AttentionSpotlight196 citations
103. Prioritized Level ReplaySpotlight194 citations
104. SPECTRE: defending against backdoor attacks using robust statistics187 citations
105. Neural Transformation Learning for Deep Anomaly Detection Beyond ImagesSpotlight186 citations
106. Neural-Pull: Learning Signed Distance Function from Point clouds by Learning to Pull Space onto SurfaceSpotlight184 citations
107. Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series ForecastingSpotlight183 citations
108. Unbalanced minibatch Optimal Transport; applications to Domain AdaptationSpotlight182 citations
109. Dissecting Supervised Contrastive LearningOral181 citations
110. Neural Rough Differential Equations for Long Time SeriesSpotlight178 citations
111. State Entropy Maximization with Random Encoders for Efficient ExplorationSpotlight177 citations
112. Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic SkillsSpotlight171 citations
113. Goal-Conditioned Reinforcement Learning with Imagined SubgoalsSpotlight170 citations
114. Heterogeneous Risk MinimizationSpotlight170 citations
115. Toward Understanding the Feature Learning Process of Self-supervised Contrastive LearningSpotlight170 citations
116. A Sharp Analysis of Model-based Reinforcement Learning with Self-PlaySpotlight169 citations
117. CRPO: A New Approach for Safe Reinforcement Learning with Convergence GuaranteeSpotlight169 citations
118. Globally-Robust Neural NetworksSpotlight169 citations
119. Improved Contrastive Divergence Training of Energy-Based ModelsSpotlight169 citations
120. Voice2Series: Reprogramming Acoustic Models for Time Series ClassificationSpotlight169 citations
121. APS: Active Pretraining with Successor FeaturesOral168 citations
122. Breaking the Limits of Message Passing Graph Neural NetworksSpotlight168 citations
123. Scaling Multi-Agent Reinforcement Learning with Selective Parameter SharingSpotlight168 citations
124. Conformal prediction interval for dynamic time-seriesOral167 citations
125. DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement LearningSpotlight167 citations
126. TFix: Learning to Fix Coding Errors with a Text-to-Text TransformerSpotlight166 citations
127. Provably End-to-end Label-noise Learning without Anchor PointsSpotlight165 citations
128. The Heavy-Tail Phenomenon in SGDSpotlight164 citations
129. From Local Structures to Size Generalization in Graph Neural NetworksSpotlight161 citations
130. PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex OptimizationOral160 citations
131. Thinking Like TransformersSpotlight160 citations
132. Elastic Graph Neural NetworksOral156 citations
133. Provably Efficient Reinforcement Learning for Discounted MDPs with Feature MappingSpotlight154 citations
134. NeRF-VAE: A Geometry Aware 3D Scene Generative ModelOral153 citations
135. Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse TrainingSpotlight152 citations
136. Towards Domain-Agnostic Contrastive LearningSpotlight149 citations
137. Break-It-Fix-It: Unsupervised Learning for Program RepairOral145 citations
138. MARINA: Faster Non-Convex Distributed Learning with CompressionSpotlight145 citations
139. EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RLSpotlight144 citations
140. Representation Matters: Offline Pretraining for Sequential Decision MakingSpotlight144 citations
141. UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled DataSpotlight144 citations
142. On Disentangled Representations Learned from Correlated DataOral142 citations
143. ProGraML: A Graph-based Program Representation for Data Flow Analysis and Compiler OptimizationsSpotlight142 citations
144. Batch Value-function Approximation with Only RealizabilitySpotlight141 citations
145. PACOH: Bayes-Optimal Meta-Learning with PAC-GuaranteesSpotlight141 citations
146. Backdoor Scanning for Deep Neural Networks through K-Arm OptimizationSpotlight139 citations
147. Few-Shot Neural Architecture SearchOral138 citations
148. Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient NormOral137 citations
149. Confidence Scores Make Instance-dependent Label-noise Learning PossibleOral137 citations
150. Cooperative Exploration for Multi-Agent Deep Reinforcement LearningOral137 citations
151. Scalable Marginal Likelihood Estimation for Model Selection in Deep LearningSpotlight136 citations
152. Discovering symbolic policies with deep reinforcement learningSpotlight135 citations
153. KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge DistillationSpotlight135 citations
154. Offline Meta-Reinforcement Learning with Advantage WeightingSpotlight135 citations
155. Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning researchSpotlight134 citations
156. Size-Invariant Graph Representations for Graph Classification ExtrapolationsOral132 citations
157. Trajectory Diversity for Zero-Shot CoordinationSpotlight131 citations
158. Deep Generative Learning via Schrödinger BridgeSpotlight130 citations
159. Leveraged Weighted Loss for Partial Label LearningOral130 citations
160. OptiDICE: Offline Policy Optimization via Stationary Distribution Correction EstimationSpotlight129 citations
161. Path Planning using Neural A* SearchSpotlight129 citations
162. RRL: Resnet as representation for Reinforcement LearningSpotlight129 citations
163. TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language ModelsSpotlight128 citations
164. Understanding Failures in Out-of-Distribution Detection with Deep Generative ModelsSpotlight128 citations
165. Bayesian Deep Learning via Subnetwork InferenceSpotlight127 citations
166. One Pass Late Fusion Multi-view ClusteringSpotlight127 citations
167. Outside the Echo Chamber: Optimizing the Performative RiskSpotlight125 citations
168. Sharf: Shape-conditioned Radiance Fields from a Single ViewSpotlight124 citations
169. Representation Subspace Distance for Domain Adaptation RegressionSpotlight122 citations
170. Decoupling Value and Policy for Generalization in Reinforcement LearningOral120 citations
171. Simple and Effective VAE Training with Calibrated DecodersSpotlight120 citations
172. Characterizing Structural Regularities of Labeled Data in Overparameterized ModelsOral119 citations
173. Oops I Took A Gradient: Scalable Sampling for Discrete DistributionsOral119 citations
174. How Do Adam and Training Strategies Help BNNs OptimizationSpotlight118 citations
175. Large Scale Private Learning via Low-rank ReparametrizationSpotlight118 citations
176. Principled Simplicial Neural Networks for Trajectory PredictionOral117 citations
177. Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting PotOral117 citations
178. What Makes for End-to-End Object Detection?Spotlight117 citations
179. Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective AdaptationSpotlight116 citations
180. Explaining Time Series Predictions with Dynamic MasksSpotlight116 citations
181. Learning Noise Transition Matrix from Only Noisy Labels via Total Variation RegularizationOral115 citations
182. Learning a Universal Template for Few-shot Dataset GeneralizationSpotlight115 citations
183. DeepReDuce: ReLU Reduction for Fast Private InferenceSpotlight114 citations
184. Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and InvariancesSpotlight114 citations
185. Private Stochastic Convex Optimization: Optimal Rates in L1 GeometryOral114 citations
186. Logarithmic Regret for Reinforcement Learning with Linear Function ApproximationSpotlight112 citations
187. Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous DataSpotlight112 citations
188. The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical SetsOral112 citations
189. Clusterability as an Alternative to Anchor Points When Learning with Noisy LabelsSpotlight111 citations
190. Deep Adaptive Design: Amortizing Sequential Bayesian Experimental DesignOral111 citations
191. Measuring Robustness in Deep Learning Based Compressive SensingOral111 citations
192. Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization?Oral109 citations
193. Conservative Objective Models for Effective Offline Model-Based OptimizationSpotlight108 citations
194. Learning and Planning in Complex Action SpacesSpotlight108 citations
195. A statistical perspective on distillationSpotlight107 citations
196. Classification with Rejection Based on Cost-sensitive ClassificationSpotlight107 citations
197. Intermediate Layer Optimization for Inverse Problems using Deep Generative ModelsSpotlight107 citations
198. MC-LSTM: Mass-Conserving LSTMSpotlight107 citations
199. Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More DepthSpotlight107 citations
200. An End-to-End Framework for Molecular Conformation Generation via Bilevel ProgrammingSpotlight106 citations
201. Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeedSpotlight105 citations
202. From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via RegularizationSpotlight105 citations
203. Graph Neural Networks Inspired by Classical Iterative AlgorithmsOral104 citations
204. Improving Generalization in Meta-learning via Task AugmentationSpotlight104 citations
205. Characterizing Fairness Over the Set of Good Models Under Selective LabelsSpotlight103 citations
206. Differentiable Particle Filtering via Entropy-Regularized Optimal TransportOral103 citations
207. LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge GraphsSpotlight103 citations
208. Learning Neural Network SubspacesSpotlight103 citations
209. On Linear Identifiability of Learned RepresentationsSpotlight103 citations
210. Provably Strict Generalisation Benefit for Equivariant ModelsSpotlight103 citations
211. Data Augmentation for Meta-LearningSpotlight102 citations
212. FOP: Factorizing Optimal Joint Policy of Maximum-Entropy Multi-Agent Reinforcement LearningSpotlight102 citations
213. 1-bit Adam: Communication Efficient Large-Scale Training with Adam’s Convergence SpeedSpotlight100 citations
214. Consensus Control for Decentralized Deep LearningSpotlight100 citations
215. Disentangling syntax and semantics in the brain with deep networksSpotlight100 citations
216. Mandoline: Model Evaluation under Distribution ShiftSpotlight100 citations
217. Poolingformer: Long Document Modeling with Pooling AttentionSpotlight99 citations
218. Fast active learning for pure exploration in reinforcement learningSpotlight97 citations
219. On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror DescentOral97 citations
220. AGENT: A Benchmark for Core Psychological ReasoningSpotlight96 citations
221. Leveraging Sparse Linear Layers for Debuggable Deep NetworksOral96 citations
222. Multiplicative Noise and Heavy Tails in Stochastic OptimizationSpotlight96 citations
223. Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU NetworksSpotlight96 citations
224. Differentially Private Query Release Through Adaptive ProjectionOral95 citations
225. Continual Learning in the Teacher-Student Setup: Impact of Task SimilaritySpotlight94 citations
226. How to Learn when Data Reacts to Your Model: Performative Gradient DescentSpotlight94 citations
227. LTL2Action: Generalizing LTL Instructions for Multi-Task RLSpotlight94 citations
228. Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution GeneralizationSpotlight93 citations
229. Learning and Planning in Average-Reward Markov Decision ProcessesSpotlight93 citations
230. How Important is the Train-Validation Split in Meta-Learning?Spotlight92 citations
231. Muesli: Combining Improvements in Policy OptimizationSpotlight92 citations
232. Optimal Complexity in Decentralized TrainingOral92 citations
233. Soft then Hard: Rethinking the Quantization in Neural Image CompressionSpotlight92 citations
234. End-to-End Learning of Coherent Probabilistic Forecasts for Hierarchical Time SeriesSpotlight91 citations
235. Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without SacrificesSpotlight90 citations
236. Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation ManifoldSpotlight90 citations
237. A Value-Function-based Interior-point Method for Non-convex Bi-level OptimizationSpotlight89 citations
238. HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network ArchitectureSpotlight89 citations
239. Order-Agnostic Cross Entropy for Non-Autoregressive Machine TranslationOral89 citations
240. World Model as a Graph: Learning Latent Landmarks for PlanningOral89 citations
241. Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RLOral88 citations
242. f-Domain Adversarial Learning: Theory and AlgorithmsSpotlight88 citations
243. iDARTS: Differentiable Architecture Search with Stochastic Implicit GradientsSpotlight88 citations
244. ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed TrainingOral87 citations
245. Annealed Flow Transport Monte CarloOral87 citations
246. CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming ConstraintsSpotlight87 citations
247. Hierarchical VAEs Know What They Don’t KnowSpotlight87 citations
248. Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation GapSpotlight87 citations
249. Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance GuaranteesSpotlight87 citations
250. UnICORNN: A recurrent model for learning very long time dependenciesSpotlight87 citations
251. When Does Data Augmentation Help With Membership Inference Attacks?Spotlight87 citations
252. Debiasing Model Updates for Improving Personalized Federated TrainingSpotlight86 citations
253. Improved OOD Generalization via Adversarial Training and PretraingSpotlight86 citations
254. A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement LearningSpotlight85 citations
255. Directional Bias AmplificationSpotlight85 citations
256. KNAS: Green Neural Architecture SearchSpotlight85 citations
257. Optimizing persistent homology based functionsOral85 citations
258. Asymmetric Loss Functions for Learning with Noisy LabelsSpotlight84 citations
259. Federated Learning under Arbitrary Communication PatternsSpotlight84 citations
260. Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant MatrixOral84 citations
261. How Framelets Enhance Graph Neural NetworksSpotlight84 citations
262. Loss Surface Simplexes for Mode Connecting Volumes and Fast EnsemblingSpotlight84 citations
263. Meta-Thompson SamplingSpotlight84 citations
264. What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?Spotlight84 citations
265. AlphaNet: Improved Training of Supernets with Alpha-DivergenceOral83 citations
266. DAGs with No Curl: An Efficient DAG Structure Learning ApproachSpotlight83 citations
267. Randomized Entity-wise Factorization for Multi-Agent Reinforcement LearningOral83 citations
268. Class2Simi: A Noise Reduction Perspective on Learning with Noisy LabelsSpotlight82 citations
269. Emergent Social Learning via Multi-agent Reinforcement LearningSpotlight82 citations
270. Skew Orthogonal ConvolutionsSpotlight82 citations
271. Towards the Unification and Robustness of Perturbation and Gradient Based ExplanationsSpotlight82 citations
272. Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation LearningSpotlight81 citations
273. Self-Damaging Contrastive LearningSpotlight81 citations
274. Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts GeneralizationSpotlight80 citations
275. Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech TranslationSpotlight80 citations
276. Optimal Counterfactual Explanations in Tree EnsemblesSpotlight80 citations
277. Examining and Combating Spurious Features under Distribution ShiftSpotlight79 citations
278. Learning Task Informed AbstractionsSpotlight79 citations
279. Modelling Behavioural Diversity for Learning in Open-Ended GamesOral79 citations
280. Off-Belief LearningSpotlight79 citations
281. Counterfactual Credit Assignment in Model-Free Reinforcement LearningSpotlight78 citations
282. Outlier-Robust Optimal TransportSpotlight78 citations
283. Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment RestrictionSpotlight78 citations
284. Revealing the Structure of Deep Neural Networks via Convex DualitySpotlight78 citations
285. Selecting Data Augmentation for Simulating InterventionsSpotlight78 citations
286. Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search SpacesSpotlight78 citations
287. Accelerate CNNs from Three Dimensions: A Comprehensive Pruning FrameworkSpotlight77 citations
288. Continuous-time Model-based Reinforcement LearningSpotlight77 citations
289. Data augmentation for deep learning based accelerated MRI reconstruction with limited dataSpotlight77 citations
290. FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning AnalysisSpotlight77 citations
291. Learning Intra-Batch Connections for Deep Metric LearningSpotlight77 citations
292. Leveraging Non-uniformity in First-order Non-convex OptimizationSpotlight77 citations
293. Low-Rank Sinkhorn FactorizationSpotlight77 citations
294. Maximum Mean Discrepancy Test is Aware of Adversarial AttacksSpotlight77 citations
295. Mind the Box: $l_1$-APGD for Sparse Adversarial Attacks on Image ClassifiersSpotlight77 citations
296. Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution StrategiesOral77 citations
297. DORO: Distributional and Outlier Robust OptimizationSpotlight76 citations
298. Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement LearningSpotlight76 citations
299. Leveraging Public Data for Practical Private Query ReleaseSpotlight76 citations
300. SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual PoliciesSpotlight76 citations
301. Self-Tuning for Data-Efficient Deep LearningSpotlight76 citations
302. Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training DynamicsSpotlight76 citations
303. Distribution-Free Calibration Guarantees for Histogram Binning without Sample SplittingSpotlight75 citations
304. Exponentially Many Local Minima in Quantum Neural NetworksSpotlight75 citations
305. Federated Composite OptimizationSpotlight75 citations
306. Learning Bounds for Open-Set LearningSpotlight75 citations
307. Momentum Residual Neural NetworksSpotlight75 citations
308. Stabilizing Equilibrium Models by Jacobian RegularizationSpotlight74 citations
309. Strategic Classification in the DarkSpotlight74 citations
310. Explanations for Monotonic Classifiers.Spotlight73 citations
311. Neural Tangent Generalization AttacksSpotlight73 citations
312. Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and SmoothnessOral73 citations
313. Fair Classification with Noisy Protected Attributes: A Framework with Provable GuaranteesSpotlight72 citations
314. Active Testing: Sample-Efficient Model EvaluationSpotlight71 citations
315. How could Neural Networks understand Programs?Spotlight71 citations
316. LieTransformer: Equivariant Self-Attention for Lie GroupsSpotlight71 citations
317. Link Prediction with Persistent Homology: An Interactive ViewSpotlight71 citations
318. Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden ConfoundingSpotlight71 citations
319. Understanding the Dynamics of Gradient Flow in Overparameterized Linear modelsSpotlight71 citations
320. Inverse Constrained Reinforcement LearningSpotlight70 citations
321. Multiplying Matrices Without MultiplyingSpotlight70 citations
322. Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist NeuronsSpotlight70 citations
323. Leveraging Language to Learn Program Abstractions and Search HeuristicsSpotlight69 citations
324. Private Adaptive Gradient Methods for Convex OptimizationSpotlight69 citations
325. Safe Reinforcement Learning Using Advantage-Based InterventionSpotlight69 citations
326. Solving high-dimensional parabolic PDEs using the tensor train formatOral68 citations
327. Controlling Graph Dynamics with Reinforcement Learning and Graph Neural NetworksSpotlight67 citations
328. Distributed Second Order Methods with Fast Rates and Compressed CommunicationSpotlight67 citations
329. Efficient Lottery Ticket Finding: Less Data is MoreSpotlight67 citations
330. Online Graph Dictionary LearningSpotlight67 citations
331. Efficient Differentiable Simulation of Articulated BodiesSpotlight66 citations
332. Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?Spotlight66 citations
333. Sparsity-Agnostic Lasso BanditSpotlight66 citations
334. Strategic Classification Made PracticalSpotlight66 citations
335. Towards Open Ad Hoc Teamwork Using Graph-based Policy LearningSpotlight66 citations
336. Watermarking Deep Neural Networks with Greedy ResidualsSpotlight66 citations
337. Fairness of Exposure in Stochastic BanditsSpotlight65 citations
338. LIME: Learning Inductive Bias for Primitives of Mathematical ReasoningSpotlight65 citations
339. Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic MapsSpotlight64 citations
340. Don’t Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary ClassificationSpotlight64 citations
341. Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processesSpotlight64 citations
342. LAMDA: Label Matching Deep Domain AdaptationSpotlight64 citations
343. One for One, or All for All: Equilibria and Optimality of Collaboration in Federated LearningSpotlight64 citations
344. Regularized Online Allocation Problems: Fairness and BeyondSpotlight64 citations
345. Skill Discovery for Exploration and Planning using Deep Skill GraphsOral64 citations
346. Composing Normalizing Flows for Inverse ProblemsSpotlight63 citations
347. Exploration in Approximate Hyper-State Space for Meta Reinforcement LearningSpotlight63 citations
348. Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time ScalingSpotlight63 citations
349. Object Segmentation Without Labels with Large-Scale Generative ModelsSpotlight63 citations
350. On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear WidthsSpotlight63 citations
351. Risk Bounds and Rademacher Complexity in Batch Reinforcement LearningSpotlight63 citations
352. Towards Defending against Adversarial Examples via Attack-Invariant FeaturesSpotlight63 citations
353. A Theory of Label Propagation for Subpopulation ShiftSpotlight62 citations
354. Breaking the Deadly Triad with a Target NetworkSpotlight62 citations
355. Coach-Player Multi-agent Reinforcement Learning for Dynamic Team CompositionOral62 citations
356. Near-Optimal Representation Learning for Linear Bandits and Linear RLSpotlight62 citations
357. Training Recurrent Neural Networks via Forward Propagation Through TimeSpotlight62 citations
358. Vector Quantized Models for PlanningSpotlight62 citations
359. Align, then memorise: the dynamics of learning with feedback alignmentSpotlight61 citations
360. Bias-Variance Reduced Local SGD for Less Heterogeneous Federated LearningSpotlight61 citations
361. DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-LearningSpotlight61 citations
362. On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear NetworksSpotlight61 citations
363. Privacy-Preserving Feature Selection with Secure Multiparty ComputationSpotlight61 citations
364. Stochastic Multi-Armed Bandits with Unrestricted Delay DistributionsSpotlight61 citations
365. Temporal Predictive Coding For Model-Based Planning In Latent SpaceSpotlight61 citations
366. "Hey, that’s not an ODE": Faster ODE Adjoints via SeminormsSpotlight60 citations
367. Grounding Language to Entities and Dynamics for Generalization in Reinforcement LearningSpotlight60 citations
368. Inferring Latent Dynamics Underlying Neural Population Activity via Neural Differential EquationsOral60 citations
369. Online Learning in Unknown Markov GamesSpotlight60 citations
370. Scalable Computations of Wasserstein Barycenter via Input Convex Neural NetworksOral60 citations
371. Few-Shot Conformal Prediction with Auxiliary TasksSpotlight59 citations
372. Learning in Nonzero-Sum Stochastic Games with PotentialsSpotlight59 citations
373. On-Policy Deep Reinforcement Learning for the Average-Reward CriterionSpotlight59 citations
374. PODS: Policy Optimization via Differentiable SimulationSpotlight59 citations
375. Spectral Normalisation for Deep Reinforcement Learning: An Optimisation PerspectiveSpotlight59 citations
376. UneVEn: Universal Value Exploration for Multi-Agent Reinforcement LearningSpotlight59 citations
377. Alternative Microfoundations for Strategic ClassificationSpotlight58 citations
378. Byzantine-Resilient High-Dimensional SGD with Local Iterations on Heterogeneous DataSpotlight58 citations
379. Cross-Gradient Aggregation for Decentralized Learning from Non-IID DataSpotlight58 citations
380. Differentially Private QuantilesSpotlight58 citations
381. Kernel Stein Discrepancy DescentOral58 citations
382. On a Combination of Alternating Minimization and Nesterov’s MomentumSpotlight58 citations
383. Relative Positional Encoding for Transformers with Linear ComplexityOral58 citations
384. Efficient Training of Robust Decision Trees Against Adversarial ExamplesSpotlight57 citations
385. High-dimensional Experimental Design and Kernel BanditsOral57 citations
386. Learning to Weight Imperfect DemonstrationsSpotlight57 citations
387. Risk-Sensitive Reinforcement Learning with Function Approximation: A Debiasing ApproachOral57 citations
388. SparseBERT: Rethinking the Importance Analysis in Self-attentionSpotlight57 citations
389. Towards Open-World Recommendation: An Inductive Model-based Collaborative Filtering ApproachSpotlight57 citations
390. What does LIME really see in images?Spotlight57 citations
391. Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline EnvironmentSpotlight56 citations
392. CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature SelectionSpotlight56 citations
393. Implicit Regularization in Tensor FactorizationSpotlight56 citations
394. Instabilities of Offline RL with Pre-Trained Neural RepresentationSpotlight56 citations
395. Model-Based Reinforcement Learning via Latent-Space CollocationSpotlight56 citations
396. SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft IISpotlight56 citations
397. Autoencoding Under Normalization ConstraintsSpotlight55 citations
398. Deep kernel processesSpotlight55 citations
399. Necessary and sufficient conditions for causal feature selection in time series with latent common causesSpotlight55 citations
400. Zero-Shot Knowledge Distillation from a Decision-Based Black-Box ModelSpotlight55 citations
401. A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box OptimizationSpotlight54 citations
402. Accuracy, Interpretability, and Differential Privacy via Explainable BoostingSpotlight54 citations
403. Fairness for Image Generation with Uncertain Sensitive AttributesSpotlight54 citations
404. Near-Optimal Linear Regression under Distribution ShiftSpotlight54 citations
405. Simultaneous Similarity-based Self-Distillation for Deep Metric LearningSpotlight54 citations
406. Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits SimultaneouslySpotlight53 citations
407. Active Feature Acquisition with Generative Surrogate ModelsSpotlight53 citations
408. Bayesian Optimization over Hybrid SpacesSpotlight53 citations
409. Ensemble Bootstrapping for Q-LearningSpotlight53 citations
410. Learning While Playing in Mean-Field Games: Convergence and OptimalitySpotlight53 citations
411. Model Distillation for Revenue Optimization: Interpretable Personalized PricingSpotlight53 citations
412. Model-Targeted Poisoning Attacks with Provable ConvergenceSpotlight53 citations
413. Monte Carlo Variational Auto-EncodersSpotlight53 citations
414. Quantifying the Benefit of Using Differentiable Learning over Tangent KernelsSpotlight53 citations
415. Train simultaneously, generalize better: Stability of gradient-based minimax learnersSpotlight53 citations
416. A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein DistanceSpotlight52 citations
417. Beyond $log^2(T)$ regret for decentralized bandits in matching marketsSpotlight52 citations
418. Bootstrapping Fitted Q-Evaluation for Off-Policy InferenceSpotlight52 citations
419. Data-efficient Hindsight Off-policy Option LearningSpotlight52 citations
420. Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object RepresentationsSpotlight52 citations
421. EfficientTTS: An Efficient and High-Quality Text-to-Speech ArchitectureSpotlight52 citations
422. GLSearch: Maximum Common Subgraph Detection via Learning to SearchSpotlight52 citations
423. Improved, Deterministic Smoothing for L_1 Certified RobustnessOral52 citations
424. Instance-Optimal Compressed Sensing via Posterior SamplingSpotlight52 citations
425. Lipschitz normalization for self-attention layers with application to graph neural networksSpotlight52 citations
426. PAC-Learning for Strategic ClassificationOral52 citations
427. Principled Exploration via Optimistic Bootstrapping and Backward InductionSpotlight52 citations
428. Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term ConstraintsOral52 citations
429. Safe Reinforcement Learning with Linear Function ApproximationSpotlight52 citations
430. Scalable Certified Segmentation via Randomized SmoothingSpotlight52 citations
431. Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-TrainingSpotlight52 citations
432. Stochastic Sign Descent Methods: New Algorithms and Better TheorySpotlight52 citations
433. Decentralized Riemannian Gradient Descent on the Stiefel ManifoldSpotlight51 citations
434. Fast Sketching of Polynomial Kernels of Polynomial DegreeSpotlight51 citations
435. HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical ProjectionsSpotlight51 citations
436. How Does Loss Function Affect Generalization Performance of Deep Learning? Application to Human Age EstimationSpotlight51 citations
437. Information Obfuscation of Graph Neural NetworksSpotlight51 citations
438. Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial AttacksSpotlight51 citations
439. Let’s Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing FrameworkOral51 citations
440. Multi-Receiver Online Bayesian PersuasionSpotlight51 citations
441. Regularized Submodular Maximization at ScaleSpotlight51 citations
442. Reward Identification in Inverse Reinforcement LearningSpotlight51 citations
443. SiameseXML: Siamese Networks meet Extreme Classifiers with 100M LabelsSpotlight51 citations
444. Stability and Generalization of Stochastic Gradient Methods for Minimax ProblemsOral51 citations
445. Value Alignment VerificationSpotlight51 citations
446. An Identifiable Double VAE For Disentangled RepresentationsSpotlight50 citations
447. Blind Pareto Fairness and Subgroup RobustnessSpotlight50 citations
448. Discriminative Complementary-Label Learning with Weighted LossOral50 citations
449. Gaussian Process-Based Real-Time Learning for Safety Critical ApplicationsSpotlight50 citations
450. Neighborhood Contrastive Learning Applied to Online Patient MonitoringSpotlight50 citations
451. Randomized Exploration in Reinforcement Learning with General Value Function ApproximationSpotlight50 citations
452. Reinforcement Learning Under Moral UncertaintySpotlight50 citations
453. Sliced Iterative Normalizing FlowsSpotlight50 citations
454. The Emergence of IndividualityOral50 citations
455. UCB Momentum Q-learning: Correcting the bias without forgettingOral50 citations
456. Value Iteration in Continuous Actions, States and TimeSpotlight50 citations
457. Zoo-Tuning: Adaptive Transfer from A Zoo of ModelsSpotlight50 citations
458. Compositional Video Synthesis with Action GraphsSpotlight49 citations
459. Differentiable Spatial Planning using TransformersSpotlight49 citations
460. Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed DetectionSpotlight49 citations
461. Interpretable Stability Bounds for Spectral Graph FiltersSpotlight49 citations
462. Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPsSpotlight49 citations
463. Robust Learning for Data Poisoning AttacksSpotlight49 citations
464. SpreadsheetCoder: Formula Prediction from Semi-structured ContextSpotlight49 citations
465. Unsupervised Part Representation by Flow CapsulesSpotlight49 citations
466. Accelerating Gossip SGD with Periodic Global AveragingSpotlight48 citations
467. Adversarial Policy Learning in Two-player Competitive GamesSpotlight48 citations
468. Average-Reward Off-Policy Policy Evaluation with Function ApproximationSpotlight48 citations
469. BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale PretrainingSpotlight48 citations
470. Correlation Clustering in Constant Many Parallel RoundsOral48 citations
471. Deep Learning for Functional Data Analysis with Adaptive Basis LayersSpotlight48 citations
472. Few-shot Language Coordination by Modeling Theory of MindSpotlight48 citations
473. K-shot NAS: Learnable Weight-Sharing for NAS with K-shot SupernetsSpotlight48 citations
474. Lossless Compression of Efficient Private Local RandomizersSpotlight48 citations
475. Sawtooth Factorial Topic Embeddings Guided Gamma Belief NetworkSpotlight48 citations
476. Selfish Sparse RNN TrainingSpotlight48 citations
477. Transfer-Based Semantic Anomaly DetectionSpotlight48 citations
478. Unsupervised Learning of Visual 3D Keypoints for ControlSpotlight48 citations
479. A Bit More Bayesian: Domain-Invariant Learning with UncertaintySpotlight47 citations
480. Continuous Coordination As a Realistic Scenario for Lifelong LearningSpotlight47 citations
481. Deep Reinforcement Learning amidst Continual Structured Non-StationaritySpotlight47 citations
482. Finite mixture models do not reliably learn the number of componentsSpotlight47 citations
483. Generalizable Episodic Memory for Deep Reinforcement LearningSpotlight47 citations
484. KO codes: inventing nonlinear encoding and decoding for reliable wireless communication via deep-learningSpotlight47 citations
485. Kernel Continual LearningSpotlight47 citations
486. Learning from Noisy Labels with No Change to the Training ProcessSpotlight47 citations
487. Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-SolversSpotlight47 citations
488. Optimal Thompson Sampling strategies for support-aware CVaR banditsSpotlight47 citations
489. Robust Policy Gradient against Strong Data CorruptionSpotlight47 citations
490. Testing DNN-based Autonomous Driving Systems under Critical Environmental ConditionsSpotlight47 citations
491. A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex OptimizationSpotlight46 citations
492. AutoAttend: Automated Attention Representation SearchSpotlight46 citations
493. GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental LearningSpotlight46 citations
494. MOTS: Minimax Optimal Thompson SamplingSpotlight46 citations
495. MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement LearningSpotlight46 citations
496. Offline Reinforcement Learning with Pseudometric LearningSpotlight46 citations
497. Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver HeuristicsSpotlight46 citations
498. Parallelizing Legendre Memory Unit TrainingSpotlight46 citations
499. A New Formalism, Method and Open Issues for Zero-Shot CoordinationSpotlight45 citations
500. BORE: Bayesian Optimization by Density-Ratio EstimationOral45 citations
501. Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual InformationSpotlight45 citations
502. Cross-domain Imitation from ObservationsOral45 citations
503. Fast Stochastic Bregman Gradient Methods: Sharp Analysis and Variance ReductionSpotlight45 citations
504. Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex ProgramsSpotlight45 citations
505. Interactive Learning from Activity DescriptionSpotlight45 citations
506. Meta-Cal: Well-controlled Post-hoc Calibration by RankingSpotlight45 citations
507. Online Learning with Optimism and DelaySpotlight45 citations
508. Phase Transitions, Distance Functions, and Implicit Neural RepresentationsSpotlight45 citations
509. Tesseract: Tensorised Actors for Multi-Agent Reinforcement LearningSpotlight45 citations
510. The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural NetworksOral45 citations
511. Towards Distraction-Robust Active Visual TrackingSpotlight45 citations
512. Correcting Exposure Bias for Link RecommendationSpotlight44 citations
513. Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single MessageSpotlight44 citations
514. Differentially Private Bayesian Inference for Generalized Linear ModelsSpotlight44 citations
515. Not All Memories are Created Equal: Learning to Forget by ExpiringOral44 citations
516. TempoRL: Learning When to ActSpotlight44 citations
517. Understanding Instance-Level Label Noise: Disparate Impacts and TreatmentsOral44 citations
518. Aggregating From Multiple Target-Shifted SourcesSpotlight43 citations
519. Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual NetworksSpotlight43 citations
520. Decomposed Mutual Information Estimation for Contrastive Representation LearningSpotlight43 citations
521. Deeply-Debiased Off-Policy Interval EstimationOral43 citations
522. Differentiable Sorting Networks for Scalable Sorting and Ranking SupervisionSpotlight43 citations
523. Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form GamesSpotlight43 citations
524. Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural ProcessesSpotlight43 citations
525. Evolving Attention with Residual ConvolutionsSpotlight43 citations
526. Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample ComplexitySpotlight43 citations
527. On the Inherent Regularization Effects of Noise Injection During TrainingSpotlight43 citations
528. Oneshot Differentially Private Top-k SelectionSpotlight43 citations
529. Recomposing the Reinforcement Learning Building Blocks with HypernetworksSpotlight43 citations
530. Toward Better Generalization Bounds with Locally Elastic StabilitySpotlight43 citations
531. Unsupervised Skill Discovery with Bottleneck Option LearningSpotlight43 citations
532. A General Framework For Detecting Anomalous Inputs to DNN ClassifiersOral42 citations
533. Global Prosody Style Transfer Without Text TranscriptionsOral42 citations
534. Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio EstimationSpotlight42 citations
535. Oblivious Sketching-based Central Path Method for Linear ProgrammingSpotlight42 citations
536. On the Predictability of Pruning Across ScalesSpotlight42 citations
537. Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve GeneralizationSpotlight42 citations
538. Representation Matters: Assessing the Importance of Subgroup Allocations in Training DataSpotlight42 citations
539. Bayesian Structural Adaptation for Continual LearningSpotlight41 citations
540. Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic RegressionSpotlight41 citations
541. Density Constrained Reinforcement LearningSpotlight41 citations
542. Elementary superexpressive activationsSpotlight41 citations
543. Fast margin maximization via dual accelerationSpotlight41 citations
544. MetaCURE: Meta Reinforcement Learning with Empowerment-Driven ExplorationSpotlight41 citations
545. On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training FrameworkSpotlight41 citations
546. On the price of explainability for some clustering problemsOral41 citations
547. Provably Efficient Learning of Transferable RewardsSpotlight41 citations
548. Robust Asymmetric Learning in POMDPsOral41 citations
549. Smooth $p$-Wasserstein Distance: Structure, Empirical Approximation, and Statistical ApplicationsSpotlight41 citations
550. Adversarial Multi Class Learning under Weak Supervision with Performance GuaranteesSpotlight40 citations
551. Dynamic Balancing for Model Selection in Bandits and RLSpotlight40 citations
552. Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous TimeSpotlight40 citations
553. Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced SparsitySpotlight40 citations
554. OmniNet: Omnidirectional Representations from TransformersOral40 citations
555. On Lower Bounds for Standard and Robust Gaussian Process Bandit OptimizationSpotlight40 citations
556. Optimal Off-Policy Evaluation from Multiple Logging PoliciesSpotlight40 citations
557. Optimal Transport Kernels for Sequential and Parallel Neural Architecture SearchSpotlight40 citations
558. PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference LearningOral40 citations
559. Representational aspects of depth and conditioning in normalizing flowsSpotlight40 citations
560. Robust Representation Learning via Perceptual Similarity MetricsSpotlight40 citations
561. Signatured Deep Fictitious Play for Mean Field Games with Common NoiseSpotlight40 citations
562. Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement LearningSpotlight40 citations
563. A Sampling-Based Method for Tensor Ring DecompositionSpotlight39 citations
564. Demystifying Inductive Biases for (Beta-)VAE Based ArchitecturesSpotlight39 citations
565. Federated Deep AUC Maximization for Hetergeneous Data with a Constant Communication ComplexitySpotlight39 citations
566. HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture SearchSpotlight39 citations
567. Learning Representations by Humans, for HumansSpotlight39 citations
568. Multi-group Agnostic PAC LearnabilitySpotlight39 citations
569. Sparse Feature Selection Makes Batch Reinforcement Learning More Sample EfficientSpotlight39 citations
570. The Logical Options FrameworkOral39 citations
571. Understanding Noise Injection in GANsSpotlight39 citations
572. Value-at-Risk Optimization with Gaussian ProcessesSpotlight39 citations
573. Doubly Robust Off-Policy Actor-Critic: Convergence and OptimalitySpotlight38 citations
574. Dropout: Explicit Forms and Capacity ControlSpotlight38 citations
575. Finite-Sample Analysis of Off-Policy Natural Actor-Critic AlgorithmSpotlight38 citations
576. Grey-box Extraction of Natural Language ModelsSpotlight38 citations
577. Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?Spotlight38 citations
578. Mixed Nash Equilibria in the Adversarial Examples GameSpotlight38 citations
579. Near-Optimal Algorithms for Explainable k-Medians and k-MeansSpotlight38 citations
580. Quantum algorithms for reinforcement learning with a generative modelSpotlight38 citations
581. Solving Inverse Problems with a Flow-based Noise ModelSpotlight38 citations
582. Tractable structured natural-gradient descent using local parameterizationsSpotlight38 citations
583. Variational Data Assimilation with a Learned Inverse Observation OperatorSpotlight38 citations
584. DriftSurf: Stable-State / Reactive-State Learning under Concept DriftSpotlight37 citations
585. Learning Online Algorithms with Distributional AdviceSpotlight37 citations
586. Nondeterminism and Instability in Neural Network OptimizationSpotlight37 citations
587. On the Optimality of Batch Policy Optimization AlgorithmsSpotlight37 citations
588. Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed DistributionsSpotlight37 citations
589. Structured World Belief for Reinforcement Learning in POMDPSpotlight37 citations
590. TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RLSpotlight37 citations
591. ADOM: Accelerated Decentralized Optimization Method for Time-Varying NetworksSpotlight36 citations
592. Differentiable Dynamic Quantization with Mixed Precision and Adaptive ResolutionSpotlight36 citations
593. Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and InferenceSpotlight36 citations
594. Graph Mixture Density NetworksSpotlight36 citations
595. Inverse Decision Modeling: Learning Interpretable Representations of BehaviorOral36 citations
596. Locally Private k-Means in One RoundOral36 citations
597. Noise and Fluctuation of Finite Learning Rate Stochastic Gradient DescentSpotlight36 citations
598. PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale ModelsSpotlight36 citations
599. Probabilistic Generating CircuitsOral36 citations
600. Sharper Generalization Bounds for ClusteringSpotlight36 citations
601. SoundDet: Polyphonic Moving Sound Event Detection and Localization from Raw WaveformSpotlight36 citations
602. Variational Auto-Regressive Gaussian Processes for Continual LearningSpotlight36 citations
603. BASGD: Buffered Asynchronous SGD for Byzantine LearningSpotlight35 citations
604. Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy OptimizationSpotlight35 citations
605. CATE: Computation-aware Neural Architecture Encoding with TransformersOral35 citations
606. Generative Video Transformer: Can Objects be the Words?Spotlight35 citations
607. Leveraging Good Representations in Linear Contextual BanditsSpotlight35 citations
608. Order Matters: Probabilistic Modeling of Node Sequence for Graph GenerationSpotlight35 citations
609. Sparse and Imperceptible Adversarial Attack via a Homotopy AlgorithmOral35 citations
610. Testing Group Fairness via Optimal Transport ProjectionsSpotlight35 citations
611. A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and PerformanceSpotlight34 citations
612. Accelerating Feedforward Computation via Parallel Nonlinear Equation SolvingSpotlight34 citations
613. Adaptive Sampling for Best Policy Identification in Markov Decision ProcessesSpotlight34 citations
614. Bayesian Attention Belief NetworksSpotlight34 citations
615. How rotational invariance of common kernels prevents generalization in high dimensionsSpotlight34 citations
616. RATT: Leveraging Unlabeled Data to Guarantee GeneralizationOral34 citations
617. Self-Paced Context Evaluation for Contextual Reinforcement LearningSpotlight34 citations
618. SketchEmbedNet: Learning Novel Concepts by Imitating DrawingsSpotlight34 citations
619. Towards Tight Bounds on the Sample Complexity of Average-reward MDPsSpotlight34 citations
620. When All We Need is a Piece of the Pie: A Generic Framework for Optimizing Two-way Partial AUCOral34 citations
621. Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity ResultsSpotlight33 citations
622. Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient ExplorationSpotlight33 citations
623. Fair Selective Classification Via SufficiencyOral33 citations
624. Finding the Stochastic Shortest Path with Low Regret: the Adversarial Cost and Unknown Transition CaseSpotlight33 citations
625. Improved Corruption Robust Algorithms for Episodic Reinforcement LearningSpotlight33 citations
626. Improving Lossless Compression Rates via Monte Carlo Bits-Back CodingOral33 citations
627. LARNet: Lie Algebra Residual Network for Face RecognitionSpotlight33 citations
628. Learning Generalized Intersection Over Union for Dense Pixelwise PredictionSpotlight33 citations
629. Model Performance Scaling with Multiple Data SourcesSpotlight33 citations
630. Pointwise Binary Classification with Pairwise Confidence ComparisonsSpotlight33 citations
631. Prior Image-Constrained Reconstruction using Style-Based Generative ModelsSpotlight33 citations
632. Adapting to Delays and Data in Adversarial Multi-Armed BanditsSpotlight32 citations
633. Adversarial Dueling BanditsSpotlight32 citations
634. Beyond the Pareto Efficient Frontier: Constraint Active Search for Multiobjective Experimental DesignSpotlight32 citations
635. Boosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch SizeSpotlight32 citations
636. Commutative Lie Group VAE for Disentanglement LearningOral32 citations
637. First-Order Methods for Wasserstein Distributionally Robust MDPSpotlight32 citations
638. Follow-the-Regularized-Leader Routes to Chaos in Routing GamesSpotlight32 citations
639. Hierarchical Agglomerative Graph Clustering in Nearly-Linear TimeSpotlight32 citations
640. Marginal Contribution Feature Importance - an Axiomatic Approach for Explaining DataSpotlight32 citations
641. Multi-Dimensional Classification via Sparse Label EncodingOral32 citations
642. Near Optimal Reward-Free Reinforcement LearningOral32 citations
643. Non-Autoregressive Electron Redistribution Modeling for Reaction PredictionSpotlight32 citations
644. Online Unrelated Machine Load Balancing with Predictions RevisitedOral32 citations
645. REPAINT: Knowledge Transfer in Deep Reinforcement LearningSpotlight32 citations
646. RNN with Particle Flow for Probabilistic Spatio-temporal ForecastingOral32 citations
647. Expressive 1-Lipschitz Neural Networks for Robust Multiple Graph Learning against Adversarial AttacksSpotlight31 citations
648. Federated Learning of User Verification Models Without Sharing EmbeddingsSpotlight31 citations
649. Kernel-Based Reinforcement Learning: A Finite-Time AnalysisSpotlight31 citations
650. Learning Curves for Analysis of Deep NetworksSpotlight31 citations
651. Learning disentangled representations via product manifold projectionSpotlight31 citations
652. Locally Persistent Exploration in Continuous Control Tasks with Sparse RewardsSpotlight31 citations
653. Making Paper Reviewing Robust to Bid Manipulation AttacksSpotlight31 citations
654. Model-based Reinforcement Learning for Continuous Control with Posterior SamplingOral31 citations
655. On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov GameOral31 citations
656. SMG: A Shuffling Gradient-Based Method with MomentumSpotlight31 citations
657. Self-Improved Retrosynthetic PlanningSpotlight31 citations
658. Top-k eXtreme Contextual Bandits with Arm HierarchySpotlight31 citations
659. Training Adversarially Robust Sparse Networks via Bayesian Connectivity SamplingSpotlight31 citations
660. A Modular Analysis of Provable Acceleration via Polyak’s Momentum: Training a Wide ReLU Network and a Deep Linear NetworkSpotlight30 citations
661. Acceleration via Fractal Learning Rate SchedulesSpotlight30 citations
662. Connecting Interpretability and Robustness in Decision Trees through SeparationSpotlight30 citations
663. Differentially-Private Clustering of Easy InstancesSpotlight30 citations
664. Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein DesignSpotlight30 citations
665. Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half PrecisionSpotlight30 citations
666. Navigation Turing Test (NTT): Learning to Evaluate Human-Like NavigationSpotlight30 citations
667. Overcoming Catastrophic Forgetting by Bayesian Generative RegularizationSpotlight30 citations
668. Parallel tempering on optimized pathsSpotlight30 citations
669. Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient ApproachSpotlight30 citations
670. The Symmetry between Arms and Knapsacks: A Primal-Dual Approach for Bandits with KnapsacksOral30 citations
671. Towards Rigorous Interpretations: a Formalisation of Feature AttributionSpotlight30 citations
672. Training Data Subset Selection for Regression with Controlled Generalization ErrorSpotlight30 citations
673. Understanding and Mitigating Accuracy Disparity in RegressionSpotlight30 citations
674. Valid Causal Inference with (Some) Invalid InstrumentsSpotlight30 citations
675. An Algorithm for Stochastic and Adversarial Bandits with Switching CostsSpotlight29 citations
676. CURI: A Benchmark for Productive Concept Learning Under UncertaintySpotlight29 citations
677. Collaborative Bayesian Optimization with Fair RegretSpotlight29 citations
678. Communication-Efficient Distributed SVD via Local Power IterationsSpotlight29 citations
679. Fundamental Tradeoffs in Distributionally Adversarial TrainingSpotlight29 citations
680. Generalised Lipschitz Regularisation Equals Distributional RobustnessSpotlight29 citations
681. Improved Confidence Bounds for the Linear Logistic Model and Applications to BanditsSpotlight29 citations
682. Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and ClassificationSpotlight29 citations
683. Learning de-identified representations of prosody from raw audioSpotlight29 citations
684. Monotonic Robust Policy Optimization with Model DiscrepancySpotlight29 citations
685. Parallel and Flexible Sampling from Autoregressive Models via Langevin DynamicsSpotlight29 citations
686. Permutation WeightingSpotlight29 citations
687. Re-understanding Finite-State Representations of Recurrent Policy NetworksSpotlight29 citations
688. Reasoning Over Virtual Knowledge Bases With Open Predicate RelationsSpotlight29 citations
689. Regularizing towards Causal Invariance: Linear Models with ProxiesSpotlight29 citations
690. Scalable Normalizing Flows for Permutation Invariant DensitiesSpotlight29 citations
691. Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement LearningSpotlight29 citations
692. Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian ApproachSpotlight29 citations
693. Systematic Analysis of Cluster Similarity Indices: How to Validate Validation MeasuresSpotlight29 citations
694. Tighter Bounds on the Log Marginal Likelihood of Gaussian Process Regression Using Conjugate GradientsOral29 citations
695. Towards Understanding Learning in Neural Networks with Linear TeachersSpotlight29 citations
696. Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot ClassificationSpotlight29 citations
697. A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitionsSpotlight28 citations
698. Adapting to misspecification in contextual bandits with offline regression oraclesSpotlight28 citations
699. Adversarial Option-Aware Hierarchical Imitation LearningSpotlight28 citations
700. Dataset Dynamics via Gradient Flows in Probability SpaceSpotlight28 citations
701. Differentially Private Correlation ClusteringSpotlight28 citations
702. Explainable Automated Graph Representation Learning with Hyperparameter ImportanceSpotlight28 citations
703. Guarantees for Tuning the Step Size using a Learning-to-Learn ApproachSpotlight28 citations
704. Improved Algorithms for Agnostic Pool-based Active ClassificationSpotlight28 citations
705. Memory Efficient Online Meta LearningSpotlight28 citations
706. More Powerful and General Selective Inference for Stepwise Feature Selection using Homotopy MethodSpotlight28 citations
707. On the Problem of Underranking in Group-Fair RankingSpotlight28 citations
708. Parameterless Transductive Feature Re-representation for Few-Shot LearningSpotlight28 citations
709. Provably Efficient Algorithms for Multi-Objective Competitive RLOral28 citations
710. SGLB: Stochastic Gradient Langevin BoostingSpotlight28 citations
711. SigGPDE: Scaling Sparse Gaussian Processes on Sequential DataSpotlight28 citations
712. Variance Reduction via Primal-Dual Accelerated Dual Averaging for Nonsmooth Convex Finite-SumsOral28 citations
713. A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-LearningSpotlight27 citations
714. Active Deep Probabilistic SubsamplingSpotlight27 citations
715. Addressing Catastrophic Forgetting in Few-Shot ProblemsSpotlight27 citations
716. Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and AcceleratorsSpotlight27 citations
717. Exact Gap between Generalization Error and Uniform Convergence in Random Feature ModelsSpotlight27 citations
718. Improving Gradient Regularization using Complex-Valued Neural NetworksSpotlight27 citations
719. Learning by Turning: Neural Architecture Aware OptimisationSpotlight27 citations
720. Oblivious Sketching for Logistic RegressionSpotlight27 citations
721. Predict then Interpolate: A Simple Algorithm to Learn Stable ClassifiersSpotlight27 citations
722. Rissanen Data Analysis: Examining Dataset Characteristics via Description LengthSpotlight27 citations
723. Sample Complexity of Robust Linear Classification on Separated DataSpotlight27 citations
724. Sequential Domain Adaptation by Synthesizing Distributionally Robust ExpertsOral27 citations
725. Weight-covariance alignment for adversarially robust neural networksSpotlight27 citations
726. You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli SamplingSpotlight27 citations
727. A Language for Counterfactual Generative ModelsSpotlight26 citations
728. A Probabilistic Approach to Neural Network PruningSpotlight26 citations
729. Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline PoliciesSpotlight26 citations
730. An Information-Geometric Distance on the Space of TasksSpotlight26 citations
731. Approximate Group Fairness for ClusteringSpotlight26 citations
732. Budgeted Heterogeneous Treatment Effect EstimationSpotlight26 citations
733. Cyclically Equivariant Neural Decoders for Cyclic CodesOral26 citations
734. Deciding What to Learn: A Rate-Distortion ApproachSpotlight26 citations
735. Diffusion Earth Mover’s Distance and Distribution EmbeddingsSpotlight26 citations
736. Label Distribution Learning MachineOral26 citations
737. Latent Programmer: Discrete Latent Codes for Program SynthesisOral26 citations
738. Learning from Similarity-Confidence DataSpotlight26 citations
739. Learning to Generate Noise for Multi-Attack RobustnessSpotlight26 citations
740. PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided ExplorationSpotlight26 citations
741. Policy Gradient Bayesian Robust Optimization for Imitation LearningSpotlight26 citations
742. Privacy-Preserving Video Classification with Convolutional Neural NetworksSpotlight26 citations
743. Revisiting Peng’s Q($λ$) for Modern Reinforcement LearningSpotlight26 citations
744. Robust Pure Exploration in Linear Bandits with Limited BudgetSpotlight26 citations
745. Straight to the Gradient: Learning to Use Novel Tokens for Neural Text GenerationOral26 citations
746. Which transformer architecture fits my data? A vocabulary bottleneck in self-attentionSpotlight26 citations
747. A Collective Learning Framework to Boost GNN Expressiveness for Node ClassificationSpotlight25 citations
748. Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural NetworksSpotlight25 citations
749. Communication-Efficient Distributed Optimization with Quantized PreconditionersSpotlight25 citations
750. Generalization Guarantees for Neural Architecture Search with Train-Validation SplitSpotlight25 citations
751. Guided Exploration with Proximal Policy Optimization using a Single DemonstrationSpotlight25 citations
752. High-Dimensional Gaussian Process Inference with DerivativesSpotlight25 citations
753. Improving Breadth-Wise Backpropagation in Graph Neural Networks Helps Learning Long-Range Dependencies.Spotlight25 citations
754. Megaverse: Simulating Embodied Agents at One Million Experiences per SecondSpotlight25 citations
755. Network Inference and Influence Maximization from SamplesOral25 citations
756. On-Off Center-Surround Receptive Fields for Accurate and Robust Image ClassificationSpotlight25 citations
757. Online A-Optimal Design and Active Linear RegressionSpotlight25 citations
758. Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label NoiseSpotlight25 citations
759. RNNRepair: Automatic RNN Repair via Model-based AnalysisSpotlight25 citations
760. SAINT-ACC: Safety-Aware Intelligent Adaptive Cruise Control for Autonomous Vehicles Using Deep Reinforcement LearningSpotlight25 citations
761. Scaling Properties of Deep Residual NetworksSpotlight25 citations
762. Sharing Less is More: Lifelong Learning in Deep Networks with Selective Layer TransferSpotlight25 citations
763. Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph DrawingSpotlight25 citations
764. Towards Practical Mean Bounds for Small SamplesSpotlight25 citations
765. A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor RepresentationSpotlight24 citations
766. A Functional Perspective on Learning Symmetric Functions with Neural NetworksSpotlight24 citations
767. A Novel Sequential Coreset Method for Gradient Descent AlgorithmsSpotlight24 citations
768. A large-scale benchmark for few-shot program induction and synthesisSpotlight24 citations
769. Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian DimensionalitySpotlight24 citations
770. Almost Optimal Anytime Algorithm for Batched Multi-Armed BanditsSpotlight24 citations
771. Deep Latent Graph MatchingSpotlight24 citations
772. Differentially Private Sliced Wasserstein DistanceOral24 citations
773. Exact Optimization of Conformal Predictors via Incremental and Decremental LearningSpotlight24 citations
774. Fast Algorithms for Stackelberg Prediction Game with Least Squares LossSpotlight24 citations
775. Function Contrastive Learning of Transferable Meta-RepresentationsSpotlight24 citations
776. GMAC: A Distributional Perspective on Actor-Critic FrameworkSpotlight24 citations
777. Hyperparameter Selection for Imitation LearningOral24 citations
778. Making transport more robust and interpretable by moving data through a small number of anchor pointsSpotlight24 citations
779. Matrix Sketching for Secure Collaborative Machine LearningSpotlight24 citations
780. Non-Exponentially Weighted Aggregation: Regret Bounds for Unbounded Loss FunctionsSpotlight24 citations
781. PHEW : Constructing Sparse Networks that Learn Fast and Generalize Well without Training DataSpotlight24 citations
782. Riemannian Convex Potential MapsSpotlight24 citations
783. Towards Better Robust Generalization with Shift Consistency RegularizationSpotlight24 citations
784. Variance Reduced Training with Stratified Sampling for Forecasting ModelsSpotlight24 citations
785. A Gradient Based Strategy for Hamiltonian Monte Carlo Hyperparameter OptimizationSpotlight23 citations
786. A New Representation of Successor Features for Transfer across Dissimilar EnvironmentsSpotlight23 citations
787. A Regret Minimization Approach to Iterative Learning ControlSpotlight23 citations
788. A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few SamplesSpotlight23 citations
789. Asynchronous Distributed Learning : Adapting to Gradient Delays without Prior KnowledgeSpotlight23 citations
790. Bias-Free Scalable Gaussian Processes via Randomized TruncationsSpotlight23 citations
791. How and Why to Use Experimental Data to Evaluate Methods for Observational Causal InferenceSpotlight23 citations
792. Learning Diverse-Structured Networks for Adversarial RobustnessSpotlight23 citations
793. Model Fusion for Personalized LearningSpotlight23 citations
794. Newton Method over Networks is Fast up to the Statistical PrecisionSpotlight23 citations
795. On the difficulty of unbiased alpha divergence minimizationSpotlight23 citations
796. Optimal Streaming Algorithms for Multi-Armed BanditsSpotlight23 citations
797. Private Alternating Least Squares: Practical Private Matrix Completion with Tighter RatesOral23 citations
798. Tightening the Dependence on Horizon in the Sample Complexity of Q-LearningSpotlight23 citations
799. Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty EstimationSpotlight22 citations
800. Analysis of stochastic Lanczos quadrature for spectrum approximationOral22 citations
801. Catformer: Designing Stable Transformers via Sensitivity AnalysisSpotlight22 citations
802. Disambiguation of Weak Supervision leading to Exponential Convergence ratesSpotlight22 citations
803. Emphatic Algorithms for Deep Reinforcement LearningSpotlight22 citations
804. Equivariant Networks for Pixelized SpheresSpotlight22 citations
805. Interpreting and Disentangling Feature Components of Various Complexity from DNNsSpotlight22 citations
806. Keyframe-Focused Visual Imitation LearningSpotlight22 citations
807. Meta-learning Hyperparameter Performance Prediction with Neural ProcessesSpotlight22 citations
808. Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement LearningSpotlight22 citations
809. Progressive-Scale Boundary Blackbox Attack via Projective Gradient EstimationSpotlight22 citations
810. Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical PerspectivesSpotlight22 citations
811. SinIR: Efficient General Image Manipulation with Single Image ReconstructionSpotlight22 citations
812. Task-Optimal Exploration in Linear Dynamical SystemsOral22 citations
813. Versatile Verification of Tree EnsemblesSpotlight22 citations
814. Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise InjectionsSpotlight21 citations
815. Characterizing the Gap Between Actor-Critic and Policy GradientSpotlight21 citations
816. DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within GibbsOral21 citations
817. Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace OffsetSpotlight21 citations
818. Differentially Private Densest Subgraph DetectionSpotlight21 citations
819. Efficient Message Passing for 0–1 ILPs with Binary Decision DiagramsSpotlight21 citations
820. Estimating Identifiable Causal Effects on Markov Equivalence Class through Double Machine LearningSpotlight21 citations
821. Integer Programming for Causal Structure Learning in the Presence of Latent VariablesOral21 citations
822. Learning Queueing Policies for Organ Transplantation Allocation using Interpretable Counterfactual Survival AnalysisSpotlight21 citations
823. On the Random Conjugate Kernel and Neural Tangent KernelSpotlight21 citations
824. Optimal Non-Convex Exact Recovery in Stochastic Block Model via Projected Power MethodSpotlight21 citations
825. Policy Caches with Successor FeaturesSpotlight21 citations
826. Provable Lipschitz Certification for Generative ModelsSpotlight21 citations
827. Provably Correct Optimization and Exploration with Non-linear PoliciesSpotlight21 citations
828. SPADE: A Spectral Method for Black-Box Adversarial Robustness EvaluationSpotlight21 citations
829. Sparse within Sparse Gaussian Processes using Neighbor InformationSpotlight21 citations
830. Stochastic Iterative Graph MatchingSpotlight21 citations
831. Uncovering the Connections Between Adversarial Transferability and Knowledge TransferabilitySpotlight21 citations
832. A Proxy Variable View of Shared ConfoundingSpotlight20 citations
833. Adversarial Combinatorial Bandits with General Non-linear Reward FunctionsSpotlight20 citations
834. Asynchronous Decentralized Optimization With Implicit Stochastic Variance ReductionSpotlight20 citations
835. DeepWalking Backwards: From Embeddings Back to GraphsSpotlight20 citations
836. Dueling Convex OptimizationSpotlight20 citations
837. Fairness and Bias in Online SelectionSpotlight20 citations
838. Fast Projection Onto Convex Smooth ConstraintsSpotlight20 citations
839. Improved Regret Bound and Experience Replay in Regularized Policy IterationOral20 citations
840. Learn-to-Share: A Hardware-friendly Transfer Learning Framework Exploiting Computation and Parameter SharingOral20 citations
841. Learning Binary Decision Trees by Argmin DifferentiationSpotlight20 citations
842. Mixed Cross Entropy Loss for Neural Machine TranslationOral20 citations
843. On Reinforcement Learning with Adversarial Corruption and Its Application to Block MDPSpotlight20 citations
844. On the Convergence of Hamiltonian Monte Carlo with Stochastic GradientsSpotlight20 citations
845. Policy Analysis using Synthetic Controls in Continuous-TimeSpotlight20 citations
846. Quantile Bandits for Best Arms IdentificationSpotlight20 citations
847. Robust Learning-Augmented Caching: An Experimental StudySpotlight20 citations
848. Self Normalizing FlowsSpotlight20 citations
849. Temporal Difference Learning as Gradient SplittingOral20 citations
850. Conditional Temporal Neural Processes with Covariance LossSpotlight19 citations
851. Consistent regression when oblivious outliers overwhelmSpotlight19 citations
852. Directed Graph Embeddings in Pseudo-Riemannian ManifoldsSpotlight19 citations
853. Discretization Drift in Two-Player GamesSpotlight19 citations
854. Integrated Defense for Resilient Graph MatchingSpotlight19 citations
855. Large-Scale Meta-Learning with Continual Trajectory ShiftingSpotlight19 citations
856. Neuro-algorithmic Policies Enable Fast Combinatorial GeneralizationSpotlight19 citations
857. Online Selection Problems against Constrained AdversarySpotlight19 citations
858. Sparsifying Networks via Subdifferential InclusionSpotlight19 citations
859. Unsupervised Co-part Segmentation through AssemblySpotlight19 citations
860. Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent GeneralizationSpotlight19 citations
861. Agnostic Learning of Halfspaces with Gradient Descent via Soft MarginsOral18 citations
862. Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved GeneralizationOral18 citations
863. Decision-Making Under Selective Labels: Optimal Finite-Domain Policies and BeyondSpotlight18 citations
864. Flow-based Attribution in Graphical Models: A Recursive Shapley ApproachSpotlight18 citations
865. Model-Free and Model-Based Policy Evaluation when Causality is UncertainSpotlight18 citations
866. Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online LearningOral18 citations
867. Online Limited Memory Neural-Linear Bandits with Likelihood MatchingSpotlight18 citations
868. Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with $\sqrt$T RegretSpotlight18 citations
869. Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with CorruptionsSpotlight18 citations
870. Provable Robustness of Adversarial Training for Learning Halfspaces with NoiseSpotlight18 citations
871. Self-supervised and Supervised Joint Training for Resource-rich Machine TranslationSpotlight18 citations
872. Submodular Maximization subject to a Knapsack Constraint: Combinatorial Algorithms with Near-optimal Adaptive ComplexitySpotlight18 citations
873. Tilting the playing field: Dynamical loss functions for machine learningOral18 citations
874. Two Heads are Better Than One: Hypergraph-Enhanced Graph Reasoning for Visual Event RatiocinationSpotlight18 citations
875. ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary VariablesSpotlight17 citations
876. Benchmarks, Algorithms, and Metrics for Hierarchical DisentanglementOral17 citations
877. Concentric mixtures of Mallows models for top-$k$ rankings: sampling and identifiabilitySpotlight17 citations
878. Cross-model Back-translated Distillation for Unsupervised Machine TranslationSpotlight17 citations
879. Generalization Bounds in the Presence of Outliers: a Median-of-Means StudySpotlight17 citations
880. Generalized Doubly Reparameterized Gradient EstimatorsSpotlight17 citations
881. Learn2Hop: Learned Optimization on Rough LandscapesSpotlight17 citations
882. Learning Stochastic Behaviour from Aggregate DataSpotlight17 citations
883. Locally Adaptive Label Smoothing Improves Predictive ChurnSpotlight17 citations
884. Message Passing Adaptive Resonance Theory for Online Active Semi-supervised LearningSpotlight17 citations
885. Multidimensional Scaling: Approximation and ComplexitySpotlight17 citations
886. PixelTransformer: Sample Conditioned Signal GenerationSpotlight17 citations
887. Post-selection inference with HSIC-LassoSpotlight17 citations
888. Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clusteringSpotlight17 citations
889. 12-Lead ECG Reconstruction via Koopman OperatorsSpotlight16 citations
890. A Structured Observation Distribution for Generative Biological Sequence Prediction and ForecastingSpotlight16 citations
891. AdaXpert: Adapting Neural Architecture for Growing DataSpotlight16 citations
892. Binary Classification from Multiple Unlabeled Datasets via Surrogate Set ClassificationSpotlight16 citations
893. Combinatorial Blocking Bandits with Stochastic DelaysSpotlight16 citations
894. Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement LearningSpotlight16 citations
895. DANCE: Enhancing saliency maps using decoysSpotlight16 citations
896. Deep Continuous NetworksSpotlight16 citations
897. Dimensionality Reduction for the Sum-of-Distances MetricOral16 citations
898. GBHT: Gradient Boosting Histogram Transform for Density EstimationSpotlight16 citations
899. Geometric convergence of elliptical slice samplingSpotlight16 citations
900. Local Correlation Clustering with Asymmetric Classification ErrorsSpotlight16 citations
901. Meta-Learning Bidirectional Update RulesSpotlight16 citations
902. Neural Pharmacodynamic State Space ModelingSpotlight16 citations
903. No-regret Algorithms for Capturing Events in Poisson Point ProcessesSpotlight16 citations
904. Off-Policy Confidence SequencesSpotlight16 citations
905. On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student SettingSpotlight16 citations
906. Parallel Droplet Control in MEDA Biochips using Multi-Agent Reinforcement LearningSpotlight16 citations
907. Randomized Algorithms for Submodular Function Maximization with a $k$-System ConstraintSpotlight16 citations
908. Reinforcement Learning of Implicit and Explicit Control Flow InstructionsSpotlight16 citations
909. Streaming Bayesian Deep Tensor FactorizationSpotlight16 citations
910. Structured Convolutional Kernel Networks for Airline Crew SchedulingSpotlight16 citations
911. T-SCI: A Two-Stage Conformal Inference Algorithm with Guaranteed Coverage for Cox-MLPSpotlight16 citations
912. Training Quantized Neural Networks to Global Optimality via Semidefinite ProgrammingSpotlight16 citations
913. Zeroth-Order Non-Convex Learning via Hierarchical Dual AveragingSpotlight16 citations
914. Adversarial Robustness Guarantees for Random Deep Neural NetworksSpotlight15 citations
915. Affine Invariant Analysis of Frank-Wolfe on Strongly Convex SetsSpotlight15 citations
916. Analyzing the tree-layer structure of Deep ForestsSpotlight15 citations
917. Best Model Identification: A Rested Bandit FormulationSpotlight15 citations
918. Bias-Robust Bayesian Optimization via Dueling BanditsSpotlight15 citations
919. CARTL: Cooperative Adversarially-Robust Transfer LearningOral15 citations
920. Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix FactorizationOral15 citations
921. Event Outlier Detection in Continuous TimeSpotlight15 citations
922. Faster Kernel Matrix Algebra via Density EstimationSpotlight15 citations
923. Modeling Hierarchical Structures with Continuous Recursive Neural NetworksOral15 citations
924. Nonparametric Hamiltonian Monte CarloSpotlight15 citations
925. On Monotonic Linear Interpolation of Neural Network ParametersSpotlight15 citations
926. On Proximal Policy Optimization’s Heavy-tailed GradientsSpotlight15 citations
927. On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel ModelsSpotlight15 citations
928. PID Accelerated Value Iteration AlgorithmSpotlight15 citations
929. Prediction-Centric Learning of Independent Cascade Dynamics from Partial ObservationsSpotlight15 citations
930. Projection Robust Wasserstein BarycentersSpotlight15 citations
931. Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured TransitionsOral15 citations
932. Relative Deviation Margin BoundsSpotlight15 citations
933. SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian ProcessesOral15 citations
934. Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and MoreSpotlight15 citations
935. Slot Machines: Discovering Winning Combinations of Random Weights in Neural NetworksSpotlight15 citations
936. Winograd Algorithm for AdderNetSpotlight15 citations
937. A Discriminative Technique for Multiple-Source AdaptationSpotlight14 citations
938. Automatic variational inference with cascading flowsSpotlight14 citations
939. Boosting for Online Convex OptimizationSpotlight14 citations
940. Deep Coherent Exploration for Continuous ControlSpotlight14 citations
941. Detection of Signal in the Spiked Rectangular ModelsSpotlight14 citations
942. Distributed Nyström Kernel Learning with CommunicationsSpotlight14 citations
943. Estimating $α$-Rank from A Few Entries with Low Rank Matrix CompletionSpotlight14 citations
944. Generalization Error Bound for Hyperbolic Ordinal EmbeddingSpotlight14 citations
945. Hierarchical Clustering of Data Streams: Scalable Algorithms and Approximation GuaranteesSpotlight14 citations
946. Instance Specific Approximations for Submodular MaximizationSpotlight14 citations
947. Learning Interaction Kernels for Agent Systems on Riemannian ManifoldsSpotlight14 citations
948. Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential RecommendationSpotlight14 citations
949. On Characterizing GAN Convergence Through Proximal Duality GapSpotlight14 citations
950. On Limited-Memory Subsampling Strategies for BanditsSpotlight14 citations
951. Projection techniques to update the truncated SVD of evolving matrices with applicationsSpotlight14 citations
952. Robust Testing and Estimation under Manipulation AttacksSpotlight14 citations
953. Robust Unsupervised Learning via L-statistic MinimizationSpotlight14 citations
954. Supervised Tree-Wasserstein DistanceSpotlight14 citations
955. The Impact of Record Linkage on Learning from Feature Partitioned DataSpotlight14 citations
956. The Power of Adaptivity for Stochastic Submodular CoverOral14 citations
957. Whittle Networks: A Deep Likelihood Model for Time SeriesSpotlight14 citations
958. A Framework for Private Matrix Analysis in Sliding Window ModelSpotlight13 citations
959. Active Learning for Distributionally Robust Level-Set EstimationSpotlight13 citations
960. Approximation Theory of Convolutional Architectures for Time Series ModellingSpotlight13 citations
961. Chebyshev Polynomial Codes: Task Entanglement-based Coding for Distributed Matrix MultiplicationSpotlight13 citations
962. Decomposable Submodular Function Minimization via Maximum FlowSpotlight13 citations
963. Detecting Rewards Deterioration in Episodic Reinforcement LearningSpotlight13 citations
964. Distributionally Robust Optimization with Markovian DataSpotlight13 citations
965. Implicit Bias of Linear RNNsSpotlight13 citations
966. Label Inference Attacks from Log-loss ScoresOral13 citations
967. MorphVAE: Generating Neural Morphologies from 3D-Walks using a Variational Autoencoder with Spherical Latent SpaceSpotlight13 citations
968. On the Power of Localized Perceptron for Label-Optimal Learning of Halfspaces with Adversarial NoiseSpotlight13 citations
969. Parameter-free Locally Accelerated Conditional GradientsSpotlight13 citations
970. Quantization Algorithms for Random Fourier FeaturesSpotlight13 citations
971. Robust Density Estimation from Batches: The Best Things in Life are (Nearly) FreeOral13 citations
972. Three Operator Splitting with a Nonconvex Loss FunctionSpotlight13 citations
973. An Integer Linear Programming Framework for Mining Constraints from DataSpotlight12 citations
974. Confidence-Budget Matching for Sequential Budgeted LearningSpotlight12 citations
975. Diffusion Source Identification on Networks with Statistical ConfidenceSpotlight12 citations
976. Dynamic Planning and Learning under Recovering RewardsSpotlight12 citations
977. Efficient Performance Bounds for Primal-Dual Reinforcement Learning from DemonstrationsSpotlight12 citations
978. From Local to Global Norm Emergence: Dissolving Self-reinforcing Substructures with Incremental Social InstrumentsSpotlight12 citations
979. GANMEX: One-vs-One Attributions using GAN-based Model ExplainabilitySpotlight12 citations
980. GeomCA: Geometric Evaluation of Data RepresentationsSpotlight12 citations
981. Group-Sparse Matrix Factorization for Transfer Learning of Word EmbeddingsSpotlight12 citations
982. Improving Ultrametrics Embeddings Through CoresetsSpotlight12 citations
983. Interpretable Stein Goodness-of-fit Tests on Riemannian ManifoldSpotlight12 citations
984. Joint Online Learning and Decision-making via Dual Mirror DescentSpotlight12 citations
985. Learning to Rehearse in Long Sequence MemorizationSpotlight12 citations
986. Markpainting: Adversarial Machine Learning meets InpaintingSpotlight12 citations
987. Modularity in Reinforcement Learning via Algorithmic Independence in Credit AssignmentOral12 citations
988. Offline Contextual Bandits with Overparameterized ModelsSpotlight12 citations
989. Posterior Value Functions: Hindsight Baselines for Policy Gradient MethodsSpotlight12 citations
990. Quantitative Understanding of VAE as a Non-linearly Scaled Isometric EmbeddingSpotlight12 citations
991. Rate-Distortion Analysis of Minimum Excess Risk in Bayesian LearningOral12 citations
992. Sparse Bayesian Learning via Stepwise RegressionSpotlight12 citations
993. Better Training using Weight-Constrained Stochastic DynamicsSpotlight11 citations
994. Convex Regularization in Monte-Carlo Tree SearchSpotlight11 citations
995. CountSketches, Feature Hashing and the Median of ThreeSpotlight11 citations
996. Decentralized Single-Timescale Actor-Critic on Zero-Sum Two-Player Stochastic GamesSpotlight11 citations
997. Disentangling Sampling and Labeling Bias for Learning in Large-output SpacesSpotlight11 citations
998. Enhancing Robustness of Neural Networks through Fourier StabilizationSpotlight11 citations
999. Estimation and Quantization of Expected Persistence DiagramsSpotlight11 citations
1000. Implicit rate-constrained optimization of non-decomposable objectivesSpotlight11 citations

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