ICML 2022 Accepted Papers

The full list of 1,228 papers accepted at ICML 2022 (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. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationSpotlight5,196 citations
2. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion ModelsSpotlight3,944 citations
3. FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series ForecastingSpotlight2,128 citations
4. Improving Language Models by Retrieving from Trillions of TokensSpotlight1,323 citations
5. Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied AgentsSpotlight1,280 citations
6. OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning FrameworkSpotlight1,222 citations
7. Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timeSpotlight1,132 citations
8. data2vec: A General Framework for Self-supervised Learning in Speech, Vision and LanguageOral1,024 citations
9. Equivariant Diffusion for Molecule Generation in 3DOral806 citations
10. GLaM: Efficient Scaling of Language Models with Mixture-of-ExpertsSpotlight765 citations
11. Planning with Diffusion for Flexible Behavior SynthesisOral764 citations
12. Out-of-Distribution Detection with Deep Nearest NeighborsSpotlight635 citations
13. Diffusion Models for Adversarial PurificationSpotlight583 citations
14. Scaling Out-of-Distribution Detection for Real-World SettingsSpotlight571 citations
15. YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for EveryoneSpotlight526 citations
16. Learning inverse folding from millions of predicted structuresOral475 citations
17. DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow ForecastingSpotlight441 citations
18. Efficient Test-Time Model Adaptation without ForgettingSpotlight411 citations
19. Structure-Aware Transformer for Graph Representation LearningSpotlight383 citations
20. Memory-Based Model Editing at ScaleSpotlight368 citations
21. Mitigating Neural Network Overconfidence with Logit NormalizationSpotlight362 citations
22. EquiBind: Geometric Deep Learning for Drug Binding Structure PredictionSpotlight356 citations
23. Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual ConceptsSpotlight346 citations
24. Transformer Quality in Linear TimeSpotlight327 citations
25. How Powerful are Spectral Graph Neural NetworksSpotlight316 citations
26. DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI ScaleSpotlight315 citations
27. Deduplicating Training Data Mitigates Privacy Risks in Language ModelsSpotlight311 citations
28. FedScale: Benchmarking Model and System Performance of Federated Learning at ScaleSpotlight299 citations
29. 3D Infomax improves GNNs for Molecular Property PredictionSpotlight294 citations
30. Black-Box Tuning for Language-Model-as-a-ServiceSpotlight288 citations
31. Rethinking Graph Neural Networks for Anomaly DetectionSpotlight287 citations
32. Score-based Generative Modeling of Graphs via the System of Stochastic Differential EquationsSpotlight281 citations
33. Temporal Difference Learning for Model Predictive ControlSpotlight278 citations
34. Interpretable and Generalizable Graph Learning via Stochastic Attention MechanismSpotlight277 citations
35. Online Decision TransformerOral276 citations
36. How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative ModelsSpotlight271 citations
37. Fishr: Invariant Gradient Variances for Out-of-Distribution GeneralizationSpotlight267 citations
38. Finding Global Homophily in Graph Neural Networks When Meeting HeterophilySpotlight263 citations
39. It’s Raw! Audio Generation with State-Space ModelsOral256 citations
40. G-Mixup: Graph Data Augmentation for Graph ClassificationOral255 citations
41. Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein PocketsSpotlight246 citations
42. Improving Out-of-Distribution Robustness via Selective AugmentationSpotlight237 citations
43. Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time RetrievalSpotlight237 citations
44. Understanding The Robustness in Vision TransformersSpotlight235 citations
45. From data to functa: Your data point is a function and you can treat it like oneSpotlight222 citations
46. The Primacy Bias in Deep Reinforcement LearningSpotlight216 citations
47. Self-supervised learning with random-projection quantizer for speech recognitionSpotlight215 citations
48. What Language Model Architecture and Pretraining Objective Works Best for Zero-Shot Generalization?Spotlight214 citations
49. The Unsurprising Effectiveness of Pre-Trained Vision Models for ControlOral212 citations
50. Federated Learning with Partial Model PersonalizationSpotlight209 citations
51. Dataset Condensation via Efficient Synthetic-Data ParameterizationSpotlight207 citations
52. Biological Sequence Design with GFlowNetsSpotlight203 citations
53. Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious CorrelationsOral201 citations
54. Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and UnderstandingSpotlight200 citations
55. ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!Spotlight192 citations
56. Neurotoxin: Durable Backdoors in Federated LearningSpotlight189 citations
57. A Study of Face Obfuscation in ImageNetSpotlight184 citations
58. Generalized Federated Learning via Sharpness Aware MinimizationSpotlight182 citations
59. Towards Understanding Sharpness-Aware MinimizationSpotlight177 citations
60. Adaptive Conformal Predictions for Time SeriesSpotlight175 citations
61. Multi-Task Learning as a Bargaining GameSpotlight175 citations
62. Prioritized Training on Points that are Learnable, Worth Learning, and not yet LearntSpotlight173 citations
63. Prompting Decision Transformer for Few-Shot Policy GeneralizationSpotlight172 citations
64. ProGCL: Rethinking Hard Negative Mining in Graph Contrastive LearningSpotlight168 citations
65. Low-Complexity Deep Convolutional Neural Networks on Fully Homomorphic Encryption Using Multiplexed Parallel ConvolutionsSpotlight166 citations
66. Robustness and Accuracy Could Be Reconcilable by (Proper) DefinitionSpotlight166 citations
67. Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)Spotlight165 citations
68. DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse TrainingSpotlight165 citations
69. Generating 3D Molecules for Target Protein BindingOral162 citations
70. Online Continual Learning through Mutual Information MaximizationSpotlight162 citations
71. Adversarially Trained Actor Critic for Offline Reinforcement LearningOral160 citations
72. Graph-Coupled Oscillator NetworksSpotlight160 citations
73. Inductive Biases and Variable Creation in Self-Attention MechanismsSpotlight159 citations
74. A Closer Look at Smoothness in Domain Adversarial TrainingSpotlight157 citations
75. Robust Training under Label Noise by Over-parameterizationSpotlight154 citations
76. Privacy for Free: How does Dataset Condensation Help Privacy?Oral151 citations
77. Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral FusionSpotlight151 citations
78. Evolving Curricula with Regret-Based Environment DesignSpotlight148 citations
79. Forget-free Continual Learning with Winning SubnetworksSpotlight147 citations
80. Active Learning on a Budget: Opposite Strategies Suit High and Low BudgetsSpotlight145 citations
81. Understanding Contrastive Learning Requires Incorporating Inductive BiasesSpotlight141 citations
82. Local Augmentation for Graph Neural NetworksSpotlight140 citations
83. Dataset Condensation with Contrastive SignalsSpotlight139 citations
84. Particle Transformer for Jet TaggingSpotlight139 citations
85. ContentVec: An Improved Self-Supervised Speech Representation by Disentangling SpeakersSpotlight138 citations
86. Let Invariant Rationale Discovery Inspire Graph Contrastive LearningSpotlight138 citations
87. A Consistent and Efficient Evaluation Strategy for Attribution MethodsSpotlight137 citations
88. Overcoming Oscillations in Quantization-Aware TrainingOral135 citations
89. Reinforcement Learning with Action-Free Pre-Training from VideosSpotlight134 citations
90. Understanding Clipping for Federated Learning: Convergence and Client-Level Differential PrivacySpotlight133 citations
91. Understanding Gradient Descent on the Edge of Stability in Deep LearningSpotlight132 citations
92. POEM: Out-of-Distribution Detection with Posterior SamplingOral131 citations
93. Penalizing Gradient Norm for Efficiently Improving Generalization in Deep LearningSpotlight130 citations
94. Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPsSpotlight130 citations
95. Learning from Counterfactual Links for Link PredictionSpotlight129 citations
96. Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence ModelingSpotlight128 citations
97. XAI for Transformers: Better Explanations through Conservative PropagationSpotlight128 citations
98. Do Differentiable Simulators Give Better Policy Gradients?Oral127 citations
99. Flowformer: Linearizing Transformers with Conservation FlowsSpotlight127 citations
100. Personalized Federated Learning through Local MemorizationSpotlight126 citations
101. CITRIS: Causal Identifiability from Temporal Intervened SequencesSpotlight125 citations
102. On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained FeaturesSpotlight125 citations
103. Causal Transformer for Estimating Counterfactual OutcomesSpotlight124 citations
104. Characterizing and Overcoming the Greedy Nature of Learning in Multi-modal Deep Neural NetworksSpotlight123 citations
105. Matching Structure for Dual LearningSpotlight123 citations
106. Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)Spotlight123 citations
107. Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain AdaptationOral122 citations
108. Personalized Federated Learning via Variational Bayesian InferenceSpotlight122 citations
109. Class-Imbalanced Semi-Supervised Learning with Adaptive ThresholdingSpotlight120 citations
110. Communication-Efficient Adaptive Federated LearningSpotlight120 citations
111. Generative Flow Networks for Discrete Probabilistic ModelingSpotlight120 citations
112. A data-driven approach for learning to control computersSpotlight119 citations
113. Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in ImagingSpotlight119 citations
114. The CLRS Algorithmic Reasoning BenchmarkSpotlight119 citations
115. Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample ComplexitySpotlight116 citations
116. Adversarial Masking for Self-Supervised LearningSpotlight115 citations
117. Confidence Score for Source-Free Unsupervised Domain AdaptationSpotlight115 citations
118. Modeling Irregular Time Series with Continuous Recurrent UnitsSpotlight115 citations
119. Training OOD Detectors in their Natural HabitatsSpotlight115 citations
120. Accelerating Bayesian Optimization for Biological Sequence Design with Denoising AutoencodersSpotlight113 citations
121. Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier GuidanceSpotlight112 citations
122. Design-Bench: Benchmarks for Data-Driven Offline Model-Based OptimizationSpotlight111 citations
123. Extended Unconstrained Features Model for Exploring Deep Neural CollapseSpotlight111 citations
124. Monarch: Expressive Structured Matrices for Efficient and Accurate TrainingOral111 citations
125. Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated LearningSpotlight111 citations
126. Domain Adaptation for Time Series Forecasting via Attention SharingSpotlight110 citations
127. Learning Domain Adaptive Object Detection with Probabilistic TeacherSpotlight110 citations
128. Meaningfully debugging model mistakes using conceptual counterfactual explanationsSpotlight108 citations
129. Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level OptimizationSpotlight108 citations
130. Balancing Discriminability and Transferability for Source-Free Domain AdaptationSpotlight107 citations
131. Benchmarking and Analyzing Point Cloud Classification under CorruptionsSpotlight106 citations
132. Fishing for User Data in Large-Batch Federated Learning via Gradient MagnificationSpotlight106 citations
133. PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight ImportanceSpotlight106 citations
134. Neural-Symbolic Models for Logical Queries on Knowledge GraphsSpotlight105 citations
135. Linear Adversarial Concept ErasureSpotlight104 citations
136. Partial Counterfactual Identification from Observational and Experimental DataSpotlight103 citations
137. Score Matching Enables Causal Discovery of Nonlinear Additive Noise ModelsOral103 citations
138. Sharp-MAML: Sharpness-Aware Model-Agnostic Meta LearningSpotlight103 citations
139. Structural Entropy Guided Graph Hierarchical PoolingSpotlight103 citations
140. Constrained Variational Policy Optimization for Safe Reinforcement LearningSpotlight101 citations
141. Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex RegularizationSpotlight100 citations
142. To Smooth or Not? When Label Smoothing Meets Noisy LabelsOral99 citations
143. Discriminator-Weighted Offline Imitation Learning from Suboptimal DemonstrationsSpotlight98 citations
144. Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic ConvergenceOral97 citations
145. Plug & Play Attacks: Towards Robust and Flexible Model Inversion AttacksSpotlight97 citations
146. Deep Safe Incomplete Multi-view Clustering: Theorem and AlgorithmSpotlight96 citations
147. Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly DetectionSpotlight96 citations
148. FedNL: Making Newton-Type Methods Applicable to Federated LearningSpotlight96 citations
149. ViT-NeT: Interpretable Vision Transformers with Neural Tree DecoderSpotlight96 citations
150. Approximately Equivariant Networks for Imperfectly Symmetric DynamicsSpotlight95 citations
151. Revisiting Consistency Regularization for Deep Partial Label LearningSpotlight95 citations
152. HyperPrompt: Prompt-based Task-Conditioning of TransformersSpotlight94 citations
153. Maximum Likelihood Training for Score-based Diffusion ODEs by High Order Denoising Score MatchingSpotlight94 citations
154. Head2Toe: Utilizing Intermediate Representations for Better Transfer LearningOral93 citations
155. HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot LearningSpotlight92 citations
156. Learning to Cut by Looking Ahead: Cutting Plane Selection via Imitation LearningSpotlight92 citations
157. Inducing Causal Structure for Interpretable Neural NetworksSpotlight91 citations
158. SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled CodebooksSpotlight91 citations
159. Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score EstimationSpotlight91 citations
160. Latent Diffusion Energy-Based Model for Interpretable Text ModellingSpotlight90 citations
161. Understanding Robust Overfitting of Adversarial Training and BeyondSpotlight90 citations
162. Understanding the unstable convergence of gradient descentSpotlight90 citations
163. AutoSNN: Towards Energy-Efficient Spiking Neural NetworksSpotlight89 citations
164. Evaluating the Adversarial Robustness of Adaptive Test-time DefensesSpotlight89 citations
165. Policy Gradient Method For Robust Reinforcement LearningSpotlight89 citations
166. HyperImpute: Generalized Iterative Imputation with Automatic Model SelectionSpotlight88 citations
167. Transformers are Meta-Reinforcement LearnersSpotlight88 citations
168. Federated Reinforcement Learning: Linear Speedup Under Markovian SamplingOral87 citations
169. Offline Meta-Reinforcement Learning with Online Self-SupervisionSpotlight87 citations
170. Saute RL: Almost Surely Safe Reinforcement Learning Using State AugmentationSpotlight87 citations
171. Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic ModelsSpotlight86 citations
172. Fisher SAM: Information Geometry and Sharpness Aware MinimisationSpotlight86 citations
173. More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations GeneralizeSpotlight86 citations
174. A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron AttributionsSpotlight85 citations
175. How to Leverage Unlabeled Data in Offline Reinforcement LearningSpotlight85 citations
176. Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic DataSpotlight85 citations
177. DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated LearningSpotlight84 citations
178. Detecting Corrupted Labels Without Training a Model to PredictSpotlight84 citations
179. Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function ApproximationSpotlight84 citations
180. Anarchic Federated LearningOral83 citations
181. Bayesian Model Selection, the Marginal Likelihood, and GeneralizationOral83 citations
182. Sparse Invariant Risk MinimizationSpotlight83 citations
183. SE(3) Equivariant Graph Neural Networks with Complete Local FramesSpotlight82 citations
184. Wide Neural Networks Forget Less CatastrophicallySpotlight82 citations
185. FedNest: Federated Bilevel, Minimax, and Compositional OptimizationOral81 citations
186. Guarantees for Epsilon-Greedy Reinforcement Learning with Function ApproximationSpotlight81 citations
187. Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and CostsSpotlight81 citations
188. Partial disentanglement for domain adaptationSpotlight81 citations
189. SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph GeneratorsSpotlight81 citations
190. On the Adversarial Robustness of Causal Algorithmic RecourseSpotlight80 citations
191. SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic QuantizationSpotlight80 citations
192. Universal Hopfield Networks: A General Framework for Single-Shot Associative Memory ModelsSpotlight80 citations
193. Detecting Adversarial Examples Is (Nearly) As Hard As Classifying ThemOral79 citations
194. Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning approachSpotlight79 citations
195. General-purpose, long-context autoregressive modeling with Perceiver ARSpotlight79 citations
196. Generalization and Robustness Implications in Object-Centric LearningSpotlight79 citations
197. Knowledge Base Question Answering by Case-based Reasoning over SubgraphsSpotlight79 citations
198. Secure Quantized Training for Deep LearningSpotlight79 citations
199. Unified Scaling Laws for Routed Language ModelsOral79 citations
200. Achieving Fairness at No Utility Cost via Data Reweighing with InfluenceSpotlight78 citations
201. De novo mass spectrometry peptide sequencing with a transformer modelSpotlight78 citations
202. Frustratingly Easy Transferability EstimationSpotlight78 citations
203. Flow-Guided Sparse Transformer for Video DeblurringSpotlight77 citations
204. Latent Outlier Exposure for Anomaly Detection with Contaminated DataSpotlight77 citations
205. On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement LearningSpotlight77 citations
206. On the Practicality of Deterministic Epistemic UncertaintySpotlight77 citations
207. Orchestra: Unsupervised Federated Learning via Globally Consistent ClusteringSpotlight77 citations
208. The Fundamental Price of Secure Aggregation in Differentially Private Federated LearningSpotlight77 citations
209. Translatotron 2: High-quality direct speech-to-speech translation with voice preservationSpotlight77 citations
210. Byzantine Machine Learning Made Easy By Resilient Averaging of MomentumsSpotlight76 citations
211. Fast Finite Width Neural Tangent KernelSpotlight76 citations
212. On the Equivalence Between Temporal and Static Equivariant Graph RepresentationsSpotlight76 citations
213. Reachability Constrained Reinforcement LearningSpotlight76 citations
214. When and How Mixup Improves CalibrationSpotlight76 citations
215. Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated LearningSpotlight75 citations
216. Lie Point Symmetry Data Augmentation for Neural PDE SolversSpotlight75 citations
217. Multi-Level Branched Regularization for Federated LearningSpotlight74 citations
218. Variational Wasserstein gradient flowSpotlight74 citations
219. Adaptive Second Order Coresets for Data-efficient Machine LearningSpotlight73 citations
220. Neuro-Symbolic Language Modeling with Automaton-augmented RetrievalSpotlight73 citations
221. Bounding Training Data Reconstruction in Private (Deep) LearningOral72 citations
222. Geometric Multimodal Contrastive Representation LearningSpotlight72 citations
223. Improved Certified Defenses against Data Poisoning with (Deterministic) Finite AggregationSpotlight72 citations
224. Measuring the Effect of Training Data on Deep Learning Predictions via Randomized ExperimentsSpotlight72 citations
225. Causal structure-based root cause analysis of outliersSpotlight71 citations
226. Decision-Focused Learning: Through the Lens of Learning to RankSpotlight71 citations
227. TAM: Topology-Aware Margin Loss for Class-Imbalanced Node ClassificationSpotlight71 citations
228. Framework for Evaluating Faithfulness of Local ExplanationsSpotlight70 citations
229. IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and LanguagesSpotlight70 citations
230. Representation Topology Divergence: A Method for Comparing Neural Network Representations.Spotlight70 citations
231. Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision ProcessesSpotlight70 citations
232. Scalable Deep Reinforcement Learning Algorithms for Mean Field GamesSpotlight70 citations
233. The Power of Exploiter: Provable Multi-Agent RL in Large State SpacesSpotlight70 citations
234. Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and MomentumOral69 citations
235. Directed Acyclic Transformer for Non-Autoregressive Machine TranslationSpotlight69 citations
236. Faster Fundamental Graph Algorithms via Learned PredictionsSpotlight69 citations
237. NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse NetworksSpotlight69 citations
238. Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor RectificationSpotlight69 citations
239. DAVINZ: Data Valuation using Deep Neural Networks at InitializationSpotlight68 citations
240. Dialog Inpainting: Turning Documents into DialogsSpotlight68 citations
241. Identification of Linear Non-Gaussian Latent Hierarchical StructureSpotlight68 citations
242. Investigating Why Contrastive Learning Benefits Robustness against Label NoiseSpotlight68 citations
243. Molecular Representation Learning via Heterogeneous Motif Graph Neural NetworksSpotlight68 citations
244. Public Data-Assisted Mirror Descent for Private Model TrainingSpotlight68 citations
245. Retroformer: Pushing the Limits of End-to-end Retrosynthesis TransformerSpotlight68 citations
246. Modeling Strong and Human-Like Gameplay with KL-Regularized SearchSpotlight67 citations
247. ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive TrainingSpotlight67 citations
248. DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical RepresentationsSpotlight66 citations
249. HousE: Knowledge Graph Embedding with Householder ParameterizationSpotlight66 citations
250. Model-Free Opponent ShapingSpotlight66 citations
251. RieszNet and ForestRiesz: Automatic Debiased Machine Learning with Neural Nets and Random ForestsOral66 citations
252. Causal Conceptions of Fairness and their ConsequencesOral65 citations
253. Certified Neural Network Watermarks with Randomized SmoothingSpotlight65 citations
254. Align-RUDDER: Learning From Few Demonstrations by Reward RedistributionOral64 citations
255. Data Augmentation as Feature ManipulationSpotlight64 citations
256. Distributionally Robust $Q$-LearningSpotlight64 citations
257. Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural NetworkSpotlight64 citations
258. Model Agnostic Sample Reweighting for Out-of-Distribution LearningSpotlight64 citations
259. Personalization Improves Privacy-Accuracy Tradeoffs in Federated LearningSpotlight64 citations
260. Zero-Shot Reward Specification via Grounded Natural LanguageSpotlight64 citations
261. Architecture Agnostic Federated Learning for Neural NetworksSpotlight63 citations
262. RankSim: Ranking Similarity Regularization for Deep Imbalanced RegressionSpotlight63 citations
263. Robust Counterfactual Explanations for Tree-Based EnsemblesSpotlight63 citations
264. 3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker DesignOral62 citations
265. A Theoretical Comparison of Graph Neural Network ExtensionsSpotlight62 citations
266. COLA: Consistent Learning with Opponent-Learning AwarenessSpotlight62 citations
267. Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward PassSpotlight62 citations
268. Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal controlSpotlight62 citations
269. Federated Minimax Optimization: Improved Convergence Analyses and AlgorithmsSpotlight62 citations
270. Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed DataOral62 citations
271. Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive LearningSpotlight62 citations
272. StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering ModelsSpotlight62 citations
273. A Differential Entropy Estimator for Training Neural NetworksSpotlight61 citations
274. Active Sampling for Min-Max FairnessSpotlight61 citations
275. Co-training Improves Prompt-based Learning for Large Language ModelsSpotlight61 citations
276. Imitation Learning by Estimating Expertise of DemonstratorsSpotlight61 citations
277. Antibody-Antigen Docking and Design via Hierarchical Structure RefinementSpotlight60 citations
278. Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential EquationsSpotlight60 citations
279. Exact Optimal Accelerated Complexity for Fixed-Point IterationsOral60 citations
280. Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive LearningSpotlight60 citations
281. The Poisson Binomial Mechanism for Unbiased Federated Learning with Secure AggregationOral60 citations
282. Calibrated Learning to Defer with One-vs-All ClassifiersSpotlight59 citations
283. Channel Importance Matters in Few-Shot Image ClassificationSpotlight59 citations
284. Denoised MDPs: Learning World Models Better Than the World ItselfSpotlight59 citations
285. EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated LearningSpotlight59 citations
286. Estimating and Penalizing Induced Preference Shifts in Recommender SystemsSpotlight59 citations
287. NP-Match: When Neural Processes meet Semi-Supervised LearningSpotlight59 citations
288. Optimizing Sequential Experimental Design with Deep Reinforcement LearningSpotlight59 citations
289. Retrieval-Augmented Reinforcement LearningSpotlight59 citations
290. Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement LearningOral59 citations
291. Towards understanding how momentum improves generalization in deep learningSpotlight59 citations
292. Accelerated Federated Learning with Decoupled Adaptive OptimizationSpotlight58 citations
293. Fairness with Adaptive WeightsSpotlight58 citations
294. Implicit Bias of the Step Size in Linear Diagonal Neural NetworksSpotlight58 citations
295. NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient FrameworkSpotlight58 citations
296. The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural NetworksSpotlight58 citations
297. A Multi-objective / Multi-task Learning Framework Induced by Pareto StationaritySpotlight57 citations
298. Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality FeaturesSpotlight57 citations
299. Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned DataSpotlight57 citations
300. Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor DefenseSpotlight57 citations
301. LIMO: Latent Inceptionism for Targeted Molecule GenerationSpotlight57 citations
302. LyaNet: A Lyapunov Framework for Training Neural ODEsSpotlight57 citations
303. Offline RL Policies Should Be Trained to be AdaptiveOral57 citations
304. Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed RecognitionOral57 citations
305. Rethinking Attention-Model Explainability through Faithfulness Violation TestSpotlight57 citations
306. A Dynamical System Perspective for Lipschitz Neural NetworksOral56 citations
307. Causal Dynamics Learning for Task-Independent State AbstractionOral56 citations
308. Information Discrepancy in Strategic LearningSpotlight56 citations
309. On Implicit Bias in Overparameterized Bilevel OptimizationSpotlight56 citations
310. Anticorrelated Noise Injection for Improved GeneralizationSpotlight55 citations
311. Continual Learning via Sequential Function-Space Variational InferenceSpotlight55 citations
312. Making Linear MDPs Practical via Contrastive Representation LearningSpotlight55 citations
313. POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and PagingSpotlight55 citations
314. Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian OptimizationSpotlight55 citations
315. Self-Supervised Models of Audio Effectively Explain Human Cortical Responses to SpeechSpotlight55 citations
316. A Langevin-like Sampler for Discrete DistributionsSpotlight54 citations
317. A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and EditingSpotlight54 citations
318. Improving Task-free Continual Learning by Distributionally Robust Memory EvolutionSpotlight54 citations
319. Optimal Algorithms for Mean Estimation under Local Differential PrivacyOral54 citations
320. Proximal Exploration for Model-guided Protein Sequence DesignSpotlight54 citations
321. Removing Batch Normalization Boosts Adversarial TrainingSpotlight54 citations
322. Smoothed Adaptive Weighting for Imbalanced Semi-Supervised Learning: Improve Reliability Against Unknown Distribution DataSpotlight54 citations
323. Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity TransferringSpotlight53 citations
324. FriendlyCore: Practical Differentially Private AggregationSpotlight53 citations
325. MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay BufferSpotlight53 citations
326. Predicting Out-of-Distribution Error with the Projection NormSpotlight53 citations
327. Continual Repeated Annealed Flow Transport Monte CarloSpotlight52 citations
328. Hierarchical Shrinkage: Improving the accuracy and interpretability of tree-based models.Oral52 citations
329. No-Regret Learning in Time-Varying Zero-Sum GamesSpotlight52 citations
330. Off-Policy Evaluation for Large Action Spaces via EmbeddingsSpotlight52 citations
331. On Last-Iterate Convergence Beyond Zero-Sum GamesSpotlight52 citations
332. Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline DatasetsSpotlight52 citations
333. Provable Reinforcement Learning with a Short-Term MemorySpotlight52 citations
334. Proximal and Federated Random ReshufflingSpotlight52 citations
335. Selective Network Linearization for Efficient Private InferenceSpotlight52 citations
336. SpeqNets: Sparsity-aware permutation-equivariant graph networksSpotlight52 citations
337. TACTiS: Transformer-Attentional Copulas for Time SeriesSpotlight52 citations
338. Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed SensingSpotlight52 citations
339. Conditional GANs with Auxiliary Discriminative ClassifierSpotlight51 citations
340. Datamodels: Understanding Predictions with Data and Data with PredictionsSpotlight51 citations
341. Online Learning with Knapsacks: the Best of Both WorldsSpotlight51 citations
342. Equivariant Quantum Graph CircuitsSpotlight50 citations
343. History Compression via Language Models in Reinforcement LearningSpotlight50 citations
344. Improving Mini-batch Optimal Transport via Partial TransportationSpotlight50 citations
345. VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMixSpotlight50 citations
346. A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision ProcessesOral49 citations
347. DRIBO: Robust Deep Reinforcement Learning via Multi-View Information BottleneckSpotlight49 citations
348. Data Scaling Laws in NMT: The Effect of Noise and ArchitectureSpotlight49 citations
349. Do More Negative Samples Necessarily Hurt In Contrastive Learning?Oral49 citations
350. GraphFM: Improving Large-Scale GNN Training via Feature MomentumSpotlight49 citations
351. Learning Symmetric Embeddings for Equivariant World ModelsSpotlight49 citations
352. Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement LearningSpotlight49 citations
353. Rich Feature Construction for the Optimization-Generalization DilemmaSpotlight49 citations
354. The power of first-order smooth optimization for black-box non-smooth problemsSpotlight49 citations
355. A Tree-based Model Averaging Approach for Personalized Treatment Effect Estimation from Heterogeneous Data SourcesSpotlight48 citations
356. A new similarity measure for covariate shift with applications to nonparametric regressionOral48 citations
357. Action-Sufficient State Representation Learning for Control with Structural ConstraintsSpotlight48 citations
358. DynaMixer: A Vision MLP Architecture with Dynamic MixingSpotlight48 citations
359. FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated LearningSpotlight48 citations
360. Generative Coarse-Graining of Molecular ConformationsSpotlight48 citations
361. Going Deeper into Permutation-Sensitive Graph Neural NetworksSpotlight48 citations
362. Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?Spotlight48 citations
363. SPDY: Accurate Pruning with Speedup GuaranteesSpotlight48 citations
364. Sample Efficient Learning of Predictors that Complement HumansSpotlight48 citations
365. Stabilizing Off-Policy Deep Reinforcement Learning from PixelsSpotlight48 citations
366. UNIREX: A Unified Learning Framework for Language Model Rationale ExtractionSpotlight48 citations
367. Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and BeyondSpotlight48 citations
368. Generalizing to New Physical Systems via Context-Informed Dynamics ModelSpotlight47 citations
369. MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object DetectionSpotlight47 citations
370. Regret Minimization with Performative FeedbackSpotlight47 citations
371. State Transition of Dendritic Spines Improves Learning of Sparse Spiking Neural NetworksSpotlight47 citations
372. Topology-aware Generalization of Decentralized SGDSpotlight47 citations
373. Variational nearest neighbor Gaussian processSpotlight47 citations
374. Convergence of Uncertainty Sampling for Active LearningSpotlight46 citations
375. Curriculum Reinforcement Learning via Constrained Optimal TransportSpotlight46 citations
376. DNA: Domain Generalization with Diversified Neural AveragingSpotlight46 citations
377. Direct Behavior Specification via Constrained Reinforcement LearningSpotlight46 citations
378. Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message PassingSpotlight46 citations
379. Linear Complexity Randomized Self-attention MechanismSpotlight46 citations
380. MAML and ANIL Provably Learn RepresentationsSpotlight46 citations
381. Matching Normalizing Flows and Probability Paths on ManifoldsSpotlight46 citations
382. Online Algorithms with Multiple PredictionsSpotlight46 citations
383. Optimistic Linear Support and Successor Features as a Basis for Optimal Policy TransferSpotlight46 citations
384. SDQ: Stochastic Differentiable Quantization with Mixed PrecisionSpotlight46 citations
385. Tell me why! Explanations support learning relational and causal structureSpotlight46 citations
386. Validating Causal Inference MethodsSpotlight46 citations
387. Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy MatchingSpotlight46 citations
388. Algorithms for the Communication of SamplesSpotlight45 citations
389. Doubly Robust Distributionally Robust Off-Policy Evaluation and LearningSpotlight45 citations
390. GNNRank: Learning Global Rankings from Pairwise Comparisons via Directed Graph Neural NetworksSpotlight45 citations
391. Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label ClassificationSpotlight45 citations
392. Learning to Solve PDE-constrained Inverse Problems with Graph NetworksSpotlight45 citations
393. Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasetsSpotlight45 citations
394. Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware TrainingSpotlight45 citations
395. Region-Based Semantic Factorization in GANsSpotlight45 citations
396. Robust Multi-Objective Bayesian Optimization Under Input NoiseSpotlight45 citations
397. Coarsening the Granularity: Towards Structurally Sparse Lottery TicketsSpotlight44 citations
398. Optimization-Induced Graph Implicit Nonlinear DiffusionSpotlight44 citations
399. Staged Training for Transformer Language ModelsSpotlight44 citations
400. A Modern Self-Referential Weight Matrix That Learns to Modify ItselfSpotlight43 citations
401. A New Perspective on the Effects of Spectrum in Graph Neural NetworksSpotlight43 citations
402. Bisimulation Makes Analogies in Goal-Conditioned Reinforcement LearningSpotlight43 citations
403. Differentiable Top-k Classification LearningSpotlight43 citations
404. First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation ApproachOral43 citations
405. H-Consistency Bounds for Surrogate Loss MinimizersOral43 citations
406. Individual Reward Assisted Multi-Agent Reinforcement LearningSpotlight43 citations
407. Langevin Monte Carlo for Contextual BanditsSpotlight43 citations
408. Neuro-Symbolic Hierarchical Rule InductionSpotlight43 citations
409. Not All Poisons are Created Equal: Robust Training against Data PoisoningOral43 citations
410. Off-Policy Reinforcement Learning with Delayed RewardsSpotlight43 citations
411. Self-Supervised Representation Learning via Latent Graph PredictionSpotlight43 citations
412. The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of AttentionSpotlight43 citations
413. Certified Robustness Against Natural Language Attacks by Causal InterventionSpotlight42 citations
414. Exploiting Redundancy: Separable Group Convolutional Networks on Lie GroupsSpotlight42 citations
415. Locally Sparse Neural Networks for Tabular Biomedical DataSpotlight42 citations
416. Probabilistically Robust Learning: Balancing Average and Worst-case PerformanceSpotlight42 citations
417. Revisiting End-to-End Speech-to-Text Translation From ScratchSpotlight42 citations
418. A Simple Reward-free Approach to Constrained Reinforcement LearningSpotlight41 citations
419. Loss Function Learning for Domain Generalization by Implicit GradientSpotlight41 citations
420. MetAug: Contrastive Learning via Meta Feature AugmentationSpotlight41 citations
421. On the Finite-Time Complexity and Practical Computation of Approximate Stationarity Concepts of Lipschitz FunctionsSpotlight41 citations
422. Resilient and Communication Efficient Learning for Heterogeneous Federated SystemsSpotlight41 citations
423. The Importance of Non-Markovianity in Maximum State Entropy ExplorationOral41 citations
424. Training Your Sparse Neural Network Better with Any MaskSpotlight41 citations
425. Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value ErrorSpotlight41 citations
426. A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU NetworksSpotlight40 citations
427. A Context-Integrated Transformer-Based Neural Network for Auction DesignSpotlight40 citations
428. Active fairness auditingOral40 citations
429. Contextual Bandits with Large Action Spaces: Made PracticalSpotlight40 citations
430. Contrastive Learning with Boosted MemorizationSpotlight40 citations
431. Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement LearningSpotlight40 citations
432. Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form GamesSpotlight40 citations
433. Probabilistic Bilevel Coreset SelectionSpotlight40 citations
434. $p$-Laplacian Based Graph Neural NetworksSpotlight39 citations
435. Adapting the Linearised Laplace Model Evidence for Modern Deep LearningSpotlight39 citations
436. Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation LearningSpotlight39 citations
437. Learning Augmented Binary Search TreesSpotlight39 citations
438. Learning Dynamics and Generalization in Deep Reinforcement LearningSpotlight39 citations
439. Near-Exact Recovery for Tomographic Inverse Problems via Deep LearningOral39 citations
440. NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance FieldsSpotlight39 citations
441. Addressing Optimism Bias in Sequence Modeling for Reinforcement LearningSpotlight38 citations
442. Constraint-based graph network simulatorSpotlight38 citations
443. Continuous Control with Action Quantization from DemonstrationsSpotlight38 citations
444. Controlling Conditional Language Models without Catastrophic ForgettingSpotlight38 citations
445. Learning Infinite-horizon Average-reward Markov Decision Process with ConstraintsSpotlight38 citations
446. Nearly Minimax Optimal Reinforcement Learning with Linear Function ApproximationSpotlight38 citations
447. Neural Language Models are not Born Equal to Fit Brain Data, but Training HelpsSpotlight38 citations
448. Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and InitializationSpotlight38 citations
449. On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy EvaluationSpotlight38 citations
450. Private Adaptive Optimization with Side informationSpotlight38 citations
451. Provable Domain Generalization via Invariant-Feature Subspace RecoverySpotlight38 citations
452. The Neural Race Reduction: Dynamics of Abstraction in Gated NetworksSpotlight38 citations
453. The State of Sparse Training in Deep Reinforcement LearningSpotlight38 citations
454. Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical SystemsSpotlight38 citations
455. Unaligned Supervision for Automatic Music Transcription in The WildSpotlight38 citations
456. Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision TransformersSpotlight38 citations
457. Adapting to Mixing Time in Stochastic Optimization with Markovian DataOral37 citations
458. Calibrated and Sharp Uncertainties in Deep Learning via Density EstimationSpotlight37 citations
459. Conformal Prediction Sets with Limited False PositivesSpotlight37 citations
460. Fast Relative Entropy Coding with A* codingSpotlight37 citations
461. From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked TransformersSpotlight37 citations
462. GACT: Activation Compressed Training for Generic Network ArchitecturesSpotlight37 citations
463. How to Stay Curious while avoiding Noisy TVs using Aleatoric Uncertainty EstimationSpotlight37 citations
464. Knowledge-Grounded Self-Rationalization via Extractive and Natural Language ExplanationsSpotlight37 citations
465. Learning to Predict Graphs with Fused Gromov-Wasserstein BarycentersSpotlight37 citations
466. Neural Laplace: Learning diverse classes of differential equations in the Laplace domainOral37 citations
467. On Numerical Integration in Neural Ordinary Differential EquationsSpotlight37 citations
468. Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization GuaranteesSpotlight37 citations
469. Sample-Efficient Reinforcement Learning with loglog(T) Switching CostSpotlight37 citations
470. Sparse Double Descent: Where Network Pruning Aggravates OverfittingSpotlight37 citations
471. Towards Scaling Difference Target Propagation by Learning Backprop TargetsSpotlight37 citations
472. Understanding Instance-Level Impact of Fairness ConstraintsSpotlight37 citations
473. When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence GuaranteeSpotlight37 citations
474. 3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy AggregationSpotlight36 citations
475. A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift GeneralizationSpotlight36 citations
476. Causal Imitation Learning under Temporally Correlated NoiseOral36 citations
477. Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-DimensionSpotlight36 citations
478. How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient RedirectionSpotlight36 citations
479. Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural NetworksSpotlight36 citations
480. Improving Transformers with Probabilistic Attention KeysSpotlight36 citations
481. Koopman Q-learning: Offline Reinforcement Learning via Symmetries of DynamicsSpotlight36 citations
482. Learning Stochastic Shortest Path with Linear Function ApproximationSpotlight36 citations
483. Near-Optimal Learning of Extensive-Form Games with Imperfect InformationSpotlight36 citations
484. On Measuring Causal Contributions via do-interventionsSpotlight36 citations
485. PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information CollaborationSpotlight36 citations
486. Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time AnalysisSpotlight36 citations
487. Symmetric Machine Theory of MindSpotlight36 citations
488. A Psychological Theory of ExplainabilitySpotlight35 citations
489. Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core QuantitiesSpotlight35 citations
490. Constrained Discrete Black-Box Optimization using Mixed-Integer ProgrammingSpotlight35 citations
491. Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone DecompositionsSpotlight35 citations
492. Graph Neural Architecture Search Under Distribution ShiftsSpotlight35 citations
493. Preconditioning for Scalable Gaussian Process Hyperparameter OptimizationOral35 citations
494. Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the $O(ε^-7/4)$ ComplexitySpotlight35 citations
495. Selling Data To a Machine Learner: Pricing via Costly SignalingSpotlight35 citations
496. You Only Cut Once: Boosting Data Augmentation with a Single CutSpotlight35 citations
497. Additive Gaussian Processes RevisitedSpotlight34 citations
498. Equivariance versus Augmentation for Spherical ImagesSpotlight34 citations
499. Finite-Sum Coupled Compositional Stochastic Optimization: Theory and ApplicationsSpotlight34 citations
500. Interventional Contrastive Learning with Meta Semantic RegularizerSpotlight34 citations
501. Nonlinear Feature Diffusion on HypergraphsSpotlight34 citations
502. Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RLSpotlight34 citations
503. Re-evaluating Word Mover’s DistanceOral34 citations
504. Robust Training of Neural Networks Using Scale Invariant ArchitecturesOral34 citations
505. Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity ModelsSpotlight34 citations
506. Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic ResponsesSpotlight34 citations
507. Utilizing Expert Features for Contrastive Learning of Time-Series RepresentationsSpotlight34 citations
508. AnyMorph: Learning Transferable Polices By Inferring Agent MorphologySpotlight33 citations
509. EqR: Equivariant Representations for Data-Efficient Reinforcement LearningSpotlight33 citations
510. Exploring the Gap between Collapsed & Whitened Features in Self-Supervised LearningSpotlight33 citations
511. From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative ModelSpotlight33 citations
512. In defense of dual-encoders for neural rankingSpotlight33 citations
513. Learning-based Optimisation of Particle Accelerators Under Partial Observability Without Real-World TrainingSpotlight33 citations
514. Lyapunov Density Models: Constraining Distribution Shift in Learning-Based ControlSpotlight33 citations
515. Robust Deep Reinforcement Learning through Bootstrapped Opportunistic CurriculumSpotlight33 citations
516. Selective Regression under Fairness CriteriaSpotlight33 citations
517. Winning the Lottery Ahead of Time: Efficient Early Network PruningSpotlight33 citations
518. Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed ScaffoldSpotlight32 citations
519. Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape GeometrySpotlight32 citations
520. Divergence-Regularized Multi-Agent Actor-CriticSpotlight32 citations
521. GALAXY: Graph-based Active Learning at the ExtremeSpotlight32 citations
522. Generalized Strategic Classification and the Case of Aligned IncentivesOral32 citations
523. Large-Scale Graph Neural Architecture SearchSpotlight32 citations
524. Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear RegressionOral32 citations
525. NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation LearningSpotlight32 citations
526. QSFL: A Two-Level Uplink Communication Optimization Framework for Federated LearningSpotlight32 citations
527. What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us?Spotlight32 citations
528. A Natural Actor-Critic Framework for Zero-Sum Markov GamesSpotlight31 citations
529. A Simple Unified Framework for High Dimensional Bandit ProblemsSpotlight31 citations
530. Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement LearningSpotlight31 citations
531. Cycle Representation Learning for Inductive Relation PredictionSpotlight31 citations
532. GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized SmoothingSpotlight31 citations
533. Gaussian Process Uniform Error Bounds with Unknown Hyperparameters for Safety-Critical ApplicationsSpotlight31 citations
534. Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology SamplingSpotlight31 citations
535. Intriguing Properties of Input-Dependent Randomized SmoothingSpotlight31 citations
536. Mirror Learning: A Unifying Framework of Policy OptimisationSpotlight31 citations
537. Mitigating Modality Collapse in Multimodal VAEs via Impartial OptimizationSpotlight31 citations
538. Non-Vacuous Generalisation Bounds for Shallow Neural NetworksSpotlight31 citations
539. Nyström Kernel Mean EmbeddingsSpotlight31 citations
540. On Distribution Shift in Learning-based Bug DetectorsSpotlight31 citations
541. Parsimonious Learning-Augmented CachingSpotlight31 citations
542. Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm PerformanceSpotlight31 citations
543. Quantum-Inspired Algorithms from Randomized Numerical Linear AlgebraSpotlight31 citations
544. Robustness Implies Generalization via Data-Dependent Generalization BoundsOral31 citations
545. Role-based Multiplex Network EmbeddingSpotlight31 citations
546. Subspace Learning for Effective Meta-LearningSpotlight31 citations
547. Value Function based Difference-of-Convex Algorithm for Bilevel Hyperparameter Selection ProblemsSpotlight31 citations
548. A Statistical Manifold Framework for Point Cloud DataSpotlight30 citations
549. Adversarially trained neural representations are already as robust as biological neural representationsOral30 citations
550. Boosting Graph Structure Learning with Dummy NodesSpotlight30 citations
551. Differentially Private Approximate QuantilesSpotlight30 citations
552. Fair Representation Learning through Implicit Path AlignmentSpotlight30 citations
553. Flashlight: Enabling Innovation in Tools for Machine LearningSpotlight30 citations
554. Instrumental Variable Regression with Confounder BalancingSpotlight30 citations
555. ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart DiseasesSpotlight30 citations
556. Multi-scale Feature Learning Dynamics: Insights for Double DescentSpotlight30 citations
557. On the Difficulty of Defending Self-Supervised Learning against Model ExtractionSpotlight30 citations
558. Robust Models Are More Interpretable Because Attributions Look NormalSpotlight30 citations
559. Stochastic Rising BanditsSpotlight30 citations
560. Tight and Robust Private Mean Estimation with Few UsersOral30 citations
561. UAST: Uncertainty-Aware Siamese TrackingSpotlight30 citations
562. An Equivalence Between Data Poisoning and Byzantine Gradient AttacksSpotlight29 citations
563. Bitwidth Heterogeneous Federated Learning with Progressive Weight DequantizationSpotlight29 citations
564. Causal Inference Through the Structural Causal Marginal ProblemSpotlight29 citations
565. Composing Partial Differential Equations with Physics-Aware Neural NetworksSpotlight29 citations
566. Context-Aware Drift DetectionSpotlight29 citations
567. Deep symbolic regression for recurrence predictionSpotlight29 citations
568. Distribution Regression with Sliced Wasserstein KernelsSpotlight29 citations
569. Double Sampling Randomized SmoothingSpotlight29 citations
570. Federated Learning with Positive and Unlabeled DataSpotlight29 citations
571. Gradient Descent on Neurons and its Link to Approximate Second-order OptimizationSpotlight29 citations
572. Hermite Polynomial Features for Private Data GenerationSpotlight29 citations
573. High Probability Guarantees for Nonconvex Stochastic Gradient Descent with Heavy TailsSpotlight29 citations
574. Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy SearchSpotlight29 citations
575. On the Surrogate Gap between Contrastive and Supervised LossesSpotlight29 citations
576. Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise ImagesSpotlight29 citations
577. Quant-BnB: A Scalable Branch-and-Bound Method for Optimal Decision Trees with Continuous FeaturesSpotlight29 citations
578. Refined Convergence Rates for Maximum Likelihood Estimation under Finite Mixture ModelsOral29 citations
579. Shuffle Private Linear Contextual BanditsSpotlight29 citations
580. Stable Conformal Prediction SetsOral29 citations
581. Streaming Algorithms for High-Dimensional Robust StatisticsSpotlight29 citations
582. Weisfeiler-Lehman Meets Gromov-WassersteinSpotlight29 citations
583. Continuous-Time Analysis of Accelerated Gradient Methods via Conservation Laws in Dilated Coordinate SystemsOral28 citations
584. Diversified Adversarial Attacks based on Conjugate Gradient MethodSpotlight28 citations
585. Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based LearningSpotlight28 citations
586. Injecting Logical Constraints into Neural Networks via Straight-Through EstimatorsSpotlight28 citations
587. LIDL: Local Intrinsic Dimension Estimation Using Approximate LikelihoodOral28 citations
588. Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill DiversitySpotlight28 citations
589. On the Generalization Analysis of Adversarial LearningSpotlight28 citations
590. Robust alignment of cross-session recordings of neural population activity by behaviour via unsupervised domain adaptationSpotlight28 citations
591. Thresholded Lasso BanditSpotlight28 citations
592. Toward Compositional Generalization in Object-Oriented World ModelingOral28 citations
593. Versatile Dueling Bandits: Best-of-both World Analyses for Learning from Relative PreferencesSpotlight28 citations
594. pathGCN: Learning General Graph Spatial Operators from PathsSpotlight28 citations
595. A Convergence Theory for SVGD in the Population Limit under Talagrand’s Inequality T1Spotlight27 citations
596. A Simple yet Universal Strategy for Online Convex OptimizationOral27 citations
597. Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and RobustnessSpotlight27 citations
598. Improving Policy Optimization with Generalist-Specialist LearningSpotlight27 citations
599. Label-Free Explainability for Unsupervised ModelsSpotlight27 citations
600. NOMU: Neural Optimization-based Model UncertaintySpotlight27 citations
601. Neural Inverse KinematicSpotlight27 citations
602. Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma ClassificationSpotlight27 citations
603. A Neural Tangent Kernel Perspective of GANsSpotlight26 citations
604. Accelerated Gradient Methods for Geodesically Convex Optimization: Tractable Algorithms and Convergence AnalysisSpotlight26 citations
605. Augment with Care: Contrastive Learning for Combinatorial ProblemsSpotlight26 citations
606. Bounding the Width of Neural Networks via Coupled Initialization A Worst Case AnalysisSpotlight26 citations
607. Deep Hierarchy in BanditsSpotlight26 citations
608. Dynamic Topic Models for Temporal Document NetworksSpotlight26 citations
609. Fairness Interventions as (Dis)Incentives for Strategic ManipulationSpotlight26 citations
610. Fast rates for noisy interpolation require rethinking the effect of inductive biasSpotlight26 citations
611. Learning Mixtures of Linear Dynamical SystemsOral26 citations
612. On Collective Robustness of Bagging Against Data PoisoningSpotlight26 citations
613. PINs: Progressive Implicit Networks for Multi-Scale Neural RepresentationsSpotlight26 citations
614. Power-Law Escape Rate of SGDSpotlight26 citations
615. Reconstructing Nonlinear Dynamical Systems from Multi-Modal Time SeriesSpotlight26 citations
616. Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep NetworksSpotlight26 citations
617. Score-Guided Intermediate Level Optimization: Fast Langevin Mixing for Inverse ProblemsSpotlight26 citations
618. Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget MattersSpotlight26 citations
619. Streaming Algorithm for Monotone k-Submodular Maximization with Cardinality ConstraintsOral26 citations
620. Style Equalization: Unsupervised Learning of Controllable Generative Sequence ModelsSpotlight26 citations
621. Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange EconomySpotlight26 citations
622. A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov GamesSpotlight25 citations
623. AdaGrad Avoids Saddle PointsSpotlight25 citations
624. Adaptive Random Walk Gradient Descent for Decentralized OptimizationSpotlight25 citations
625. Correlation Clustering via Strong Triadic Closure Labeling: Fast Approximation Algorithms and Practical Lower BoundsSpotlight25 citations
626. Demystifying the Adversarial Robustness of Random Transformation DefensesSpotlight25 citations
627. Differentially Private Community Detection for Stochastic Block ModelsSpotlight25 citations
628. Does the Data Induce Capacity Control in Deep Learning?Spotlight25 citations
629. Flow-based Recurrent Belief State Learning for POMDPsSpotlight25 citations
630. Generalizing to Evolving Domains with Latent Structure-Aware Sequential AutoencoderSpotlight25 citations
631. LCANets: Lateral Competition Improves Robustness Against Corruption and AttackSpotlight25 citations
632. Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental LimitsOral25 citations
633. Learning from Demonstration: Provably Efficient Adversarial Policy Imitation with Linear Function ApproximationSpotlight25 citations
634. NeuralEF: Deconstructing Kernels by Deep Neural NetworksSpotlight25 citations
635. Object Permanence Emerges in a Random Walk along MemorySpotlight25 citations
636. On the Role of Discount Factor in Offline Reinforcement LearningSpotlight25 citations
637. Private frequency estimation via projective geometrySpotlight25 citations
638. Robust Imitation Learning against Variations in Environment DynamicsSpotlight25 citations
639. End-to-End Balancing for Causal Continuous Treatment-Effect EstimationSpotlight24 citations
640. From Dirichlet to Rubin: Optimistic Exploration in RL without BonusesOral24 citations
641. G$^2$CN: Graph Gaussian Convolution Networks with Concentrated Graph FiltersSpotlight24 citations
642. Generalization Bounds using Lower Tail Exponents in Stochastic OptimizersSpotlight24 citations
643. Large Batch Experience ReplayOral24 citations
644. Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable ConvergenceSpotlight24 citations
645. On the Learning of Non-Autoregressive TransformersSpotlight24 citations
646. On the Robustness of CountSketch to Adaptive InputsSpotlight24 citations
647. PDE-Based Optimal Strategy for Unconstrained Online LearningSpotlight24 citations
648. Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-OutSpotlight24 citations
649. Provably Efficient Offline Reinforcement Learning for Partially Observable Markov Decision ProcessesSpotlight24 citations
650. Smoothed Adversarial Linear Contextual Bandits with KnapsacksSpotlight24 citations
651. The dynamics of representation learning in shallow, non-linear autoencodersSpotlight24 citations
652. Accelerated, Optimal and Parallel: Some results on model-based stochastic optimizationSpotlight23 citations
653. Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local SmoothnessSpotlight23 citations
654. Debiaser Beware: Pitfalls of Centering Regularized Transport MapsSpotlight23 citations
655. Deconfounded Value Decomposition for Multi-Agent Reinforcement LearningSpotlight23 citations
656. Fair and Fast k-Center Clustering for Data SummarizationSpotlight23 citations
657. Generative Cooperative Networks for Natural Language GenerationSpotlight23 citations
658. Improve Single-Point Zeroth-Order Optimization Using High-Pass and Low-Pass FiltersSpotlight23 citations
659. Improving Screening Processes via Calibrated Subset SelectionSpotlight23 citations
660. Inferring Cause and Effect in the Presence of Heteroscedastic NoiseSpotlight23 citations
661. Learning Efficient and Robust Ordinary Differential Equations via Invertible Neural NetworksSpotlight23 citations
662. Learning fair representation with a parametric integral probability metricSpotlight23 citations
663. Learning of Cluster-based Feature Importance for Electronic Health Record Time-seriesSpotlight23 citations
664. Neural Tangent Kernel Empowered Federated LearningSpotlight23 citations
665. Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference TheorySpotlight23 citations
666. PACE: A Parallelizable Computation Encoder for Directed Acyclic GraphsSpotlight23 citations
667. Position Prediction as an Effective Pretraining StrategySpotlight23 citations
668. Proving Theorems using Incremental Learning and Hindsight Experience ReplaySpotlight23 citations
669. REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy TransferOral23 citations
670. Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample EfficiencySpotlight23 citations
671. Robust Kernel Density Estimation with Median-of-Means principleSpotlight23 citations
672. Robustness Verification for Contrastive LearningOral23 citations
673. A General Recipe for Likelihood-free Bayesian OptimizationOral22 citations
674. A State-Distribution Matching Approach to Non-Episodic Reinforcement LearningSpotlight22 citations
675. AGNAS: Attention-Guided Micro and Macro-Architecture SearchSpotlight22 citations
676. Adversarial Robustness against Multiple and Single $l_p$-Threat Models via Quick Fine-Tuning of Robust ClassifiersSpotlight22 citations
677. AutoIP: A United Framework to Integrate Physics into Gaussian ProcessesSpotlight22 citations
678. Certifying Out-of-Domain Generalization for Blackbox FunctionsSpotlight22 citations
679. Constrained Offline Policy OptimizationSpotlight22 citations
680. Data-SUITE: Data-centric identification of in-distribution incongruous examplesSpotlight22 citations
681. DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural NetworksSpotlight22 citations
682. Entropic Gromov-Wasserstein between Gaussian DistributionsSpotlight22 citations
683. Gating Dropout: Communication-efficient Regularization for Sparsely Activated TransformersSpotlight22 citations
684. Learning Iterative Reasoning through Energy MinimizationSpotlight22 citations
685. Mitigating Gender Bias in Face Recognition using the von Mises-Fisher Mixture ModelSpotlight22 citations
686. On the Convergence of Local Stochastic Compositional Gradient Descent with MomentumSpotlight22 citations
687. Pairwise Conditional Gradients without Swap Steps and Sparser Kernel HerdingSpotlight22 citations
688. Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement LearningSpotlight22 citations
689. Quantifying and Learning Linear Symmetry-Based DisentanglementSpotlight22 citations
690. Scalable Spike-and-SlabSpotlight22 citations
691. Simple and near-optimal algorithms for hidden stratification and multi-group learningSpotlight22 citations
692. Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious FunctionSpotlight22 citations
693. The Role of Deconfounding in Meta-learningSpotlight22 citations
694. Accelerating Shapley Explanation via Contributive Cooperator SelectionSpotlight21 citations
695. Building Robust Ensembles via Margin BoostingSpotlight21 citations
696. Contextual Information-Directed SamplingSpotlight21 citations
697. Differentially Private Coordinate Descent for Composite Empirical Risk MinimizationSpotlight21 citations
698. Dynamic Regret of Online Markov Decision ProcessesSpotlight21 citations
699. Examining Scaling and Transfer of Language Model Architectures for Machine TranslationSpotlight21 citations
700. Exploiting Independent Instruments: Identification and Distribution GeneralizationSpotlight21 citations
701. Fighting Fire with Fire: Avoiding DNN Shortcuts through PrimingSpotlight21 citations
702. Improving Adversarial Robustness via Mutual Information EstimationSpotlight21 citations
703. Measure Estimation in the Barycentric Coding ModelSpotlight21 citations
704. Modeling Adversarial Noise for Adversarial TrainingSpotlight21 citations
705. On Transportation of Mini-batches: A Hierarchical ApproachSpotlight21 citations
706. Optimal Algorithms for Stochastic Multi-Level Compositional OptimizationSpotlight21 citations
707. Permutation Search of Tensor Network Structures via Local SamplingSpotlight21 citations
708. Structure-preserving GANsSpotlight21 citations
709. Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous SpacesSpotlight21 citations
710. Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video RestorationSpotlight21 citations
711. A Tighter Analysis of Spectral Clustering, and BeyondSpotlight20 citations
712. Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed BanditsSpotlight20 citations
713. An Exact Symbolic Reduction of Linear Smart Predict+Optimize to Mixed Integer Linear ProgrammingSpotlight20 citations
714. Deletion Robust Submodular Maximization over MatroidsOral20 citations
715. Difference Advantage Estimation for Multi-Agent Policy GradientsSpotlight20 citations
716. Efficient Online ML API Selection for Multi-Label Classification TasksSpotlight20 citations
717. Fair Generalized Linear Models with a Convex PenaltySpotlight20 citations
718. Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin AttackSpotlight20 citations
719. Fast-Rate PAC-Bayesian Generalization Bounds for Meta-LearningSpotlight20 citations
720. Fictitious Play and Best-Response Dynamics in Identical Interest and Zero-Sum Stochastic GamesSpotlight20 citations
721. GenLabel: Mixup Relabeling using Generative ModelsSpotlight20 citations
722. Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region QuantificationSpotlight20 citations
723. Input-agnostic Certified Group Fairness via Gaussian Parameter SmoothingSpotlight20 citations
724. Learning Pseudometric-based Action Representations for Offline Reinforcement LearningSpotlight20 citations
725. On the Hidden Biases of Policy Mirror Ascent in Continuous Action SpacesSpotlight20 citations
726. PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient EstimationSpotlight20 citations
727. Probabilistic ODE Solutions in Millions of DimensionsSpotlight20 citations
728. RetrievalGuard: Provably Robust 1-Nearest Neighbor Image RetrievalSpotlight20 citations
729. Robust SDE-Based Variational Formulations for Solving Linear PDEs via Deep LearningSpotlight20 citations
730. Safe Learning in Tree-Form Sequential Decision Making: Handling Hard and Soft ConstraintsSpotlight20 citations
731. Sequential Covariate Shift Detection Using Classifier Two-Sample TestsSpotlight20 citations
732. Understanding and Improving Knowledge Graph Embedding for Entity AlignmentSpotlight20 citations
733. An iterative clustering algorithm for the Contextual Stochastic Block Model with optimality guaranteesSpotlight19 citations
734. Auxiliary Learning with Joint Task and Data SchedulingSpotlight19 citations
735. Convolutional and Residual Networks Provably Contain Lottery TicketsSpotlight19 citations
736. Diffusion bridges vector quantized variational autoencodersSpotlight19 citations
737. Discrete Probabilistic Inverse Optimal TransportSpotlight19 citations
738. Efficient Distributionally Robust Bayesian Optimization with Worst-case SensitivitySpotlight19 citations
739. Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium ComputationSpotlight19 citations
740. Entropic Causal Inference: Graph IdentifiabilitySpotlight19 citations
741. Fast Composite Optimization and Statistical Recovery in Federated LearningSpotlight19 citations
742. Feature Learning and Signal Propagation in Deep Neural NetworksSpotlight19 citations
743. Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier AnalysisSpotlight19 citations
744. IDYNO: Learning Nonparametric DAGs from Interventional Dynamic DataSpotlight19 citations
745. Inverse Contextual Bandits: Learning How Behavior Evolves over TimeSpotlight19 citations
746. Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable RobustnessSpotlight19 citations
747. Online Learning for Min Sum Set Cover and Pandora’s BoxOral19 citations
748. Provably Adversarially Robust Nearest Prototype ClassifiersSpotlight19 citations
749. Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple TimesSpotlight19 citations
750. Secure Distributed Training at ScaleSpotlight19 citations
751. Self-supervised Models are Good Teaching Assistants for Vision TransformersSpotlight19 citations
752. Sequential and Parallel Constrained Max-value Entropy Search via Information Lower BoundSpotlight19 citations
753. Set Norm and Equivariant Skip Connections: Putting the Deep in Deep SetsSpotlight19 citations
754. ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural NetworksSpotlight19 citations
755. Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced TopologySpotlight19 citations
756. Universal Joint Approximation of Manifolds and Densities by Simple Injective FlowsSpotlight19 citations
757. A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural NetworksSpotlight18 citations
758. Accurate Quantization of Measures via Interacting Particle-based OptimizationSpotlight18 citations
759. An Intriguing Property of Geophysics InversionSpotlight18 citations
760. Bayesian Optimization under Stochastic Delayed FeedbackSpotlight18 citations
761. Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness ConstraintSpotlight18 citations
762. Deep Probability EstimationSpotlight18 citations
763. Delayed Reinforcement Learning by ImitationSpotlight18 citations
764. Faster Privacy Accounting via Evolving DiscretizationSpotlight18 citations
765. Implicit Bias of Linear Equivariant NetworksSpotlight18 citations
766. Learning Bellman Complete Representations for Offline Policy EvaluationOral18 citations
767. Learning Multiscale Transformer Models for Sequence GenerationSpotlight18 citations
768. Linear Bandit Algorithms with Sublinear Time ComplexitySpotlight18 citations
769. Modular Conformal CalibrationSpotlight18 citations
770. More Efficient Sampling for Tensor Decomposition With Worst-Case GuaranteesSpotlight18 citations
771. Nesterov Accelerated Shuffling Gradient Method for Convex OptimizationSpotlight18 citations
772. Optimizing Tensor Network Contraction Using Reinforcement LearningSpotlight18 citations
773. Path-Gradient Estimators for Continuous Normalizing FlowsOral18 citations
774. Regret Bounds for Stochastic Shortest Path Problems with Linear Function ApproximationSpotlight18 citations
775. Robust Policy Learning over Multiple Uncertainty SetsSpotlight18 citations
776. Self-Organized Polynomial-Time Coordination GraphsSpotlight18 citations
777. Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum GamesSpotlight18 citations
778. TPC: Transformation-Specific Smoothing for Point Cloud ModelsSpotlight18 citations
779. A Framework for Learning to Request Rich and Contextually Useful Information from HumansSpotlight17 citations
780. Combining Diverse Feature PriorsSpotlight17 citations
781. Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action SpacesOral17 citations
782. DNNR: Differential Nearest Neighbors RegressionSpotlight17 citations
783. Deep and Flexible Graph Neural Architecture SearchSpotlight17 citations
784. Detached Error Feedback for Distributed SGD with Random SparsificationSpotlight17 citations
785. Generalized Results for the Existence and Consistency of the MLE in the Bradley-Terry-Luce ModelOral17 citations
786. Generalizing Gaussian Smoothing for Random SearchSpotlight17 citations
787. Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDPOral17 citations
788. Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance OrderingsSpotlight17 citations
789. LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial OptimisationSpotlight17 citations
790. Learning to Incorporate Texture Saliency Adaptive Attention to Image CartoonizationSpotlight17 citations
791. Low-Precision Stochastic Gradient Langevin DynamicsSpotlight17 citations
792. Maslow’s Hammer in Catastrophic Forgetting: Node Re-Use vs. Node ActivationSpotlight17 citations
793. Nearly Optimal Catoni’s M-estimator for Infinite VarianceSpotlight17 citations
794. Partial Label Learning via Label Influence FunctionSpotlight17 citations
795. Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated FrameworkSpotlight17 citations
796. Safe Exploration for Efficient Policy Evaluation and ComparisonSpotlight17 citations
797. Sanity Simulations for Saliency MethodsSpotlight17 citations
798. Self-conditioning Pre-Trained Language ModelsSpotlight17 citations
799. Towards Evaluating Adaptivity of Model-Based Reinforcement Learning MethodsSpotlight17 citations
800. Utility Theory for Sequential Decision MakingSpotlight17 citations
801. A Reduction from Linear Contextual Bandits Lower Bounds to Estimations Lower BoundsSpotlight16 citations
802. A Study on the Ramanujan Graph Property of Winning Lottery TicketsSpotlight16 citations
803. Asking for Knowledge (AFK): Training RL Agents to Query External Knowledge Using LanguageSpotlight16 citations
804. DRAGONN: Distributed Randomized Approximate Gradients of Neural NetworksSpotlight16 citations
805. Delay-Adaptive Step-sizes for Asynchronous LearningSpotlight16 citations
806. Equivalence Analysis between Counterfactual Regret Minimization and Online Mirror DescentSpotlight16 citations
807. Fast Aquatic Swimmer Optimization with Differentiable Projective Dynamics and Neural Network Hydrodynamic ModelsSpotlight16 citations
808. Fast Provably Robust Decision Trees and BoostingSpotlight16 citations
809. Feature Space Particle Inference for Neural Network EnsemblesSpotlight16 citations
810. Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural NetworksSpotlight16 citations
811. Generative Modeling for Multi-task Visual LearningSpotlight16 citations
812. Greedy when Sure and Conservative when Uncertain about the OpponentsSpotlight16 citations
813. Learning General Halfspaces with Adversarial Label Noise via Online Gradient DescentSpotlight16 citations
814. Model Selection in Batch Policy OptimizationSpotlight16 citations
815. NysADMM: faster composite convex optimization via low-rank approximationSpotlight16 citations
816. Optimally Controllable Perceptual Lossy CompressionSpotlight16 citations
817. Principal Component FlowsSpotlight16 citations
818. Private Streaming SCO in $\ell_p$ geometry with Applications in High Dimensional Online Decision MakingSpotlight16 citations
819. ROCK: Causal Inference Principles for Reasoning about Commonsense CausalitySpotlight16 citations
820. Time Is MattEr: Temporal Self-supervision for Video TransformersSpotlight16 citations
821. Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient DescentOral16 citations
822. Transfer and Marginalize: Explaining Away Label Noise with Privileged InformationSpotlight16 citations
823. VLUE: A Multi-Task Multi-Dimension Benchmark for Evaluating Vision-Language Pre-trainingSpotlight16 citations
824. Zero-shot AutoML with Pretrained ModelsSpotlight16 citations
825. A Joint Exponential Mechanism For Differentially Private Top-$k$Spotlight15 citations
826. A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained OptimizationSpotlight15 citations
827. Active Multi-Task Representation LearningSpotlight15 citations
828. Adaptive Gaussian Process Change Point DetectionSpotlight15 citations
829. An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to LearnSpotlight15 citations
830. Cascaded Gaps: Towards Logarithmic Regret for Risk-Sensitive Reinforcement LearningSpotlight15 citations
831. Correlated Quantization for Distributed Mean Estimation and OptimizationSpotlight15 citations
832. CtrlFormer: Learning Transferable State Representation for Visual Control via TransformerSpotlight15 citations
833. Fat–Tailed Variational Inference with Anisotropic Tail Adaptive FlowsSpotlight15 citations
834. Fenrir: Physics-Enhanced Regression for Initial Value ProblemsSpotlight15 citations
835. Generalized Data Distribution IterationSpotlight15 citations
836. Greedy based Value Representation for Optimal Coordination in Multi-agent Reinforcement LearningSpotlight15 citations
837. Identity-Disentangled Adversarial Augmentation for Self-supervised LearningSpotlight15 citations
838. Iterative Hard Thresholding with Adaptive Regularization: Sparser Solutions Without Sacrificing RuntimeSpotlight15 citations
839. Matching Learned Causal Effects of Neural Networks with Domain PriorsSpotlight15 citations
840. Minimizing Control for Credit Assignment with Strong FeedbackSpotlight15 citations
841. Nearly Optimal Policy Optimization with Stable at Any Time GuaranteeSpotlight15 citations
842. Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation LearningSpotlight15 citations
843. On Learning Mixture of Linear Regressions in the Non-Realizable SettingSpotlight15 citations
844. Online and Consistent Correlation ClusteringSpotlight15 citations
845. PAC-Net: A Model Pruning Approach to Inductive Transfer LearningSpotlight15 citations
846. Reverse Engineering the Neural Tangent KernelSpotlight15 citations
847. SCHA-VAE: Hierarchical Context Aggregation for Few-Shot GenerationSpotlight15 citations
848. Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary FrameworkSpotlight15 citations
849. Sharpened Quasi-Newton Methods: Faster Superlinear Rate and Larger Local Convergence NeighborhoodSpotlight15 citations
850. Short-Term Plasticity Neurons Learning to Learn and ForgetSpotlight15 citations
851. Solving Stackelberg Prediction Game with Least Squares Loss via Spherically Constrained Least Squares ReformulationOral15 citations
852. Structured Stochastic Gradient MCMCSpotlight15 citations
853. Surrogate Likelihoods for Variational Annealed Importance SamplingSpotlight15 citations
854. When Are Linear Stochastic Bandits Attackable?Spotlight15 citations
855. A Unified View on PAC-Bayes Bounds for Meta-LearningSpotlight14 citations
856. Achieving Minimax Rates in Pool-Based Batch Active LearningSpotlight14 citations
857. Adaptive Model Design for Markov Decision ProcessSpotlight14 citations
858. Batched Dueling BanditsOral14 citations
859. Bayesian Optimization for Distributionally Robust Chance-constrained ProblemSpotlight14 citations
860. Convergence of Invariant Graph NetworksSpotlight14 citations
861. Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field RegimeSpotlight14 citations
862. Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement LearningSpotlight14 citations
863. Failure and success of the spectral bias prediction for Laplace Kernel Ridge Regression: the case of low-dimensional dataSpotlight14 citations
864. Fast Population-Based Reinforcement Learning on a Single MachineSpotlight14 citations
865. Generic Coreset for Scalable Learning of Monotonic Kernels: Logistic Regression, Sigmoid and moreSpotlight14 citations
866. Learning to Estimate and Refine Fluid Motion with Physical DynamicsSpotlight14 citations
867. Learning to Separate Voices by Spatial RegionsSpotlight14 citations
868. Neural Implicit Dictionary Learning via Mixture-of-Expert TrainingSpotlight14 citations
869. Neural Tangent Kernel Analysis of Deep Narrow Neural NetworksSpotlight14 citations
870. On the Convergence of the Shapley Value in Parametric Bayesian Learning GamesSpotlight14 citations
871. Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement LearningSpotlight14 citations
872. Robust Meta-learning with Sampling Noise and Label Noise via Eigen-ReptileSpotlight14 citations
873. Sparsity in Partially Controllable Linear SystemsSpotlight14 citations
874. Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-LearningOral14 citations
875. Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and RiskSpotlight14 citations
876. Towards Coherent and Consistent Use of Entities in Narrative GenerationSpotlight14 citations
877. Variational Mixtures of ODEs for Inferring Cellular Gene Expression DynamicsSpotlight14 citations
878. Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of RegularizationSpotlight13 citations
879. BabelTower: Learning to Auto-parallelized Program TranslationSpotlight13 citations
880. Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for OptimizationOral13 citations
881. C-MinHash: Improving Minwise Hashing with Circulant PermutationSpotlight13 citations
882. Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPsSpotlight13 citations
883. Consistent Polyhedral Surrogates for Top-k Classification and VariantsSpotlight13 citations
884. Dual Perspective of Label-Specific Feature Learning for Multi-Label ClassificationSpotlight13 citations
885. Fast and Provable Nonconvex Tensor RPCASpotlight13 citations
886. For Learning in Symmetric Teams, Local Optima are Global Nash EquilibriaSpotlight13 citations
887. Individual Preference Stability for ClusteringOral13 citations
888. Learning to Hash Robustly, GuaranteedSpotlight13 citations
889. Leverage Score Sampling for Tensor Product Matrices in Input Sparsity TimeSpotlight13 citations
890. Marginal Tail-Adaptive Normalizing FlowsSpotlight13 citations
891. Multicoated Supermasks Enhance Hidden NetworksSpotlight13 citations
892. One-Pass Diversified Sampling with Application to Terabyte-Scale Genomic Sequence StreamsSpotlight13 citations
893. RECAPP: Crafting a More Efficient Catalyst for Convex OptimizationSpotlight13 citations
894. Searching for BurgerFormer with Micro-Meso-Macro Space DesignSpotlight13 citations
895. Simultaneously Learning Stochastic and Adversarial Bandits with General Graph FeedbackSpotlight13 citations
896. Stability Based Generalization Bounds for Exponential Family Langevin DynamicsSpotlight13 citations
897. Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classificationSpotlight13 citations
898. Tractable Uncertainty for Structure LearningOral13 citations
899. VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian NoveltySpotlight13 citations
900. Wide Bayesian neural networks have a simple weight posterior: theory and accelerated samplingSpotlight13 citations
901. A Simple Guard for Learned OptimizersSpotlight12 citations
902. Bayesian Imitation Learning for End-to-End Mobile ManipulationSpotlight12 citations
903. ButterflyFlow: Building Invertible Layers with Butterfly MatricesSpotlight12 citations
904. Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning EnvironmentsSpotlight12 citations
905. Convergence and Recovery Guarantees of the K-Subspaces Method for Subspace ClusteringSpotlight12 citations
906. Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement LearningSpotlight12 citations
907. Distinguishing rule and exemplar-based generalization in learning systemsSpotlight12 citations
908. Efficient Computation of Higher-Order Subgraph Attribution via Message PassingSpotlight12 citations
909. Efficient Variance Reduction for Meta-learningSpotlight12 citations
910. FITNESS: (Fine Tune on New and Similar Samples) to detect anomalies in streams with drift and outliersSpotlight12 citations
911. FOCUS: Familiar Objects in Common and Uncommon SettingsSpotlight12 citations
912. Function-space Inference with Sparse Implicit ProcessesOral12 citations
913. Functional Generalized Empirical Likelihood Estimation for Conditional Moment RestrictionsSpotlight12 citations
914. How Tempering Fixes Data Augmentation in Bayesian Neural NetworksOral12 citations
915. Interpretable Off-Policy Learning via Hyperbox SearchSpotlight12 citations
916. Label-Descriptive Patterns and Their Application to Characterizing Classification ErrorsSpotlight12 citations
917. Multi Resolution Analysis (MRA) for Approximate Self-AttentionSpotlight12 citations
918. Near-optimal rate of consistency for linear models with missing valuesSpotlight12 citations
919. Neural Network Pruning Denoises the Features and Makes Local Connectivity Emerge in Visual TasksSpotlight12 citations
920. Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure PerspectiveSpotlight12 citations
921. On the Statistical Benefits of Curriculum LearningSpotlight12 citations
922. Path-Aware and Structure-Preserving Generation of Synthetically Accessible MoleculesSpotlight12 citations
923. SpaceMAP: Visualizing High-Dimensional Data by Space ExpansionSpotlight12 citations
924. Stochastic Reweighted Gradient DescentSpotlight12 citations
925. Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference AlgorithmSpotlight12 citations
926. Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect FourOral12 citations
927. Why the Rich Get Richer? On the Balancedness of Random Partition ModelsSpotlight12 citations
928. A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward MachinesSpotlight11 citations
929. Adaptive Data Analysis with Correlated ObservationsSpotlight11 citations
930. An Asymptotic Test for Conditional Independence using Analytic Kernel EmbeddingsSpotlight11 citations
931. Approximate Bayesian Computation with Domain Expert in the LoopSpotlight11 citations
932. Being Properly ImproperSpotlight11 citations
933. Continual Learning with Guarantees via Weight Interval ConstraintsSpotlight11 citations
934. DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement LearningSpotlight11 citations
935. Decentralized Online Convex Optimization in Networked SystemsSpotlight11 citations
936. Feature and Parameter Selection in Stochastic Linear BanditsSpotlight11 citations
937. Generative Trees: Adversarial and CopycatOral11 citations
938. Interactively Learning Preference Constraints in Linear BanditsSpotlight11 citations
939. Model-Value Inconsistency as a Signal for Epistemic UncertaintySpotlight11 citations
940. Neuron Dependency Graphs: A Causal Abstraction of Neural NetworksSpotlight11 citations
941. On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component AnalysisSpotlight11 citations
942. Only tails matter: Average-Case Universality and Robustness in the Convex RegimeSpotlight11 citations
943. PDO-s3DCNNs: Partial Differential Operator Based Steerable 3D CNNsSpotlight11 citations
944. Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning SystemsOral11 citations
945. Robust Group Synchronization via Quadratic ProgrammingSpotlight11 citations
946. Scalable First-Order Bayesian Optimization via Structured Automatic DifferentiationSpotlight11 citations
947. Supervised Learning with General Risk FunctionalsSpotlight11 citations
948. Understanding Doubly Stochastic ClusteringSpotlight11 citations
949. Unsupervised Ground Metric Learning Using Wasserstein Singular VectorsSpotlight11 citations
950. Unsupervised Image Representation Learning with Deep Latent ParticlesSpotlight11 citations
951. VarScene: A Deep Generative Model for Realistic Scene Graph SynthesisSpotlight11 citations
952. Variational Sparse Coding with Learned ThresholdingSpotlight11 citations
953. A deep convolutional neural network that is invariant to time rescalingSpotlight10 citations
954. Adapting k-means Algorithms for OutliersSpotlight10 citations
955. Anytime Information Cascade Popularity Prediction via Self-Exciting ProcessesSpotlight10 citations
956. Be Like Water: Adaptive Floating Point for Machine LearningSpotlight10 citations
957. Bregman Neural NetworksSpotlight10 citations
958. Choosing Answers in Epsilon-Best-Answer Identification for Linear BanditsSpotlight10 citations
959. Functional Output Regression with Infimal Convolution: Exploring the Huber and $ε$-insensitive LossesSpotlight10 citations
960. Hardness and Algorithms for Robust and Sparse OptimizationSpotlight10 citations
961. How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment PerspectiveSpotlight10 citations
962. Improved Regret for Differentially Private Exploration in Linear MDPSpotlight10 citations
963. Inductive Matrix Completion: No Bad Local Minima and a Fast AlgorithmSpotlight10 citations
964. LSB: Local Self-Balancing MCMC in Discrete SpacesSpotlight10 citations
965. Learning Stable Classifiers by Transferring Unstable FeaturesSpotlight10 citations
966. Learning to Infer Structures of Network GamesSpotlight10 citations
967. Meta-Learning Hypothesis Spaces for Sequential Decision-makingSpotlight10 citations
968. Minimax Classification under Concept Drift with Multidimensional Adaptation and Performance GuaranteesSpotlight10 citations
969. ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive BiasOral10 citations
970. Multiple-Play Stochastic Bandits with Shareable Finite-Capacity ArmsSpotlight10 citations
971. No-Regret Learning in Partially-Informed AuctionsSpotlight10 citations
972. Online Active RegressionOral10 citations
973. Plug-In Inversion: Model-Agnostic Inversion for Vision with Data AugmentationsSpotlight10 citations
974. Random Forest Density EstimationSpotlight10 citations
975. Risk-Averse No-Regret Learning in Online Convex GamesSpotlight10 citations
976. Rotting Infinitely Many-Armed BanditsSpotlight10 citations
977. Sparse Mixed Linear Regression with Guarantees: Taming an Intractable Problem with Invex RelaxationSpotlight10 citations
978. Structure Preserving Neural Networks: A Case Study in the Entropy Closure of the Boltzmann EquationSpotlight10 citations
979. Understanding Policy Gradient Algorithms: A Sensitivity-Based ApproachSpotlight10 citations
980. Visual Attention Emerges from Recurrent Sparse ReconstructionSpotlight10 citations
981. A Deep Learning Approach for the Segmentation of Electroencephalography Data in Eye Tracking ApplicationsSpotlight9 citations
982. Adversarial Attacks on Gaussian Process BanditsSpotlight9 citations
983. Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement LearningSpotlight9 citations
984. Bayesian Nonparametric Learning for Point Processes with Spatial Homogeneity: A Spatial Analysis of NBA Shot LocationsSpotlight9 citations
985. Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement LearningSpotlight9 citations
986. Bregman Proximal Langevin Monte Carlo via Bregman-Moreau EnvelopesSpotlight9 citations
987. C*-algebra Net: A New Approach Generalizing Neural Network Parameters to C*-algebraSpotlight9 citations
988. COAT: Measuring Object Compositionality in Emergent RepresentationsSpotlight9 citations
989. Communicating via Markov Decision ProcessesSpotlight9 citations
990. Communication-efficient Distributed Learning for Large Batch OptimizationSpotlight9 citations
991. Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense MechanismsSpotlight9 citations
992. Counterfactual Prediction for Outcome-Oriented TreatmentsSpotlight9 citations
993. Deep Causal Metric LearningSpotlight9 citations
994. Deep equilibrium networks are sensitive to initialization statisticsSpotlight9 citations
995. Efficient Learning for AlphaZero via Path ConsistencySpotlight9 citations
996. Efficient PAC Learning from the Crowd with Pairwise ComparisonsSpotlight9 citations
997. Faster Algorithms for Learning Convex FunctionsSpotlight9 citations
998. Generalised Policy Improvement with Geometric Policy CompositionOral9 citations
999. Improving Ensemble Distillation With Weight Averaging and Diversifying PerturbationSpotlight9 citations
1000. Kernel Methods for Radial Transformed Compositional Data with Many ZerosSpotlight9 citations

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