ICML 2020 Accepted Papers

The full list of 1,082 papers accepted at ICML 2020 (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. A Simple Framework for Contrastive Learning of Visual RepresentationsPoster24,175 citations
2. SCAFFOLD: Stochastic Controlled Averaging for Federated LearningPoster3,685 citations
3. PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive SummarizationPoster2,551 citations
4. Retrieval Augmented Language Model Pre-TrainingPoster2,380 citations
5. Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacksPoster2,290 citations
6. Understanding Contrastive Representation Learning through Alignment and Uniformity on the HyperspherePoster2,212 citations
7. Transformers are RNNs: Fast Autoregressive Transformers with Linear AttentionPoster2,128 citations
8. Generative Pretraining From PixelsPoster2,012 citations
9. Simple and Deep Graph Convolutional NetworksPoster2,010 citations
10. Data-Efficient Image Recognition with Contrastive Predictive CodingPoster1,721 citations
11. Contrastive Multi-View Representation Learning on GraphsPoster1,685 citations
12. Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain AdaptationPoster1,634 citations
13. Learning to Simulate Complex Physics with Graph NetworksPoster1,440 citations
14. CURL: Contrastive Unsupervised Representations for Reinforcement LearningPoster1,294 citations
15. On Layer Normalization in the Transformer ArchitecturePoster1,272 citations
16. Overfitting in adversarially robust deep learningPoster1,072 citations
17. Concept Bottleneck ModelsPoster1,035 citations
18. XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual GeneralisationPoster1,009 citations
19. Implicit Geometric Regularization for Learning ShapesPoster950 citations
20. The Many Shapley Values for Model ExplanationPoster949 citations
21. Test-Time Training with Self-Supervision for Generalization under Distribution ShiftsPoster945 citations
22. Frustratingly Simple Few-Shot Object DetectionPoster762 citations
23. Agent57: Outperforming the Atari Human BenchmarkPoster759 citations
24. The Non-IID Data Quagmire of Decentralized Machine LearningPoster724 citations
25. Leveraging Frequency Analysis for Deep Fake Image RecognitionPoster708 citations
26. An Optimistic Perspective on Offline Reinforcement LearningPoster707 citations
27. Rigging the Lottery: Making All Tickets WinnersPoster697 citations
28. Leveraging Procedural Generation to Benchmark Reinforcement LearningPoster686 citations
29. Up or Down? Adaptive Rounding for Post-Training QuantizationPoster685 citations
30. Which Tasks Should Be Learned Together in Multi-task Learning?Poster669 citations
31. Linear Mode Connectivity and the Lottery Ticket HypothesisPoster668 citations
32. On Gradient Descent Ascent for Nonconvex-Concave Minimax ProblemsPoster656 citations
33. Uncertainty Estimation Using a Single Deep Deterministic Neural NetworkPoster620 citations
34. A Unified Theory of Decentralized SGD with Changing Topology and Local UpdatesPoster610 citations
35. Minimally distorted Adversarial Examples with a Fast Adaptive Boundary AttackPoster607 citations
36. Spectral Clustering with Graph Neural Networks for Graph PoolingPoster580 citations
37. Normalized Loss Functions for Deep Learning with Noisy LabelsPoster558 citations
38. Problems with Shapley-value-based explanations as feature importance measuresPoster558 citations
39. Certified Data Removal from Machine Learning ModelsPoster544 citations
40. Inductive Relation Prediction by Subgraph ReasoningPoster529 citations
41. Accelerating Large-Scale Inference with Anisotropic Vector QuantizationPoster519 citations
42. Learning and Evaluating Contextual Embedding of Source CodePoster514 citations
43. NGBoost: Natural Gradient Boosting for Probabilistic PredictionPoster507 citations
44. Planning to Explore via Self-Supervised World ModelsPoster507 citations
45. Attacks Which Do Not Kill Training Make Adversarial Learning StrongerPoster505 citations
46. Unsupervised Discovery of Interpretable Directions in the GAN Latent SpacePoster487 citations
47. Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal MixupPoster481 citations
48. Stabilizing Transformers for Reinforcement LearningPoster478 citations
49. Coresets for Data-efficient Training of Machine Learning ModelsPoster465 citations
50. UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-TrainingPoster465 citations
51. CLUB: A Contrastive Log-ratio Upper Bound of Mutual InformationPoster464 citations
52. FetchSGD: Communication-Efficient Federated Learning with SketchingPoster464 citations
53. How Good is the Bayes Posterior in Deep Neural Networks Really?Poster451 citations
54. Reliable Fidelity and Diversity Metrics for Generative ModelsPoster450 citations
55. An Investigation of Why Overparameterization Exacerbates Spurious CorrelationsPoster444 citations
56. Does label smoothing mitigate label noise?Poster441 citations
57. Performative PredictionPoster437 citations
58. What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?Poster414 citations
59. Generalization and Representational Limits of Graph Neural NetworksPoster400 citations
60. Hierarchical Generation of Molecular Graphs using Structural MotifsPoster397 citations
61. Transformer Hawkes ProcessPoster396 citations
62. Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU NetworksPoster382 citations
63. Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous DataPoster381 citations
64. Sparse Sinkhorn AttentionPoster380 citations
65. Weakly-Supervised Disentanglement Without CompromisesPoster379 citations
66. AutoML-Zero: Evolving Machine Learning Algorithms From ScratchPoster377 citations
67. Robust Graph Representation Learning via Neural SparsificationPoster366 citations
68. Responsive Safety in Reinforcement Learning by PID Lagrangian MethodsPoster365 citations
69. Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of TransformersPoster360 citations
70. Model-Based Reinforcement Learning with Value-Targeted RegressionPoster358 citations
71. Revisiting Fundamentals of Experience ReplayPoster357 citations
72. Learning De-biased Representations with Biased RepresentationsPoster356 citations
73. Proving the Lottery Ticket Hypothesis: Pruning is All You NeedPoster352 citations
74. On the Global Convergence Rates of Softmax Policy Gradient MethodsPoster349 citations
75. Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret BoundPoster345 citations
76. Provably Efficient Exploration in Policy OptimizationPoster338 citations
77. Neural Contextual Bandits with UCB-based ExplorationPoster330 citations
78. Skew-Fit: State-Covering Self-Supervised Reinforcement LearningPoster321 citations
79. Is Local SGD Better than Minibatch SGD?Poster316 citations
80. Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow PredictionPoster310 citations
81. Invariant Risk Minimization GamesPoster307 citations
82. PolyGen: An Autoregressive Generative Model of 3D MeshesPoster307 citations
83. Self-Attentive Hawkes ProcessPoster298 citations
84. How to Train Your Neural ODE: the World of Jacobian and Kinetic RegularizationPoster296 citations
85. Peer Loss Functions: Learning from Noisy Labels without Knowing Noise RatesPoster294 citations
86. Fast Differentiable Sorting and RankingPoster292 citations
87. Detecting Out-of-Distribution Examples with Gram MatricesPoster291 citations
88. ROMA: Multi-Agent Reinforcement Learning with Emergent RolesPoster288 citations
89. Equivariant Flows: Exact Likelihood Generative Learning for Symmetric DensitiesPoster287 citations
90. Understanding and Mitigating the Tradeoff between Robustness and AccuracyPoster286 citations
91. Understanding Self-Training for Gradual Domain AdaptationPoster284 citations
92. Reward-Free Exploration for Reinforcement LearningPoster281 citations
93. FedBoost: A Communication-Efficient Algorithm for Federated LearningPoster279 citations
94. When Does Self-Supervision Help Graph Convolutional Networks?Poster277 citations
95. Soft Threshold Weight Reparameterization for Learnable SparsityPoster272 citations
96. Multi-Objective Molecule Generation using Interpretable SubstructuresPoster269 citations
97. Consistent Estimators for Learning to Defer to an ExpertPoster268 citations
98. Mix-n-Match : Ensemble and Compositional Methods for Uncertainty Calibration in Deep LearningPoster267 citations
99. Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled DataPoster267 citations
100. Efficient and Scalable Bayesian Neural Nets with Rank-1 FactorsPoster266 citations
101. Learning Near Optimal Policies with Low Inherent Bellman ErrorPoster266 citations
102. Rethinking Bias-Variance Trade-off for Generalization of Neural NetworksPoster265 citations
103. DeltaGrad: Rapid retraining of machine learning modelsPoster264 citations
104. LEEP: A New Measure to Evaluate Transferability of Learned RepresentationsPoster264 citations
105. Invariant RationalizationPoster263 citations
106. Reinforcement Learning for Integer Programming: Learning to CutPoster263 citations
107. Interpretations are Useful: Penalizing Explanations to Align Neural Networks with Prior KnowledgePoster262 citations
108. Beyond UCB: Optimal and Efficient Contextual Bandits with Regression OraclesPoster258 citations
109. Minimax Pareto Fairness: A Multi Objective PerspectivePoster258 citations
110. Beyond Synthetic Noise: Deep Learning on Controlled Noisy LabelsPoster255 citations
111. Adversarial Filters of Dataset BiasesPoster252 citations
112. Stabilizing Differentiable Architecture Search via Perturbation-based RegularizationPoster252 citations
113. Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile CriticsPoster250 citations
114. Data Valuation using Reinforcement LearningPoster249 citations
115. Efficient Domain Generalization via Common-Specific Low-Rank DecompositionPoster247 citations
116. Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?Poster245 citations
117. Naive Exploration is Optimal for Online LQRPoster244 citations
118. Randomized Smoothing of All Shapes and SizesPoster242 citations
119. Optimal transport mapping via input convex neural networksPoster240 citations
120. Self-supervised Label Augmentation via Input TransformationsPoster240 citations
121. Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural NetworksPoster238 citations
122. Laplacian Regularized Few-Shot LearningPoster237 citations
123. Learning Deep Kernels for Non-Parametric Two-Sample TestsPoster237 citations
124. On the Iteration Complexity of Hypergradient ComputationPoster237 citations
125. Topological AutoencodersPoster236 citations
126. Progressive Identification of True Labels for Partial-Label LearningPoster233 citations
127. Explainable k-Means and k-Medians ClusteringPoster232 citations
128. Do RNN and LSTM have Long Memory?Poster230 citations
129. “Other-Play” for Zero-Shot CoordinationPoster230 citations
130. Unsupervised Speech Decomposition via Triple Information BottleneckPoster226 citations
131. Generalized and Scalable Optimal Sparse Decision TreesPoster224 citations
132. DROCC: Deep Robust One-Class ClassificationPoster222 citations
133. Frequency Bias in Neural Networks for Input of Non-Uniform DensityPoster220 citations
134. Revisiting Training Strategies and Generalization Performance in Deep Metric LearningPoster220 citations
135. Learning with Good Feature Representations in Bandits and in RL with a Generative ModelPoster217 citations
136. Minimax Weight and Q-Function Learning for Off-Policy EvaluationPoster216 citations
137. Deep Coordination GraphsPoster215 citations
138. Safe Reinforcement Learning in Constrained Markov Decision ProcessesPoster215 citations
139. Certified Robustness to Label-Flipping Attacks via Randomized SmoothingPoster214 citations
140. Generalisation error in learning with random features and the hidden manifold modelPoster214 citations
141. Confidence-Aware Learning for Deep Neural NetworksPoster213 citations
142. Graph-based, Self-Supervised Program Repair from Diagnostic FeedbackPoster212 citations
143. Likelihood-free MCMC with Amortized Approximate Ratio EstimatorsPoster212 citations
144. Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training DataPoster211 citations
145. Online Continual Learning from Imbalanced DataPoster210 citations
146. Graph Optimal Transport for Cross-Domain AlignmentPoster209 citations
147. Learning to Branch for Multi-Task LearningPoster209 citations
148. Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot ControlPoster209 citations
149. One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic ControlPoster208 citations
150. Voice Separation with an Unknown Number of Multiple SpeakersPoster208 citations
151. Evaluating Machine Accuracy on ImageNetPoster205 citations
152. GNN-FiLM: Graph Neural Networks with Feature-wise Linear ModulationPoster202 citations
153. Provable Self-Play Algorithms for Competitive Reinforcement LearningPoster202 citations
154. Forecasting Sequential Data Using Consistent Koopman AutoencodersPoster201 citations
155. Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement LearningPoster200 citations
156. Decision Trees for Decision-Making under the Predict-then-Optimize FrameworkPoster199 citations
157. Continuous Graph Neural NetworksPoster198 citations
158. A Graph to Graphs Framework for Retrosynthesis PredictionPoster196 citations
159. Adversarial Robustness Against the Union of Multiple Perturbation ModelsPoster196 citations
160. Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis TestingPoster195 citations
161. Feature Selection using Stochastic GatesPoster194 citations
162. Lorentz Group Equivariant Neural Network for Particle PhysicsPoster193 citations
163. Dynamics of Deep Neural Networks and Neural Tangent HierarchyPoster192 citations
164. Double Trouble in Double Descent: Bias and Variance(s) in the Lazy RegimePoster191 citations
165. Inducing and Exploiting Activation Sparsity for Fast Inference on Deep Neural NetworksPoster191 citations
166. Stochastic Latent Residual Video PredictionPoster189 citations
167. TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular DynamicsPoster189 citations
168. Improving Transformer Optimization Through Better InitializationPoster187 citations
169. Missing Data Imputation using Optimal TransportPoster187 citations
170. Efficiently sampling functions from Gaussian process posteriorsPoster186 citations
171. Graph Structure of Neural NetworksPoster186 citations
172. Predictive Multiplicity in ClassificationPoster186 citations
173. The Effect of Natural Distribution Shift on Question Answering ModelsPoster186 citations
174. Learning with Bounded Instance and Label-dependent Label NoisePoster185 citations
175. Collaborative Machine Learning with Incentive-Aware Model RewardsPoster183 citations
176. Explore, Discover and Learn: Unsupervised Discovery of State-Covering SkillsPoster183 citations
177. Online metric algorithms with untrusted predictionsPoster182 citations
178. Normalizing Flows on Tori and SpheresPoster181 citations
179. InstaHide: Instance-hiding Schemes for Private Distributed LearningPoster180 citations
180. Set Functions for Time SeriesPoster179 citations
181. From ImageNet to Image Classification: Contextualizing Progress on BenchmarksPoster178 citations
182. Minimax-Optimal Off-Policy Evaluation with Linear Function ApproximationPoster178 citations
183. Feature-map-level Online Adversarial Knowledge DistillationPoster176 citations
184. Operation-Aware Soft Channel Pruning using Differentiable MasksPoster176 citations
185. Learning to Navigate The Synthetically Accessible Chemical Space Using Reinforcement LearningPoster175 citations
186. Acceleration for Compressed Gradient Descent in Distributed and Federated OptimizationPoster174 citations
187. Do We Need Zero Training Loss After Achieving Zero Training Error?Poster174 citations
188. Bootstrap Latent-Predictive Representations for Multitask Reinforcement LearningPoster173 citations
189. Dual Mirror Descent for Online Allocation ProblemsPoster173 citations
190. Invertible generative models for inverse problems: mitigating representation error and dataset biasPoster173 citations
191. The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of GeneralizationPoster173 citations
192. Error-Bounded Correction of Noisy LabelsPoster171 citations
193. Context-aware Dynamics Model for Generalization in Model-Based Reinforcement LearningPoster170 citations
194. Invariant Causal Prediction for Block MDPsPoster169 citations
195. Constant Curvature Graph Convolutional NetworksPoster168 citations
196. Confidence-Calibrated Adversarial Training: Generalizing to Unseen AttacksPoster165 citations
197. WaveFlow: A Compact Flow-based Model for Raw AudioPoster164 citations
198. Towards Accurate Post-training Network Quantization via Bit-Split and StitchingPoster163 citations
199. Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient DescentPoster162 citations
200. Multi-Task Learning with User Preferences: Gradient Descent with Controlled Ascent in Pareto OptimizationPoster162 citations
201. Adaptive Reward-Poisoning Attacks against Reinforcement LearningPoster160 citations
202. Bayesian Graph Neural Networks with Adaptive Connection SamplingPoster160 citations
203. SIGUA: Forgetting May Make Learning with Noisy Labels More RobustPoster160 citations
204. When Explanations Lie: Why Many Modified BP Attributions FailPoster160 citations
205. Implicit Class-Conditioned Domain Alignment for Unsupervised Domain AdaptationPoster159 citations
206. Infinite attention: NNGP and NTK for deep attention networksPoster159 citations
207. Lifted Disjoint Paths with Application in Multiple Object TrackingPoster159 citations
208. Retro*: Learning Retrosynthetic Planning with Neural Guided A* SearchPoster158 citations
209. A Game Theoretic Framework for Model Based Reinforcement LearningPoster157 citations
210. On Contrastive Learning for Likelihood-free InferencePoster157 citations
211. From Local SGD to Local Fixed-Point Methods for Federated LearningPoster156 citations
212. A Distributional Framework For Data ValuationPoster155 citations
213. Maximum Likelihood with Bias-Corrected Calibration is Hard-To-Beat at Label Shift AdaptationPoster155 citations
214. The Shapley Taylor Interaction IndexPoster155 citations
215. Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement LearningPoster154 citations
216. Adaptive Gradient Descent without DescentPoster152 citations
217. A Generative Model for Molecular Distance GeometryPoster151 citations
218. Continuously Indexed Domain AdaptationPoster150 citations
219. Multi-fidelity Bayesian Optimization with Max-value Entropy Search and its ParallelizationPoster150 citations
220. Zeno++: Robust Fully Asynchronous SGDPoster150 citations
221. Implicit Learning Dynamics in Stackelberg Games: Equilibria Characterization, Convergence Analysis, and Empirical StudyPoster149 citations
222. Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement LearningPoster149 citations
223. Searching to Exploit Memorization Effect in Learning with Noisy LabelsPoster149 citations
224. SDE-Net: Equipping Deep Neural Networks with Uncertainty EstimatesPoster148 citations
225. Few-shot Relation Extraction via Bayesian Meta-learning on Relation GraphsPoster147 citations
226. Semi-Supervised Learning with Normalizing FlowsPoster147 citations
227. A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level SingletonPoster146 citations
228. Enhanced POET: Open-ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their SolutionsPoster146 citations
229. Fair Generative Modeling via Weak SupervisionPoster146 citations
230. Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODEPoster145 citations
231. Fast and Three-rious: Speeding Up Weak Supervision with Triplet MethodsPoster145 citations
232. Reinforcement Learning for Molecular Design Guided by Quantum MechanicsPoster145 citations
233. The Implicit and Explicit Regularization Effects of DropoutPoster145 citations
234. Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic CircuitsPoster144 citations
235. Momentum Improves Normalized SGDPoster144 citations
236. Learning to Encode Position for Transformer with Continuous Dynamical ModelPoster142 citations
237. Scalable Differentiable Physics for Learning and ControlPoster141 citations
238. On Learning Sets of Symmetric ElementsPoster140 citations
239. Safe Imitation Learning via Fast Bayesian Reward Inference from PreferencesPoster140 citations
240. Imputer: Sequence Modelling via Imputation and Dynamic ProgrammingPoster138 citations
241. Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown TransitionPoster138 citations
242. Optimal Continual Learning has Perfect Memory and is NP-hardPoster138 citations
243. ControlVAE: Controllable Variational AutoencoderPoster137 citations
244. Do GANs always have Nash equilibria?Poster137 citations
245. Decoupled Greedy Learning of CNNsPoster136 citations
246. Encoding Musical Style with Transformer AutoencodersPoster136 citations
247. Progressive Graph Learning for Open-Set Domain AdaptationPoster136 citations
248. Strategic Classification is Causal Modeling in DisguisePoster136 citations
249. Good Subnetworks Provably Exist: Pruning via Greedy Forward SelectionPoster135 citations
250. Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision ProcessesPoster135 citations
251. Structural Language Models of CodePoster135 citations
252. Non-Autoregressive Neural Text-to-SpeechPoster132 citations
253. Learning Efficient Multi-agent Communication: An Information Bottleneck ApproachPoster130 citations
254. Reverse-engineering deep ReLU networksPoster130 citations
255. Federated Learning with Only Positive LabelsPoster129 citations
256. Graph Filtration LearningPoster128 citations
257. Informative Dropout for Robust Representation Learning: A Shape-bias PerspectivePoster128 citations
258. On the Generalization Benefit of Noise in Stochastic Gradient DescentPoster128 citations
259. Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) OptimismPoster128 citations
260. Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden ConfoundersPoster128 citations
261. Complexity of Finding Stationary Points of Nonconvex Nonsmooth FunctionsPoster126 citations
262. Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer NetworksPoster125 citations
263. On the Noisy Gradient Descent that Generalizes as SGDPoster125 citations
264. Relaxing Bijectivity Constraints with Continuously Indexed Normalising FlowsPoster125 citations
265. Two Simple Ways to Learn Individual Fairness Metrics from DataPoster125 citations
266. Bayesian Optimisation over Multiple Continuous and Categorical InputsPoster124 citations
267. Learning with Multiple Complementary LabelsPoster124 citations
268. PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector EliminationPoster122 citations
269. TaskNorm: Rethinking Batch Normalization for Meta-LearningPoster122 citations
270. The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient DescentPoster121 citations
271. Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging ProblemsPoster121 citations
272. Aligned Cross Entropy for Non-Autoregressive Machine TranslationPoster120 citations
273. Concise Explanations of Neural Networks using Adversarial TrainingPoster120 citations
274. GradientDICE: Rethinking Generalized Offline Estimation of Stationary ValuesPoster120 citations
275. Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited ResourcesPoster120 citations
276. Doubly robust off-policy evaluation with shrinkagePoster119 citations
277. Learning Fair Policies in Multi-Objective (Deep) Reinforcement Learning with Average and Discounted RewardsPoster118 citations
278. On Leveraging Pretrained GANs for Generation with Limited DataPoster118 citations
279. Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label RatesPoster118 citations
280. The Tree Ensemble Layer: Differentiability meets Conditional ComputationPoster118 citations
281. An Imitation Learning Approach for Cache ReplacementPoster117 citations
282. Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement LearningPoster117 citations
283. Approximation Capabilities of Neural ODEs and Invertible Residual NetworksPoster116 citations
284. Improved Optimistic Algorithms for Logistic BanditsPoster115 citations
285. Efficient Continuous Pareto Exploration in Multi-Task LearningPoster114 citations
286. AutoGAN-Distiller: Searching to Compress Generative Adversarial NetworksPoster113 citations
287. Self-PU: Self Boosted and Calibrated Positive-Unlabeled TrainingPoster113 citations
288. InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANsPoster112 citations
289. Low-Rank Bottleneck in Multi-head Attention ModelsPoster112 citations
290. On Unbalanced Optimal Transport: An Analysis of Sinkhorn AlgorithmPoster112 citations
291. Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial PerturbationsPoster111 citations
292. The Implicit Regularization of Stochastic Gradient Flow for Least SquaresPoster111 citations
293. The Role of Regularization in Classification of High-dimensional Noisy Gaussian MixturePoster111 citations
294. Curse of Dimensionality on Randomized Smoothing for Certifiable RobustnessPoster110 citations
295. Disentangling Trainability and Generalization in Deep Neural NetworksPoster110 citations
296. Neural Kernels Without TangentsPoster110 citations
297. Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and MorePoster109 citations
298. Fairwashing explanations with off-manifold detergentPoster109 citations
299. Few-shot Domain Adaptation by Causal Mechanism TransferPoster109 citations
300. Gamification of Pure Exploration for Linear BanditsPoster109 citations
301. A Mean Field Analysis Of Deep ResNet And Beyond: Towards Provably Optimization Via Overparameterization From DepthPoster108 citations
302. Attentive Group Equivariant Convolutional NetworksPoster108 citations
303. Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic ReasoningPoster108 citations
304. Implicit Regularization of Random Feature ModelsPoster108 citations
305. Improving the Gating Mechanism of Recurrent Neural NetworksPoster108 citations
306. Adversarial Robustness for CodePoster107 citations
307. Optimistic Policy Optimization with Bandit FeedbackPoster107 citations
308. Robustness to Spurious Correlations via Human AnnotationsPoster106 citations
309. Efficient nonparametric statistical inference on population feature importance using Shapley valuesPoster105 citations
310. PowerNorm: Rethinking Batch Normalization in TransformersPoster105 citations
311. FR-Train: A Mutual Information-Based Approach to Fair and Robust TrainingPoster104 citations
312. Learning Reasoning Strategies in End-to-End Differentiable ProvingPoster104 citations
313. Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without SamplingPoster104 citations
314. On Second-Order Group Influence Functions for Black-Box PredictionsPoster104 citations
315. What Can Learned Intrinsic Rewards Capture?Poster104 citations
316. The Complexity of Finding Stationary Points with Stochastic Gradient DescentPoster103 citations
317. Deep Reinforcement Learning with Robust and Smooth PolicyPoster102 citations
318. Differentiating through the Fréchet MeanPoster102 citations
319. New Oracle-Efficient Algorithms for Private Synthetic Data ReleasePoster102 citations
320. Non-autoregressive Machine Translation with Disentangled Context TransformerPoster102 citations
321. Robust and Stable Black Box ExplanationsPoster102 citations
322. The Usual Suspects? Reassessing Blame for VAE Posterior CollapsePoster102 citations
323. Bayesian Differential Privacy for Machine LearningPoster101 citations
324. Individual Fairness for k-ClusteringPoster101 citations
325. Online Learned Continual Compression with Adaptive Quantization ModulesPoster101 citations
326. Discount Factor as a Regularizer in Reinforcement LearningPoster100 citations
327. Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning AttacksPoster100 citations
328. Small-GAN: Speeding up GAN Training using Core-SetsPoster100 citations
329. Bayesian Experimental Design for Implicit Models by Mutual Information Neural EstimationPoster99 citations
330. Compressive sensing with un-trained neural networks: Gradient descent finds a smooth approximationPoster99 citations
331. Radioactive data: tracing through trainingPoster99 citations
332. Fair Learning with Private Demographic DataPoster98 citations
333. Haar Graph PoolingPoster98 citations
334. On the Number of Linear Regions of Convolutional Neural NetworksPoster98 citations
335. Parametric Gaussian Process RegressorsPoster98 citations
336. A distributional view on multi-objective policy optimizationPoster97 citations
337. Learning Algebraic Multigrid Using Graph Neural NetworksPoster97 citations
338. Monte-Carlo Tree Search as Regularized Policy OptimizationPoster97 citations
339. Multi-objective Bayesian Optimization using Pareto-frontier EntropyPoster96 citations
340. SimGANs: Simulator-Based Generative Adversarial Networks for ECG Synthesis to Improve Deep ECG ClassificationPoster96 citations
341. DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial TrainingPoster95 citations
342. Evaluating the Performance of Reinforcement Learning AlgorithmsPoster95 citations
343. Learning Human Objectives by Evaluating Hypothetical BehaviorPoster95 citations
344. A Finite-Time Analysis of Q-Learning with Neural Network Function ApproximationPoster94 citations
345. Domain Aggregation Networks for Multi-Source Domain AdaptationPoster93 citations
346. Learning What to Defer for Maximum Independent SetsPoster93 citations
347. Logarithmic Regret for Adversarial Online ControlPoster92 citations
348. Multi-Agent Determinantal Q-LearningPoster92 citations
349. On the Generalization Effects of Linear Transformations in Data AugmentationPoster92 citations
350. Countering Language Drift with Seeded Iterated LearningPoster91 citations
351. DeBayes: a Bayesian Method for Debiasing Network EmbeddingsPoster91 citations
352. Deep k-NN for Noisy LabelsPoster91 citations
353. Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: Joint Gradient Estimation and TrackingPoster90 citations
354. Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot TasksPoster90 citations
355. A Tree-Structured Decoder for Image-to-Markup GenerationPoster89 citations
356. Born-Again Tree EnsemblesPoster89 citations
357. Random Hypervolume Scalarizations for Provable Multi-Objective Black Box OptimizationPoster89 citations
358. Automated Synthetic-to-Real GeneralizationPoster88 citations
359. Causal Strategic Linear RegressionPoster88 citations
360. Implicit differentiation of Lasso-type models for hyperparameter optimizationPoster88 citations
361. Improving Generative Imagination in Object-Centric World ModelsPoster88 citations
362. Linear bandits with Stochastic Delayed FeedbackPoster88 citations
363. Measuring Non-Expert Comprehension of Machine Learning Fairness MetricsPoster88 citations
364. Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient DescentPoster88 citations
365. Variational Label EnhancementPoster88 citations
366. Efficiently Solving MDPs with Stochastic Mirror DescentPoster87 citations
367. Interpretable, Multidimensional, Multimodal Anomaly Detection with Negative Sampling for Detection of Device FailurePoster87 citations
368. Adversarial Risk via Optimal Transport and Optimal CouplingsPoster86 citations
369. Domain Adaptive Imitation LearningPoster86 citations
370. Individual Calibration with Randomized ForecastingPoster86 citations
371. Learning Robot Skills with Temporal Variational InferencePoster86 citations
372. Semi-Supervised StyleGAN for Disentanglement LearningPoster86 citations
373. Causal Modeling for Fairness In Dynamical SystemsPoster85 citations
374. Goal-Aware Prediction: Learning to Model What MattersPoster85 citations
375. MetaFun: Meta-Learning with Iterative Functional UpdatesPoster85 citations
376. Proper Network Interpretability Helps Adversarial Robustness in ClassificationPoster85 citations
377. Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian MixturesPoster85 citations
378. Scalable Deep Generative Modeling for Sparse GraphsPoster85 citations
379. Educating Text Autoencoders: Latent Representation Guidance via DenoisingPoster84 citations
380. Interference and Generalization in Temporal Difference LearningPoster84 citations
381. Logarithmic Regret for Learning Linear Quadratic Regulators EfficientlyPoster84 citations
382. Too Relaxed to Be FairPoster84 citations
383. Designing Optimal Dynamic Treatment Regimes: A Causal Reinforcement Learning ApproachPoster83 citations
384. Estimating Generalization under Distribution Shifts via Domain-Invariant RepresentationsPoster83 citations
385. Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over ModulesPoster83 citations
386. An Explicitly Relational Neural Network ArchitecturePoster82 citations
387. Debiased Sinkhorn barycentersPoster82 citations
388. Differentiable Product Quantization for End-to-End Embedding CompressionPoster82 citations
389. Optimizing for the Future in Non-Stationary MDPsPoster82 citations
390. Sparse Gaussian Processes with Spherical Harmonic FeaturesPoster82 citations
391. Visual Grounding of Learned Physical ModelsPoster82 citations
392. Adversarial Learning Guarantees for Linear Hypotheses and Neural NetworksPoster81 citations
393. Learning from Irregularly-Sampled Time Series: A Missing Data PerspectivePoster81 citations
394. Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks Using PAC-Bayesian AnalysisPoster81 citations
395. SoftSort: A Continuous Relaxation for the argsort OperatorPoster81 citations
396. Closing the convergence gap of SGD without replacementPoster80 citations
397. Convolutional Kernel Networks for Graph-Structured DataPoster80 citations
398. Cautious Adaptation For Reinforcement Learning in Safety-Critical SettingsPoster79 citations
399. Evolutionary Reinforcement Learning for Sample-Efficient Multiagent CoordinationPoster79 citations
400. Meta-learning for Mixed Linear RegressionPoster78 citations
401. Provable Representation Learning for Imitation Learning via Bi-level OptimizationPoster78 citations
402. Data preprocessing to mitigate bias: A maximum entropy based approachPoster77 citations
403. Equivariant Neural RenderingPoster77 citations
404. Scalable Nearest Neighbor Search for Optimal TransportPoster77 citations
405. Temporal Phenotyping using Deep Predictive Clustering of Disease ProgressionPoster77 citations
406. What can I do here? A Theory of Affordances in Reinforcement LearningPoster77 citations
407. Automatic Shortcut Removal for Self-Supervised Representation LearningPoster76 citations
408. Constrained Markov Decision Processes via Backward Value FunctionsPoster76 citations
409. FACT: A Diagnostic for Group Fairness Trade-offsPoster76 citations
410. Learning Representations that Support ExtrapolationPoster76 citations
411. Learning to Simulate and Design for Structural EngineeringPoster76 citations
412. Optimal Differential Privacy Composition for Exponential MechanismsPoster76 citations
413. Active World Model Learning with Progress CuriosityPoster75 citations
414. Customizing ML Predictions for Online AlgorithmsPoster75 citations
415. Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential TransitionsPoster75 citations
416. More Data Can Expand The Generalization Gap Between Adversarially Robust and Standard ModelsPoster75 citations
417. On the Convergence of Nesterov’s Accelerated Gradient Method in Stochastic SettingsPoster75 citations
418. In Defense of Uniform Convergence: Generalization via Derandomization with an Application to Interpolating Predictors74 citations
419. Latent Variable Modelling with Hyperbolic Normalizing FlowsPoster74 citations
420. Meta-learning with Stochastic Linear BanditsPoster74 citations
421. Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching ApproachPoster74 citations
422. Private Reinforcement Learning with PAC and Regret GuaranteesPoster74 citations
423. Description Based Text Classification with Reinforcement LearningPoster73 citations
424. Q-value Path Decomposition for Deep Multiagent Reinforcement LearningPoster73 citations
425. Training Neural Networks for and by InterpolationPoster73 citations
426. Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum SearchPoster72 citations
427. Don’t Waste Your Bits! Squeeze Activations and Gradients for Deep Neural Networks via TinyScriptPoster72 citations
428. DropNet: Reducing Neural Network Complexity via Iterative PruningPoster72 citations
429. Adversarial Neural Pruning with Latent Vulnerability SuppressionPoster71 citations
430. Learning Optimal Tree Models under Beam SearchPoster71 citations
431. On Differentially Private Stochastic Convex Optimization with Heavy-tailed DataPoster71 citations
432. Optimizing Data Usage via Differentiable RewardsPoster71 citations
433. Robust Learning with the Hilbert-Schmidt Independence CriterionPoster71 citations
434. The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural NetworksPoster71 citations
435. Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributionsPoster70 citations
436. Convergence of a Stochastic Gradient Method with Momentum for Non-Smooth Non-Convex OptimizationPoster70 citations
437. Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence FunctionsPoster70 citations
438. Graph-based Nearest Neighbor Search: From Practice to TheoryPoster70 citations
439. Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function ApproximationPoster70 citations
440. VFlow: More Expressive Generative Flows with Variational Data AugmentationPoster70 citations
441. Distributionally Robust Policy Evaluation and Learning in Offline Contextual BanditsPoster69 citations
442. Improving generalization by controlling label-noise information in neural network weightsPoster69 citations
443. Moniqua: Modulo Quantized Communication in Decentralized SGDPoster69 citations
444. Quantized Decentralized Stochastic Learning over Directed GraphsPoster69 citations
445. The Differentiable Cross-Entropy MethodPoster69 citations
446. Time-Consistent Self-Supervision for Semi-Supervised LearningPoster69 citations
447. Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary LabelsPoster69 citations
448. Bidirectional Model-based Policy OptimizationPoster68 citations
449. Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?Poster68 citations
450. Estimating Model Uncertainty of Neural Networks in Sparse Information FormPoster68 citations
451. Linear Lower Bounds and Conditioning of Differentiable GamesPoster68 citations
452. Online Learning with Imperfect HintsPoster68 citations
453. Private Query Release Assisted by Public DataPoster68 citations
454. Second-Order Provable Defenses against Adversarial AttacksPoster68 citations
455. Statistically Preconditioned Accelerated Gradient Method for Distributed OptimizationPoster68 citations
456. Fair k-Centers via Maximum MatchingPoster67 citations
457. Full Law Identification in Graphical Models of Missing Data: Completeness ResultsPoster67 citations
458. Identifying Statistical Bias in Dataset ReplicationPoster67 citations
459. On Implicit Regularization in $β$-VAEsPoster67 citations
460. On Variational Learning of Controllable Representations for Text without SupervisionPoster67 citations
461. Population-Based Black-Box Optimization for Biological Sequence DesignPoster67 citations
462. Self-Attentive Associative MemoryPoster67 citations
463. Sharp Statistical Guaratees for Adversarially Robust Gaussian ClassificationPoster67 citations
464. XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot LearningPoster67 citations
465. Loss Function Search for Face RecognitionPoster66 citations
466. Stochastic bandits with arm-dependent delaysPoster66 citations
467. Why bigger is not always better: on finite and infinite neural networksPoster66 citations
468. Distribution Augmentation for Generative ModelingPoster65 citations
469. Scalable Differential Privacy with Certified Robustness in Adversarial LearningPoster65 citations
470. Finite-Time Last-Iterate Convergence for Multi-Agent Learning in GamesPoster64 citations
471. Generalization Error of Generalized Linear Models in High DimensionsPoster64 citations
472. Let’s Agree to Agree: Neural Networks Share Classification Order on Real DatasetsPoster64 citations
473. Revisiting Spatial Invariance with Low-Rank Local ConnectivityPoster64 citations
474. Deep Isometric Learning for Visual RecognitionPoster63 citations
475. Off-Policy Actor-Critic with Shared Experience ReplayPoster63 citations
476. Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient NoisePoster62 citations
477. OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learningPoster62 citations
478. On the consistency of top-k surrogate lossesPoster62 citations
479. Optimizer Benchmarking Needs to Account for Hyperparameter TuningPoster62 citations
480. Stochastic Subspace Cubic Newton MethodPoster62 citations
481. Thompson Sampling Algorithms for Mean-Variance BanditsPoster62 citations
482. Training Binary Neural Networks through Learning with Noisy SupervisionPoster62 citations
483. BINOCULARS for efficient, nonmyopic sequential experimental designPoster61 citations
484. DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette ImagesPoster61 citations
485. Near-optimal Regret Bounds for Stochastic Shortest PathPoster61 citations
486. Safe screening rules for L0-regression from Perspective RelaxationsPoster61 citations
487. Improving Robustness of Deep-Learning-Based Image ReconstructionPoster60 citations
488. Meta Variance Transfer: Learning to Augment from the OthersPoster60 citations
489. Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text ClassificationPoster60 citations
490. A new regret analysis for Adam-type algorithmsPoster59 citations
491. Control Frequency Adaptation via Action Persistence in Batch Reinforcement LearningPoster59 citations
492. Cooperative Multi-Agent Bandits with Heavy TailsPoster59 citations
493. Fast OSCAR and OWL Regression via Safe Screening RulesPoster59 citations
494. Gradient Temporal-Difference Learning with Regularized CorrectionsPoster59 citations
495. Learning To Stop While Learning To PredictPoster59 citations
496. Stochastic Hamiltonian Gradient Methods for Smooth GamesPoster59 citations
497. Super-efficiency of automatic differentiation for functions defined as a minimumPoster59 citations
498. Tails of Lipschitz Triangular FlowsPoster59 citations
499. Class-Weighted Classification: Trade-offs and Robust ApproachesPoster58 citations
500. CoMic: Complementary Task Learning & Mimicry for Reusable SkillsPoster58 citations
501. Intrinsic Reward Driven Imitation Learning via Generative ModelPoster58 citations
502. Learning Autoencoders with Relational RegularizationPoster58 citations
503. Neural Topic Modeling with Continual Lifelong LearningPoster58 citations
504. Small Data, Big Decisions: Model Selection in the Small-Data RegimePoster58 citations
505. The Boomerang SamplerPoster58 citations
506. Universal Equivariant Multilayer PerceptronsPoster58 citations
507. Variational Imitation Learning with Diverse-quality DemonstrationsPoster58 citations
508. Why Are Learned Indexes So Effective?Poster58 citations
509. LowFER: Low-rank Bilinear Pooling for Link PredictionPoster57 citations
510. Non-convex Learning via Replica Exchange Stochastic Gradient MCMCPoster57 citations
511. Parameter-free, Dynamic, and Strongly-Adaptive Online LearningPoster57 citations
512. Private Counting from Anonymous Messages: Near-Optimal Accuracy with Vanishing Communication OverheadPoster57 citations
513. Ready Policy One: World Building Through Active LearningPoster57 citations
514. Stochastic Gradient and Langevin ProcessesPoster57 citations
515. Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate ShiftPoster57 citations
516. Fast and Private Submodular and $k$-Submodular Functions Maximization with Matroid ConstraintsPoster56 citations
517. Information Particle Filter Tree: An Online Algorithm for POMDPs with Belief-Based Rewards on Continuous DomainsPoster56 citations
518. Multi-Agent Routing Value Iteration NetworkPoster56 citations
519. Structured Prediction with Partial Labelling through the Infimum LossPoster56 citations
520. Anderson Acceleration of Proximal Gradient MethodsPoster55 citations
521. Angular Visual HardnessPoster55 citations
522. Knowing The What But Not The Where in Bayesian OptimizationPoster55 citations
523. Momentum-Based Policy Gradient MethodsPoster55 citations
524. Representations for Stable Off-Policy Reinforcement LearningPoster55 citations
525. Spectral Graph Matching and Regularized Quadratic Relaxations: Algorithm and TheoryPoster55 citations
526. Bridging the Gap Between f-GANs and Wasserstein GANsPoster54 citations
527. Context Aware Local Differential PrivacyPoster54 citations
528. Finite-Time Convergence in Continuous-Time OptimizationPoster54 citations
529. PDO-eConvs: Partial Differential Operator Based Equivariant ConvolutionsPoster54 citations
530. A Quantile-based Approach for Hyperparameter Transfer LearningPoster53 citations
531. Extrapolation for Large-batch Training in Deep LearningPoster53 citations
532. Learning Flat Latent Manifolds with VAEsPoster53 citations
533. On the Global Optimality of Model-Agnostic Meta-LearningPoster53 citations
534. Statistically Efficient Off-Policy Policy GradientsPoster53 citations
535. Sub-Goal Trees a Framework for Goal-Based Reinforcement LearningPoster53 citations
536. Symbolic Network: Generalized Neural Policies for Relational MDPsPoster53 citations
537. Training Deep Energy-Based Models with f-Divergence MinimizationPoster53 citations
538. Variational Autoencoders with Riemannian Brownian Motion PriorsPoster53 citations
539. Bayesian Learning from Sequential Data using Gaussian Processes with Signature CovariancesPoster52 citations
540. Does the Markov Decision Process Fit the Data: Testing for the Markov Property in Sequential Decision MakingPoster52 citations
541. Learning Portable Representations for High-Level PlanningPoster52 citations
542. Online Pricing with Offline Data: Phase Transition and Inverse Square LawPoster52 citations
543. Unique Properties of Flat Minima in Deep NetworksPoster52 citations
544. A general recurrent state space framework for modeling neural dynamics during decision-makingPoster51 citations
545. Acceleration through spectral density estimationPoster51 citations
546. Adversarial Attacks on Copyright Detection SystemsPoster51 citations
547. Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural NetworksPoster51 citations
548. How to Solve Fair k-Center in Massive Data ModelsPoster51 citations
549. Source Separation with Deep Generative PriorsPoster51 citations
550. Adaptive Estimator Selection for Off-Policy EvaluationPoster50 citations
551. CAUSE: Learning Granger Causality from Event Sequences using Attribution MethodsPoster50 citations
552. Convergence Rates of Variational Inference in Sparse Deep LearningPoster50 citations
553. Gradient-free Online Learning in Continuous Games with Delayed RewardsPoster50 citations
554. Hierarchically Decoupled Imitation For Morphological TransferPoster50 citations
555. T-GD: Transferable GAN-generated Images Detection FrameworkPoster50 citations
556. The FAST Algorithm for Submodular MaximizationPoster50 citations
557. Tightening Exploration in Upper Confidence Reinforcement LearningPoster50 citations
558. Towards Non-Parametric Drift Detection via Dynamic Adapting Window Independence Drift Detection (DAWIDD)Poster50 citations
559. Accountable Off-Policy Evaluation With Kernel Bellman StatisticsPoster49 citations
560. Hallucinative Topological Memory for Zero-Shot Visual PlanningPoster49 citations
561. Learning with Feature and Distribution Evolvable StreamsPoster49 citations
562. Message Passing Least Squares Framework and its Application to Rotation SynchronizationPoster49 citations
563. Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform SamplingPoster49 citations
564. A Sequential Self Teaching Approach for Improving Generalization in Sound Event RecognitionPoster48 citations
565. Graph Homomorphism ConvolutionPoster48 citations
566. It’s Not What Machines Can Learn, It’s What We Cannot TeachPoster48 citations
567. Learning disconnected manifolds: a no GAN’s landPoster48 citations
568. No-Regret Exploration in Goal-Oriented Reinforcement LearningPoster48 citations
569. Optimal Bounds between f-Divergences and Integral Probability MetricsPoster48 citations
570. Sparse Subspace Clustering with Entropy-NormPoster48 citations
571. Strength from Weakness: Fast Learning Using Weak SupervisionPoster48 citations
572. Structure Adaptive Algorithms for Stochastic BanditsPoster48 citations
573. Training Binary Neural Networks using the Bayesian Learning RulePoster48 citations
574. A Pairwise Fair and Community-preserving Approach to k-Center ClusteringPoster47 citations
575. Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent VariablesPoster47 citations
576. Generalization to New Actions in Reinforcement LearningPoster47 citations
577. Involutive MCMC: a Unifying FrameworkPoster47 citations
578. Learning to Score Behaviors for Guided Policy OptimizationPoster47 citations
579. SGD Learns One-Layer Networks in WGANsPoster47 citations
580. Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance SamplingPoster47 citations
581. Calibration, Entropy Rates, and Memory in Language ModelsPoster46 citations
582. Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian RelaxationPoster46 citations
583. Evolutionary Topology Search for Tensor Network DecompositionPoster46 citations
584. Feature Quantization Improves GAN TrainingPoster46 citations
585. Inertial Block Proximal Methods for Non-Convex Non-Smooth OptimizationPoster46 citations
586. Landscape Connectivity and Dropout Stability of SGD Solutions for Over-parameterized Neural NetworksPoster46 citations
587. Learning Selection Strategies in Buchberger’s AlgorithmPoster46 citations
588. Logistic Regression for Massive Data with Rare EventsPoster46 citations
589. Finding trainable sparse networks through Neural Tangent TransferPoster45 citations
590. Implicit Euler Skip Connections: Enhancing Adversarial Robustness via Numerical StabilityPoster45 citations
591. LTF: A Label Transformation Framework for Correcting Label ShiftPoster45 citations
592. Latent Space Factorisation and Manipulation via Matrix Subspace ProjectionPoster45 citations
593. Perceptual Generative AutoencodersPoster45 citations
594. Two Routes to Scalable Credit Assignment without Weight SymmetryPoster45 citations
595. Amortized Finite Element Analysis for Fast PDE-Constrained OptimizationPoster44 citations
596. Growing Action SpacesPoster44 citations
597. High-dimensional Robust Mean Estimation via Gradient DescentPoster44 citations
598. My Fair Bandit: Distributed Learning of Max-Min Fairness with Multi-player BanditsPoster44 citations
599. Provable Smoothness Guarantees for Black-Box Variational InferencePoster44 citations
600. Scalable Exact Inference in Multi-Output Gaussian ProcessesPoster44 citations
601. Towards Adaptive Residual Network Training: A Neural-ODE PerspectivePoster44 citations
602. Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration for Mean-Field Reinforcement LearningPoster43 citations
603. Coresets for Clustering in Graphs of Bounded TreewidthPoster43 citations
604. Discriminative Adversarial Search for Abstractive SummarizationPoster43 citations
605. Handling the Positive-Definite Constraint in the Bayesian Learning RulePoster43 citations
606. Selective Dyna-Style Planning Under Limited Model CapacityPoster43 citations
607. Streaming k-Submodular Maximization under Noise subject to Size ConstraintPoster43 citations
608. A Flexible Latent Space Model for Multilayer NetworksPoster42 citations
609. An EM Approach to Non-autoregressive Conditional Sequence GenerationPoster42 citations
610. Emergence of Separable Manifolds in Deep Language RepresentationsPoster42 citations
611. Entropy Minimization In Emergent LanguagesPoster42 citations
612. Hypernetwork approach to generating point cloudsPoster42 citations
613. Model Fusion with Kullback-Leibler DivergencePoster42 citations
614. Student-Teacher Curriculum Learning via Reinforcement Learning: Predicting Hospital Inpatient Admission LocationPoster42 citations
615. Universal Average-Case Optimality of Polyak MomentumPoster42 citations
616. Automatic Reparameterisation of Probabilistic ProgramsPoster41 citations
617. Differentially Private Set UnionPoster41 citations
618. Distinguishing Cause from Effect Using Quantiles: Bivariate Quantile Causal DiscoveryPoster41 citations
619. FormulaZero: Distributionally Robust Online Adaptation via Offline Population SynthesisPoster41 citations
620. Stochastic Frank-Wolfe for Constrained Finite-Sum MinimizationPoster41 citations
621. Streaming Submodular Maximization under a k-Set System ConstraintPoster41 citations
622. The Intrinsic Robustness of Stochastic Bandits to Strategic ManipulationPoster41 citations
623. Working Memory GraphsPoster41 citations
624. A simpler approach to accelerated optimization: iterative averaging meets optimismPoster40 citations
625. Deep Streaming Label LearningPoster40 citations
626. Efficiently Learning Adversarially Robust Halfspaces with NoisePoster40 citations
627. On Approximate Thompson Sampling with Langevin AlgorithmsPoster40 citations
628. When are Non-Parametric Methods Robust?Poster40 citations
629. Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer CasePoster39 citations
630. Kernel Methods for Cooperative Multi-Agent Contextual BanditsPoster39 citations
631. AdaScale SGD: A User-Friendly Algorithm for Distributed TrainingPoster38 citations
632. Causal Structure Discovery from Distributions Arising from Mixtures of DAGsPoster38 citations
633. Efficient Intervention Design for Causal Discovery with LatentsPoster38 citations
634. Label-Noise Robust Domain AdaptationPoster38 citations
635. Online mirror descent and dual averaging: keeping pace in the dynamic casePoster38 citations
636. Quadratically Regularized Subgradient Methods for Weakly Convex Optimization with Weakly Convex ConstraintsPoster38 citations
637. Quantum BoostingPoster38 citations
638. Restarted Bayesian Online Change-point Detector achieves Optimal Detection DelayPoster38 citations
639. Smaller, more accurate regression forests using tree alternating optimizationPoster38 citations
640. Stochastic Regret Minimization in Extensive-Form GamesPoster38 citations
641. ACFlow: Flow Models for Arbitrary Conditional LikelihoodsPoster37 citations
642. Adaptive Droplet Routing in Digital Microfluidic Biochips Using Deep Reinforcement LearningPoster37 citations
643. Bio-Inspired Hashing for Unsupervised Similarity SearchPoster37 citations
644. Counterfactual Cross-Validation: Stable Model Selection Procedure for Causal Inference ModelsPoster37 citations
645. Healing Products of Gaussian Process ExpertsPoster37 citations
646. Implicit competitive regularization in GANsPoster37 citations
647. Mapping natural-language problems to formal-language solutions using structured neural representationsPoster37 citations
648. Neural Architecture Search in A Proxy Validation Loss LandscapePoster37 citations
649. Nonparametric Score EstimatorsPoster37 citations
650. Projection-free Distributed Online Convex Optimization with $O(\sqrtT)$ Communication ComplexityPoster37 citations
651. R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in GamesPoster37 citations
652. Training Linear Neural Networks: Non-Local Convergence and Complexity ResultsPoster37 citations
653. Variational Bayesian QuantizationPoster37 citations
654. Alleviating Privacy Attacks via Causal LearningPoster36 citations
655. Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued PoliciesPoster36 citations
656. Convolutional dictionary learning based auto-encoders for natural exponential-family distributionsPoster36 citations
657. Deep Gaussian Markov Random FieldsPoster36 citations
658. Optimal Estimator for Unlabeled Linear RegressionPoster36 citations
659. Optimization Theory for ReLU Neural Networks Trained with Normalization LayersPoster36 citations
660. Stronger and Faster Wasserstein Adversarial AttacksPoster36 citations
661. Understanding and Stabilizing GANs’ Training Dynamics Using Control TheoryPoster36 citations
662. Budgeted Online Influence MaximizationPoster35 citations
663. Characterizing Distribution Equivalence and Structure Learning for Cyclic and Acyclic Directed GraphsPoster35 citations
664. Frequentist Uncertainty in Recurrent Neural Networks via Blockwise Influence FunctionsPoster35 citations
665. On the Expressivity of Neural Networks for Deep Reinforcement LearningPoster35 citations
666. Optimal approximation for unconstrained non-submodular minimizationPoster35 citations
667. Randomly Projected Additive Gaussian Processes for RegressionPoster35 citations
668. Stochastic Gauss-Newton Algorithms for Nonconvex Compositional OptimizationPoster35 citations
669. Boosting Frank-Wolfe by Chasing GradientsPoster34 citations
670. From Importance Sampling to Doubly Robust Policy GradientPoster34 citations
671. Learning to Learn Kernels with Variational Random FeaturesPoster34 citations
672. NetGAN without GAN: From Random Walks to Low-Rank ApproximationsPoster34 citations
673. Quantum Expectation-Maximization for Gaussian mixture modelsPoster34 citations
674. Time-aware Large Kernel ConvolutionsPoster34 citations
675. Adversarial Attacks on Probabilistic Autoregressive Forecasting ModelsPoster33 citations
676. Causal Effect Identifiability under Partial-ObservabilityPoster33 citations
677. Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical SystemsPoster33 citations
678. Empirical Study of the Benefits of Overparameterization in Learning Latent Variable ModelsPoster33 citations
679. How recurrent networks implement contextual processing in sentiment analysisPoster33 citations
680. Self-Concordant Analysis of Frank-Wolfe AlgorithmsPoster33 citations
681. The continuous categorical: a novel simplex-valued exponential familyPoster33 citations
682. Unsupervised Transfer Learning for Spatiotemporal Predictive NetworksPoster33 citations
683. A Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural CircuitsPoster32 citations
684. Aggregation of Multiple KnockoffsPoster32 citations
685. Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine LearningPoster32 citations
686. Batch Stationary Distribution EstimationPoster32 citations
687. Evaluating Lossy Compression Rates of Deep Generative ModelsPoster32 citations
688. Fast Adaptation to New Environments via Policy-Dynamics Value FunctionsPoster32 citations
689. Incremental Sampling Without Replacement for Sequence ModelsPoster32 citations
690. Optimal Randomized First-Order Methods for Least-Squares ProblemsPoster32 citations
691. Privately Learning Markov Random FieldsPoster32 citations
692. Sample Complexity Bounds for 1-bit Compressive Sensing and Binary Stable Embeddings with Generative PriorsPoster32 citations
693. Spread DivergencePoster32 citations
694. Deep Reasoning Networks for Unsupervised Pattern De-mixing with Constraint ReasoningPoster31 citations
695. ECLIPSE: An Extreme-Scale Linear Program Solver for Web-ApplicationsPoster31 citations
696. Faster Graph Embeddings via CoarseningPoster31 citations
697. Margin-aware Adversarial Domain Adaptation with Optimal TransportPoster31 citations
698. Sequential Transfer in Reinforcement Learning with a Generative ModelPoster31 citations
699. Causal Inference using Gaussian Processes with Structured Latent ConfoundersPoster30 citations
700. Confidence Sets and Hypothesis Testing in a Likelihood-Free Inference SettingPoster30 citations
701. Explaining Groups of Points in Low-Dimensional RepresentationsPoster30 citations
702. Feature Noise Induces Loss Discrepancy Across GroupsPoster30 citations
703. Fully Parallel Hyperparameter Search: Reshaped Space-FillingPoster30 citations
704. PENNI: Pruned Kernel Sharing for Efficient CNN InferencePoster30 citations
705. T-Basis: a Compact Representation for Neural NetworksPoster30 citations
706. When deep denoising meets iterative phase retrievalPoster30 citations
707. Accelerated Stochastic Gradient-free and Projection-free MethodsPoster29 citations
708. Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential AdvertisingPoster29 citations
709. Inverse Active Sensing: Modeling and Understanding Timely Decision-MakingPoster29 citations
710. Near-Tight Margin-Based Generalization Bounds for Support Vector MachinesPoster29 citations
711. Predictive Coding for Locally-Linear ControlPoster29 citations
712. Robustifying Sequential Neural ProcessesPoster29 citations
713. Inexact Tensor Methods with Dynamic AccuraciesPoster28 citations
714. Learning Adversarially Robust Representations via Worst-Case Mutual Information MaximizationPoster28 citations
715. Learning Quadratic Games on NetworksPoster28 citations
716. Learning to Rank Learning CurvesPoster28 citations
717. Negative Sampling in Semi-Supervised learningPoster28 citations
718. Recurrent Hierarchical Topic-Guided RNN for Language GenerationPoster28 citations
719. Regularized Optimal Transport is Ground Cost AdversarialPoster28 citations
720. Topologically Densified DistributionsPoster28 citations
721. Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimalityPoster28 citations
722. AR-DAE: Towards Unbiased Neural Entropy Gradient EstimationPoster27 citations
723. Analytic Marching: An Analytic Meshing Solution from Deep Implicit Surface NetworksPoster27 citations
724. Black-box Certification and Learning under Adversarial PerturbationsPoster27 citations
725. Decentralised Learning with Random Features and Distributed Gradient DescentPoster27 citations
726. Deep Divergence LearningPoster27 citations
727. Dispersed Exponential Family Mixture VAEs for Interpretable Text GenerationPoster27 citations
728. Generative Adversarial Imitation Learning with Neural Network Parameterization: Global Optimality and Convergence RatePoster27 citations
729. Improved Sleeping Bandits with Stochastic Action Sets and Adversarial RewardsPoster27 citations
730. Kernel interpolation with continuous volume samplingPoster27 citations
731. On Convergence-Diagnostic based Step Sizes for Stochastic Gradient DescentPoster27 citations
732. On Relativistic f-DivergencesPoster27 citations
733. Sets ClusteringPoster27 citations
734. Thompson Sampling via Local UncertaintyPoster27 citations
735. Uniform Convergence of Rank-weighted LearningPoster27 citations
736. Converging to Team-Maxmin Equilibria in Zero-Sum Multiplayer GamesPoster26 citations
737. Convex Calibrated Surrogates for the Multi-Label F-MeasurePoster26 citations
738. Differentiable Likelihoods for Fast Inversion of ’Likelihood-Free’ Dynamical SystemsPoster26 citations
739. Distributed Online Optimization over a Heterogeneous Network with Any-Batch Mirror DescentPoster26 citations
740. Estimating Q(s,s’) with Deep Deterministic Dynamics GradientsPoster26 citations
741. Multidimensional Shape ConstraintsPoster26 citations
742. NADS: Neural Architecture Distribution Search for Uncertainty AwarenessPoster26 citations
743. Near-linear time Gaussian process optimization with adaptive batching and resparsificationPoster26 citations
744. Neural Clustering ProcessesPoster26 citations
745. Neural Datalog Through Time: Informed Temporal Modeling via Logical SpecificationPoster26 citations
746. On hyperparameter tuning in general clustering problemsmPoster26 citations
747. Rate-distortion optimization guided autoencoder for isometric embedding in Euclidean latent spacePoster26 citations
748. Stochastically Dominant Distributional Reinforcement LearningPoster26 citations
749. Temporal Logic Point ProcessesPoster26 citations
750. The Performance Analysis of Generalized Margin Maximizers on Separable DataPoster26 citations
751. Adding seemingly uninformative labels helps in low data regimesPoster25 citations
752. Adversarial Robustness via Runtime Masking and CleansingPoster25 citations
753. Deep Graph Random Process for Relational-Thinking-Based Speech RecognitionPoster25 citations
754. Improving Molecular Design by Stochastic Iterative Target AugmentationPoster25 citations
755. Information-Theoretic Local Minima Characterization and RegularizationPoster25 citations
756. LP-SparseMAP: Differentiable Relaxed Optimization for Sparse Structured PredictionPoster25 citations
757. Non-Stationary Delayed Bandits with Intermediate ObservationsPoster25 citations
758. On the Sample Complexity of Adversarial Multi-Source PAC LearningPoster25 citations
759. RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayErPoster25 citations
760. Recht-Re Noncommutative Arithmetic-Geometric Mean Conjecture is FalsePoster25 citations
761. Stochastic Optimization for Regularized Wasserstein EstimatorsPoster25 citations
762. Tight Bounds on Minimax Regret under Logarithmic Loss via Self-ConcordancePoster25 citations
763. Towards Understanding the Regularization of Adversarial Robustness on Neural NetworksPoster25 citations
764. A Sample Complexity Separation between Non-Convex and Convex Meta-LearningPoster24 citations
765. Almost Tune-Free Variance ReductionPoster24 citations
766. Divide, Conquer, and Combine: a New Inference Strategy for Probabilistic Programs with Stochastic SupportPoster24 citations
767. Duality in RKHSs with Infinite Dimensional Outputs: Application to Robust LossesPoster24 citations
768. Efficient Policy Learning from Surrogate-Loss Classification ReductionsPoster24 citations
769. Lower Complexity Bounds for Finite-Sum Convex-Concave Minimax Optimization ProblemsPoster24 citations
770. Meta-Learning with Shared Amortized Variational InferencePoster24 citations
771. Minimax Rate for Learning From Pairwise Comparisons in the BTL ModelPoster24 citations
772. Near Input Sparsity Time Kernel Embeddings via Adaptive SamplingPoster24 citations
773. Online Control of the False Coverage Rate and False Sign RatePoster24 citations
774. Optimal Robust Learning of Discrete Distributions from BatchesPoster24 citations
775. Ordinal Non-negative Matrix Factorization for RecommendationPoster24 citations
776. Random extrapolation for primal-dual coordinate descentPoster24 citations
777. Structured Linear Contextual Bandits: A Sharp and Geometric Smoothed AnalysisPoster24 citations
778. Structured Policy Iteration for Linear Quadratic RegulatorPoster24 citations
779. Video Prediction via Example GuidancePoster24 citations
780. Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural NetworksPoster23 citations
781. Efficient Non-conjugate Gaussian Process Factor Models for Spike Count Data using Polynomial ApproximationsPoster23 citations
782. From Chaos to Order: Symmetry and Conservation Laws in Game DynamicsPoster23 citations
783. Go Wide, Then Narrow: Efficient Training of Deep Thin NetworksPoster23 citations
784. Influenza Forecasting Framework based on Gaussian ProcessesPoster23 citations
785. Learning Compound Tasks without Task-specific Knowledge via Imitation and Self-supervised LearningPoster23 citations
786. Multi-Precision Policy Enforced Training (MuPPET) : A Precision-Switching Strategy for Quantised Fixed-Point Training of CNNsPoster23 citations
787. No-Regret and Incentive-Compatible Online LearningPoster23 citations
788. On Lp-norm Robustness of Ensemble Decision Stumps and TreesPoster23 citations
789. One Size Fits All: Can We Train One Denoiser for All Noise Levels?Poster23 citations
790. Parallel Algorithm for Non-Monotone DR-Submodular MaximizationPoster23 citations
791. Predicting Choice with Set-Dependent AggregationPoster23 citations
792. Sparse Shrunk Additive ModelsPoster23 citations
793. Taylor Expansion Policy OptimizationPoster23 citations
794. Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum ProblemsPoster23 citations
795. A Swiss Army Knife for Minimax Optimal TransportPoster22 citations
796. Channel Equilibrium Networks for Learning Deep RepresentationPoster22 citations
797. Communication-Efficient Distributed PCA by Riemannian OptimizationPoster22 citations
798. Deep PQR: Solving Inverse Reinforcement Learning using Anchor Actions22 citations
799. From PAC to Instance-Optimal Sample Complexity in the Plackett-Luce ModelPoster22 citations
800. GraphOpt: Learning Optimization Models of Graph FormationPoster22 citations
801. Graphical Models Meet Bandits: A Variational Thompson Sampling Approach22 citations
802. Learning for Dose Allocation in Adaptive Clinical Trials with Safety ConstraintsPoster22 citations
803. Optimally Solving Two-Agent Decentralized POMDPs Under One-Sided Information SharingPoster22 citations
804. Optimistic Bounds for Multi-output LearningPoster22 citations
805. Predictive Sampling with Forecasting Autoregressive ModelsPoster22 citations
806. Private Outsourced Bayesian OptimizationPoster22 citations
807. Probing Emergent Semantics in Predictive Agents via Question AnsweringPoster22 citations
808. Projective Preferential Bayesian OptimizationPoster22 citations
809. Robust One-Bit Recovery via ReLU Generative Networks: Near-Optimal Statistical Rate and Global Landscape AnalysisPoster22 citations
810. StochasticRank: Global Optimization of Scale-Free Discrete FunctionsPoster22 citations
811. Tensor denoising and completion based on ordinal observationsPoster22 citations
812. Accelerating the diffusion-based ensemble sampling by non-reversible dynamicsPoster21 citations
813. All in the Exponential Family: Bregman Duality in Thermodynamic Variational InferencePoster21 citations
814. An Accelerated DFO Algorithm for Finite-sum Convex FunctionsPoster21 citations
815. Batch Reinforcement Learning with Hyperparameter GradientsPoster21 citations
816. Consistent Structured Prediction with Max-Min Margin Markov NetworksPoster21 citations
817. Constructive Universal High-Dimensional Distribution Generation through Deep ReLU NetworksPoster21 citations
818. Efficient Identification in Linear Structural Causal Models with Auxiliary CutsetsPoster21 citations
819. Learning Task-Agnostic Embedding of Multiple Black-Box Experts for Multi-Task Model FusionPoster21 citations
820. Multinomial Logit Bandit with Low Switching CostPoster21 citations
821. Piecewise Linear Regression via a Difference of Convex FunctionsPoster21 citations
822. Refined bounds for algorithm configuration: The knife-edge of dual class approximabilityPoster21 citations
823. Reserve Pricing in Repeated Second-Price Auctions with Strategic BiddersPoster21 citations
824. Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth ExpansionPoster21 citations
825. Spectral Subsampling MCMC for Stationary Time SeriesPoster21 citations
826. Teaching with Limited Information on the Learner’s BehaviourPoster21 citations
827. Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization?Poster20 citations
828. Black-Box Variational Inference as a Parametric Approximation to Langevin DynamicsPoster20 citations
829. Correlation Clustering with Asymmetric Classification ErrorsPoster20 citations
830. Data Amplification: Instance-Optimal Property EstimationPoster20 citations
831. Decentralized Reinforcement Learning: Global Decision-Making via Local Economic TransactionsPoster20 citations
832. Fiedler Regularization: Learning Neural Networks with Graph SparsityPoster20 citations
833. History-Gradient Aided Batch Size Adaptation for Variance Reduced AlgorithmsPoster20 citations
834. Latent Bernoulli AutoencoderPoster20 citations
835. Non-separable Non-stationary random fieldsPoster20 citations
836. On Efficient Constructions of CheckpointsPoster20 citations
837. Optimizing Black-box Metrics with Adaptive SurrogatesPoster20 citations
838. Oracle Efficient Private Non-Convex OptimizationPoster20 citations
839. Simultaneous Inference for Massive Data: Distributed BootstrapPoster20 citations
840. Spectral Frank-Wolfe Algorithm: Strict Complementarity and Linear ConvergencePoster20 citations
841. Sub-linear Memory Sketches for Near Neighbor Search on Streaming DataPoster20 citations
842. Subspace Fitting Meets Regression: The Effects of Supervision and Orthonormality Constraints on Double Descent of Generalization ErrorsPoster20 citations
843. Undirected Graphical Models as Approximate PosteriorsPoster20 citations
844. Better depth-width trade-offs for neural networks through the lens of dynamical systemsPoster19 citations
845. Bounding the fairness and accuracy of classifiers from population statisticsPoster19 citations
846. Expert Learning through Generalized Inverse Multiobjective Optimization: Models, Insights, and AlgorithmsPoster19 citations
847. Kernelized Stein Discrepancy Tests of Goodness-of-fit for Time-to-Event DataPoster19 citations
848. Learning Calibratable Policies using Programmatic Style-ConsistencyPoster19 citations
849. Learning Similarity Metrics for Numerical SimulationsPoster19 citations
850. Low-Variance and Zero-Variance Baselines for Extensive-Form GamesPoster19 citations
851. Multiresolution Tensor Learning for Efficient and Interpretable Spatial AnalysisPoster19 citations
852. On the Power of Compressed Sensing with Generative ModelsPoster19 citations
853. PackIt: A Virtual Environment for Geometric PlanningPoster19 citations
854. Provable guarantees for decision tree induction: the agnostic settingPoster19 citations
855. Robustness to Programmable String Transformations via Augmented Abstract TrainingPoster19 citations
856. Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message PassingPoster19 citations
857. State Space Expectation Propagation: Efficient Inference Schemes for Temporal Gaussian ProcessesPoster19 citations
858. Transformation of ReLU-based recurrent neural networks from discrete-time to continuous-timePoster19 citations
859. p-Norm Flow Diffusion for Local Graph ClusteringPoster19 citations
860. Can Stochastic Zeroth-Order Frank-Wolfe Method Converge Faster for Non-Convex Problems?Poster18 citations
861. Causal Effect Estimation and Optimal Dose Suggestions in Mobile HealthPoster18 citations
862. Composable Sketches for Functions of Frequencies: Beyond the Worst CasePoster18 citations
863. Explicit Gradient Learning for Black-Box OptimizationPoster18 citations
864. Learnable Group Transform For Time-SeriesPoster18 citations
865. Online Learning with Dependent Stochastic Feedback GraphsPoster18 citations
866. Optimal Non-parametric Learning in Repeated Contextual Auctions with Strategic BuyerPoster18 citations
867. Preference Modeling with Context-Dependent Salient FeaturesPoster18 citations
868. Schatten Norms in Matrix Streams: Hello Sparsity, Goodbye DimensionPoster18 citations
869. Sequence Generation with Mixed RepresentationsPoster18 citations
870. Uncertainty-Aware Lookahead Factor Models for Quantitative InvestingPoster18 citations
871. A Markov Decision Process Model for Socio-Economic Systems Impacted by Climate ChangePoster17 citations
872. Adaptive Adversarial Multi-task Representation LearningPoster17 citations
873. Adversarial Nonnegative Matrix FactorizationPoster17 citations
874. Approximating Stacked and Bidirectional Recurrent Architectures with the Delayed Recurrent Neural NetworkPoster17 citations
875. Boosting for Control of Dynamical SystemsPoster17 citations
876. Combinatorial Pure Exploration for Dueling BanditPoster17 citations
877. Dual-Path Distillation: A Unified Framework to Improve Black-Box AttacksPoster17 citations
878. Error Estimation for Sketched SVD via the BootstrapPoster17 citations
879. Graph Random Neural Features for Distance-Preserving Graph RepresentationsPoster17 citations
880. Input-Sparsity Low Rank Approximation in Schatten NormPoster17 citations
881. Low Bias Low Variance Gradient Estimates for Boolean Stochastic NetworksPoster17 citations
882. MoNet3D: Towards Accurate Monocular 3D Object Localization in Real TimePoster17 citations
883. Modulating Surrogates for Bayesian OptimizationPoster17 citations
884. Multilinear Latent Conditioning for Generating Unseen Attribute CombinationsPoster17 citations
885. Online Dense Subgraph Discovery via Blurred-Graph FeedbackPoster17 citations
886. Orthogonalized SGD and Nested Architectures for Anytime Neural NetworksPoster17 citations
887. Sample Amplification: Increasing Dataset Size even when Learning is ImpossiblePoster17 citations
888. Sparse Convex Optimization via Adaptively Regularized Hard ThresholdingPoster17 citations
889. The Sample Complexity of Best-$k$ Items Selection from Pairwise ComparisonsPoster17 citations
890. Adaptive Region-Based Active LearningPoster16 citations
891. Adaptive Sketching for Fast and Convergent Canonical Polyadic DecompositionPoster16 citations
892. Associative Memory in Iterated Overparameterized Sigmoid AutoencodersPoster16 citations
893. Eliminating the Invariance on the Loss Landscape of Linear AutoencodersPoster16 citations
894. Energy-Based Processes for Exchangeable DataPoster16 citations
895. Exploration Through Reward Biasing: Reward-Biased Maximum Likelihood Estimation for Stochastic Multi-Armed BanditsPoster16 citations
896. Fast Deterministic CUR Matrix Decomposition with Accuracy AssurancePoster16 citations
897. Implicit Generative Modeling for Efficient ExplorationPoster16 citations
898. Inductive-bias-driven Reinforcement Learning For Efficient Schedules in Heterogeneous ClustersPoster16 citations
899. Interpreting Robust Optimization via Adversarial Influence FunctionsPoster16 citations
900. On Conditional Versus Marginal Bias in Multi-Armed BanditsPoster16 citations
901. On Coresets for Regularized RegressionPoster16 citations
902. Reducing Sampling Error in Batch Temporal Difference LearningPoster16 citations
903. Robust Bayesian Classification Using An Optimistic Score RatioPoster16 citations
904. Variance Reduction and Quasi-Newton for Particle-Based Variational InferencePoster16 citations
905. A Free-Energy Principle for Representation LearningPoster15 citations
906. An end-to-end approach for the verification problem: learning the right distancePoster15 citations
907. Asynchronous Coagent NetworksPoster15 citations
908. Continuous-time Lower Bounds for Gradient-based AlgorithmsPoster15 citations
909. Fiduciary BanditsPoster15 citations
910. On the Theoretical Properties of the Network JackknifePoster15 citations
911. Principled learning method for Wasserstein distributionally robust optimization with local perturbationsPoster15 citations
912. Sequential Cooperative Bayesian InferencePoster15 citations
913. Sparsified Linear Programming for Zero-Sum Equilibrium FindingPoster15 citations
914. A Chance-Constrained Generative Framework for Sequence OptimizationPoster14 citations
915. A Geometric Approach to Archetypal Analysis via Sparse ProjectionsPoster14 citations
916. Active Learning on Attributed Graphs via Graph Cognizant Logistic Regression and Preemptive Query GenerationPoster14 citations
917. Boosted Histogram Transform for RegressionPoster14 citations
918. Boosting Deep Neural Network Efficiency with Dual-Module InferencePoster14 citations
919. Curvature-corrected learning dynamics in deep neural networksPoster14 citations
920. Estimation of Bounds on Potential Outcomes For Decision MakingPoster14 citations
921. Generating Programmatic Referring Expressions via Program SynthesisPoster14 citations
922. Inter-domain Deep Gaussian ProcessesPoster14 citations
923. Lookahead-Bounded Q-learningPoster14 citations
924. Polynomial Tensor Sketch for Element-wise Function of Low-Rank MatrixPoster14 citations
925. Streaming Coresets for Symmetric Tensor FactorizationPoster14 citations
926. Supervised Quantile Normalization for Low Rank Matrix FactorizationPoster14 citations
927. Task-Oriented Active Perception and Planning in Environments with Partially Known SemanticsPoster14 citations
928. Variance Reduction in Stochastic Particle-Optimization SamplingPoster14 citations
929. When Demands Evolve Larger and Noisier: Learning and Earning in a Growing EnvironmentPoster14 citations
930. Generative Flows with Matrix ExponentialPoster13 citations
931. Multi-step Greedy Reinforcement Learning AlgorithmsPoster13 citations
932. Multiclass Neural Network Minimization via Tropical Newton Polytope ApproximationPoster13 citations
933. Online Multi-Kernel Learning with Graph-Structured FeedbackPoster13 citations
934. Optimization from Structured Samples for Coverage FunctionsPoster13 citations
935. Provably Efficient Model-based Policy AdaptationPoster13 citations
936. Rank Aggregation from Pairwise Comparisons in the Presence of Adversarial CorruptionsPoster13 citations
937. Recovery of Sparse Signals from a Mixture of Linear SamplesPoster13 citations
938. Self-Modulating Nonparametric Event-Tensor FactorizationPoster13 citations
939. Supervised learning: no loss no cryPoster13 citations
940. A Nearly-Linear Time Algorithm for Exact Community Recovery in Stochastic Block ModelPoster12 citations
941. An end-to-end Differentially Private Latent Dirichlet Allocation Using a Spectral AlgorithmPoster12 citations
942. Bandits with Adversarial ScalingPoster12 citations
943. Bisection-Based Pricing for Repeated Contextual Auctions against Strategic BuyerPoster12 citations
944. BoXHED: Boosted eXact Hazard Estimator with Dynamic covariatesPoster12 citations
945. DINO: Distributed Newton-Type Optimization MethodPoster12 citations
946. Data-Dependent Differentially Private Parameter Learning for Directed Graphical ModelsPoster12 citations
947. Divide and Conquer: Leveraging Intermediate Feature Representations for Quantized Training of Neural NetworksPoster12 citations
948. Fast computation of Nash Equilibria in Imperfect Information GamesPoster12 citations
949. Interpolation between Residual and Non-Residual NetworksPoster12 citations
950. Learning Factorized Weight Matrix for Joint FilteringPoster12 citations
951. On Efficient Low Distortion Ultrametric EmbeddingPoster12 citations
952. On Semi-parametric Inference for BARTPoster12 citations
953. On a projective ensemble approach to two sample test for equality of distributionsPoster12 citations
954. Online Convex Optimization in the Random Order ModelPoster12 citations
955. Robust Pricing in Dynamic Mechanism DesignPoster12 citations
956. Best Arm Identification for Cascading Bandits in the Fixed Confidence SettingPoster11 citations
957. Cost-effectively Identifying Causal Effects When Only Response Variable is ObservablePoster11 citations
958. DeepCoDA: personalized interpretability for compositional health dataPoster11 citations
959. Dissecting Non-Vacuous Generalization Bounds based on the Mean-Field ApproximationPoster11 citations
960. Distance Metric Learning with Joint Representation DiversificationPoster11 citations
961. From Sets to Multisets: Provable Variational Inference for Probabilistic Integer Submodular ModelsPoster11 citations
962. Generalization Guarantees for Sparse Kernel Approximation with Entropic Optimal FeaturesPoster11 citations
963. Improved Communication Cost in Distributed PageRank Computation – A Theoretical StudyPoster11 citations
964. Inferring DQN structure for high-dimensional continuous controlPoster11 citations
965. LazyIter: A Fast Algorithm for Counting Markov Equivalent DAGs and Designing ExperimentsPoster11 citations
966. Learning Opinions in Social NetworksPoster11 citations
967. Learning and Sampling of Atomic Interventions from ObservationsPoster11 citations
968. Neural Network Control Policy Verification With Persistent Adversarial PerturbationPoster11 citations
969. On the Unreasonable Effectiveness of the Greedy Algorithm: Greedy Adapts to SharpnessPoster11 citations
970. Online Bayesian Moment Matching based SAT Solver HeuristicsPoster11 citations
971. Preselection BanditsPoster11 citations
972. Towards Understanding the Dynamics of the First-Order AdversariesPoster11 citations
973. Towards a General Theory of Infinite-Width Limits of Neural ClassifiersPoster11 citations
974. Word-Level Speech Recognition With a Letter to Word EncoderPoster11 citations
975. A Flexible Framework for Nonparametric Graphical Modeling that Accommodates Machine LearningPoster10 citations
976. Bayesian Sparsification of Deep C-valued NetworksPoster10 citations
977. Circuit-Based Intrinsic Methods to Detect OverfittingPoster10 citations
978. Cost-Effective Interactive Attention Learning with Neural Attention ProcessesPoster10 citations
979. DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion PathsPoster10 citations
980. Enhancing Simple Models by Exploiting What They Already KnowPoster10 citations
981. Estimating the Number and Effect Sizes of Non-null HypothesesPoster10 citations
982. Extreme Multi-label Classification from Aggregated LabelsPoster10 citations
983. Familywise Error Rate Control by Interactive UnmaskingPoster10 citations
984. Goodness-of-Fit Tests for Inhomogeneous Random GraphsPoster10 citations
985. Learning Mixtures of Graphs from Epidemic CascadesPoster10 citations
986. Learning the Valuations of a $k$-demand AgentPoster10 citations
987. Nearly Linear Row Sampling Algorithm for Quantile RegressionPoster10 citations
988. Privately detecting changes in unknown distributionsPoster10 citations
989. Scalable Identification of Partially Observed Systems with Certainty-Equivalent EMPoster10 citations
990. Semismooth Newton Algorithm for Efficient Projections onto $\ell_1, ∞$-norm BallPoster10 citations
991. Adversarial Mutual Information for Text GenerationPoster9 citations
992. Choice Set Optimization Under Discrete Choice Models of Group DecisionsPoster9 citations
993. Double Reinforcement Learning for Efficient and Robust Off-Policy EvaluationPoster9 citations
994. Estimating the Error of Randomized Newton Methods: A Bootstrap ApproachPoster9 citations
995. Explainable and Discourse Topic-aware Neural Language UnderstandingPoster9 citations
996. Guided Learning of Nonconvex Models through Successive Functional Gradient OptimizationPoster9 citations
997. Learning Discrete Structured Representations by Adversarially Maximizing Mutual InformationPoster9 citations
998. Learning Structured Latent Factors from Dependent Data:A Generative Model Framework from Information-Theoretic PerspectivePoster9 citations
999. Learning the piece-wise constant graph structure of a varying Ising modelPoster9 citations
1000. Multigrid Neural MemoryPoster9 citations

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