ICLR 2020 Accepted Papers

The full list of 687 papers accepted at ICLR 2020 (International Conference on Learning Representations). 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. ALBERT: A Lite BERT for Self-supervised Learning of Language RepresentationsSpotlight8,832 citations
2. BERTScore: Evaluating Text Generation with BERTPoster6,747 citations
3. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than GeneratorsPoster4,882 citations
4. The Curious Case of Neural Text DegenerationPoster3,518 citations
5. Reformer: The Efficient TransformerTalk3,397 citations
6. On the Convergence of FedAvg on Non-IID DataTalk3,022 citations
7. On the Variance of the Adaptive Learning Rate and BeyondPoster2,552 citations
8. VL-BERT: Pre-training of Generic Visual-Linguistic RepresentationsPoster2,015 citations
9. Strategies for Pre-training Graph Neural NetworksSpotlight1,823 citations
10. DropEdge: Towards Deep Graph Convolutional Networks on Node ClassificationPoster1,783 citations
11. N-BEATS: Neural basis expansion analysis for interpretable time series forecastingPoster1,691 citations
12. Dream to Control: Learning Behaviors by Latent ImaginationSpotlight1,635 citations
13. Once-for-All: Train One Network and Specialize it for Efficient DeploymentPoster1,607 citations
14. AugMix: A Simple Data Processing Method to Improve Robustness and UncertaintyPoster1,605 citations
15. Decoupling Representation and Classifier for Long-Tailed RecognitionPoster1,599 citations
16. Fast is better than free: Revisiting adversarial trainingPoster1,505 citations
17. Federated Learning with Matched AveragingTalk1,489 citations
18. Geom-GCN: Geometric Graph Convolutional NetworksSpotlight1,460 citations
19. Contrastive Representation DistillationPoster1,458 citations
20. GraphSAINT: Graph Sampling Based Inductive Learning MethodPoster1,395 citations
21. DivideMix: Learning with Noisy Labels as Semi-supervised LearningPoster1,342 citations
22. Composition-based Multi-Relational Graph Convolutional NetworksPoster1,247 citations
23. Deep Double Descent: Where Bigger Models and More Data HurtPoster1,228 citations
24. InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information MaximizationSpotlight1,221 citations
25. Large Batch Optimization for Deep Learning: Training BERT in 76 minutesPoster1,205 citations
26. Model Based Reinforcement Learning for AtariSpotlight1,127 citations
27. Fair Resource Allocation in Federated LearningPoster1,079 citations
28. Plug and Play Language Models: A Simple Approach to Controlled Text GenerationPoster1,069 citations
29. LEARNED STEP SIZE QUANTIZATIONPoster1,015 citations
30. Emergent Tool Use From Multi-Agent AutocurriculaSpotlight961 citations
31. Deep Batch Active Learning by Diverse, Uncertain Gradient Lower BoundsTalk957 citations
32. Self-labelling via simultaneous clustering and representation learningSpotlight953 citations
33. Generalization through Memorization: Nearest Neighbor Language ModelsPoster952 citations
34. NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture SearchSpotlight944 citations
35. Improving Adversarial Robustness Requires Revisiting Misclassified ExamplesPoster925 citations
36. PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture SearchSpotlight920 citations
37. DBA: Distributed Backdoor Attacks against Federated LearningPoster907 citations
38. Deep Semi-Supervised Anomaly DetectionPoster824 citations
39. vq-wav2vec: Self-Supervised Learning of Discrete Speech RepresentationsPoster811 citations
40. Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLPoster809 citations
41. Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationPoster802 citations
42. Inductive representation learning on temporal graphsPoster800 citations
43. Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few ExamplesPoster788 citations
44. Picking Winning Tickets Before Training by Preserving Gradient FlowPoster775 citations
45. On the Relationship between Self-Attention and Convolutional LayersPoster767 citations
46. U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image TranslationPoster764 citations
47. A Baseline for Few-Shot Image ClassificationPoster757 citations
48. Fantastic Generalization Measures and Where to Find ThemPoster757 citations
49. Nesterov Accelerated Gradient and Scale Invariance for Adversarial AttacksPoster734 citations
50. Reducing Transformer Depth on Demand with Structured DropoutPoster708 citations
51. PairNorm: Tackling Oversmoothing in GNNsPoster685 citations
52. Your classifier is secretly an energy based model and you should treat it like oneTalk674 citations
53. Learning The Difference That Makes A Difference With Counterfactually-Augmented DataSpotlight661 citations
54. Compressive Transformers for Long-Range Sequence ModellingPoster654 citations
55. Learning To Explore Using Active Neural SLAMPoster649 citations
56. On Mutual Information Maximization for Representation LearningPoster634 citations
57. Neural Text Generation With Unlikelihood TrainingPoster622 citations
58. Why Gradient Clipping Accelerates Training: A Theoretical Justification for AdaptivityTalk609 citations
59. Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence ScoringPoster600 citations
60. A Fair Comparison of Graph Neural Networks for Graph ClassificationPoster588 citations
61. Deep Learning For Symbolic MathematicsSpotlight585 citations
62. Directional Message Passing for Molecular GraphsSpotlight584 citations
63. Graph Neural Networks Exponentially Lose Expressive Power for Node ClassificationSpotlight575 citations
64. FreeLB: Enhanced Adversarial Training for Natural Language UnderstandingSpotlight567 citations
65. DDSP: Differentiable Digital Signal ProcessingSpotlight562 citations
66. CLEVRER: Collision Events for Video Representation and ReasoningSpotlight559 citations
67. BatchEnsemble: an Alternative Approach to Efficient Ensemble and Lifelong LearningPoster550 citations
68. GraphAF: a Flow-based Autoregressive Model for Molecular Graph GenerationPoster544 citations
69. DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion FramesPoster542 citations
70. Graph Convolutional Reinforcement LearningPoster528 citations
71. Cross-Domain Few-Shot Classification via Learned Feature-Wise TransformationSpotlight524 citations
72. Incorporating BERT into Neural Machine TranslationPoster522 citations
73. Dynamics-Aware Unsupervised Discovery of SkillsTalk518 citations
74. TabFact: A Large-scale Dataset for Table-based Fact VerificationPoster517 citations
75. Don't Use Large Mini-batches, Use Local SGDPoster516 citations
76. Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous DrivingPoster515 citations
77. Classification-Based Anomaly Detection for General DataPoster493 citations
78. DiffTaichi: Differentiable Programming for Physical SimulationPoster486 citations
79. Continual learning with hypernetworksSpotlight481 citations
80. Comparing Rewinding and Fine-tuning in Neural Network PruningTalk479 citations
81. On the "steerability" of generative adversarial networksPoster474 citations
82. Adversarial Policies: Attacking Deep Reinforcement LearningPoster472 citations
83. Abductive Commonsense ReasoningPoster468 citations
84. Understanding and Robustifying Differentiable Architecture SearchTalk464 citations
85. How much Position Information Do Convolutional Neural Networks Encode?Spotlight462 citations
86. A Meta-Transfer Objective for Learning to Disentangle Causal MechanismsPoster438 citations
87. Evaluating The Search Phase of Neural Architecture SearchPoster437 citations
88. Lite Transformer with Long-Short Range AttentionPoster437 citations
89. Are Transformers universal approximators of sequence-to-sequence functions?Poster432 citations
90. Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetsSpotlight423 citations
91. Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep LearningPoster412 citations
92. Never Give Up: Learning Directed Exploration StrategiesPoster410 citations
93. Measuring Compositional Generalization: A Comprehensive Method on Realistic DataPoster406 citations
94. Neural Oblivious Decision Ensembles for Deep Learning on Tabular DataPoster402 citations
95. SELF: Learning to Filter Noisy Labels with Self-EnsemblingPoster400 citations
96. Cross-Lingual Ability of Multilingual BERT: An Empirical StudyPoster396 citations
97. Towards Stable and Efficient Training of Verifiably Robust Neural NetworksPoster396 citations
98. Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent BackpropagationPoster393 citations
99. Selection via Proxy: Efficient Data Selection for Deep LearningPoster391 citations
100. Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box EmbeddingsPoster388 citations
101. Gradient Descent Maximizes the Margin of Homogeneous Neural NetworksTalk385 citations
102. Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural NetworksPoster377 citations
103. Federated Adversarial Domain AdaptationPoster373 citations
104. From Variational to Deterministic AutoencodersPoster364 citations
105. A Learning-based Iterative Method for Solving Vehicle Routing ProblemsPoster363 citations
106. MMA Training: Direct Input Space Margin Maximization through Adversarial TrainingPoster358 citations
107. Cyclical Stochastic Gradient MCMC for Bayesian Deep LearningTalk357 citations
108. Pre-training Tasks for Embedding-based Large-scale RetrievalPoster355 citations
109. Tensor Decompositions for Temporal Knowledge Base CompletionPoster355 citations
110. What graph neural networks cannot learn: depth vs widthPoster351 citations
111. Contrastive Learning of Structured World ModelsTalk348 citations
112. Inductive Matrix Completion Based on Graph Neural NetworksSpotlight346 citations
113. Consistency Regularization for Generative Adversarial NetworksPoster337 citations
114. Symplectic ODE-Net: Learning Hamiltonian Dynamics with ControlPoster337 citations
115. Keep Doing What Worked: Behavior Modelling Priors for Offline Reinforcement LearningPoster330 citations
116. Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question AnsweringPoster329 citations
117. VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-LearningPoster329 citations
118. What Can Neural Networks Reason About?Spotlight325 citations
119. Learning Robust Representations via Multi-View Information BottleneckPoster323 citations
120. High Fidelity Speech Synthesis with Adversarial NetworksTalk321 citations
121. GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent RepresentationsPoster316 citations
122. Causal Discovery with Reinforcement LearningTalk315 citations
123. Input Complexity and Out-of-distribution Detection with Likelihood-based Generative ModelsPoster315 citations
124. The Logical Expressiveness of Graph Neural NetworksSpotlight313 citations
125. SQIL: Imitation Learning via Reinforcement Learning with Sparse RewardsPoster312 citations
126. Drawing Early-Bird Tickets: Toward More Efficient Training of Deep NetworksSpotlight310 citations
127. Projection-Based Constrained Policy OptimizationPoster307 citations
128. Gradient-Based Neural DAG LearningPoster306 citations
129. DeepV2D: Video to Depth with Differentiable Structure from MotionPoster305 citations
130. Sign-OPT: A Query-Efficient Hard-label Adversarial AttackPoster305 citations
131. Training binary neural networks with real-to-binary convolutionsPoster298 citations
132. Neural Tangents: Fast and Easy Infinite Neural Networks in PythonSpotlight293 citations
133. Ensemble Distribution DistillationPoster289 citations
134. Symplectic Recurrent Neural NetworksSpotlight286 citations
135. Global Relational Models of Source CodePoster285 citations
136. Semantically-Guided Representation Learning for Self-Supervised Monocular DepthPoster285 citations
137. Revisiting Self-Training for Neural Sequence GenerationPoster282 citations
138. Neural Policy Gradient Methods: Global Optimality and Rates of ConvergencePoster281 citations
139. A Neural Dirichlet Process Mixture Model for Task-Free Continual LearningPoster280 citations
140. Decentralized Deep Learning with Arbitrary Communication CompressionPoster280 citations
141. You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph EmbeddingsPoster273 citations
142. HOPPITY: LEARNING GRAPH TRANSFORMATIONS TO DETECT AND FIX BUGS IN PROGRAMSSpotlight272 citations
143. SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and DecompositionPoster269 citations
144. Meta-Learning with Warped Gradient DescentTalk266 citations
145. Uncertainty-guided Continual Learning with Bayesian Neural NetworksPoster266 citations
146. Language GANs Falling ShortPoster265 citations
147. Hamiltonian Generative NetworksSpotlight264 citations
148. ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningPoster264 citations
149. An Exponential Learning Rate Schedule for Deep LearningSpotlight263 citations
150. Deep Graph Matching ConsensusPoster262 citations
151. LAMOL: LAnguage MOdeling for Lifelong Language LearningPoster261 citations
152. Scaling Autoregressive Video ModelsSpotlight261 citations
153. Dynamic Model Pruning with FeedbackPoster260 citations
154. Adversarial AutoAugmentPoster257 citations
155. Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?Spotlight256 citations
156. FasterSeg: Searching for Faster Real-time Semantic SegmentationPoster255 citations
157. Hyper-SAGNN: a self-attention based graph neural network for hypergraphsPoster254 citations
158. Automatically Discovering and Learning New Visual Categories with Ranking StatisticsPoster250 citations
159. Bridging Mode Connectivity in Loss Landscapes and Adversarial RobustnessPoster249 citations
160. Meta-Learning without MemorizationSpotlight249 citations
161. Network Randomization: A Simple Technique for Generalization in Deep Reinforcement LearningPoster246 citations
162. Understanding the Limitations of Variational Mutual Information EstimatorsPoster246 citations
163. Understanding Knowledge Distillation in Non-autoregressive Machine TranslationPoster245 citations
164. Intriguing Properties of Adversarial Training at ScalePoster244 citations
165. Mixout: Effective Regularization to Finetune Large-scale Pretrained Language ModelsPoster242 citations
166. RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated EnvironmentsPoster241 citations
167. On Identifiability in TransformersPoster237 citations
168. Restricting the Flow: Information Bottlenecks for AttributionTalk237 citations
169. Learning to Control PDEs with Differentiable PhysicsSpotlight235 citations
170. Thieves on Sesame Street! Model Extraction of BERT-based APIsPoster235 citations
171. Few-shot Text Classification with Distributional SignaturesPoster233 citations
172. Generative Models for Effective ML on Private, Decentralized DatasetsPoster232 citations
173. Imitation Learning via Off-Policy Distribution MatchingPoster231 citations
174. StructPool: Structured Graph Pooling via Conditional Random FieldsPoster230 citations
175. Lagrangian Fluid Simulation with Continuous ConvolutionsPoster229 citations
176. Prediction Poisoning: Towards Defenses Against DNN Model Stealing AttacksPoster228 citations
177. Maxmin Q-learning: Controlling the Estimation Bias of Q-learningPoster227 citations
178. A Constructive Prediction of the Generalization Error Across ScalesPoster223 citations
179. Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networksPoster223 citations
180. Reinforcement Learning Based Graph-to-Sequence Model for Natural Question GenerationPoster221 citations
181. The Ingredients of Real World Robotic Reinforcement LearningSpotlight220 citations
182. Estimating counterfactual treatment outcomes over time through adversarially balanced representationsSpotlight218 citations
183. NAS evaluation is frustratingly hardPoster218 citations
184. Curriculum Loss: Robust Learning and Generalization against Label CorruptionPoster217 citations
185. SlowMo: Improving Communication-Efficient Distributed SGD with Slow MomentumPoster217 citations
186. Robust anomaly detection and backdoor attack detection via differential privacyPoster216 citations
187. Behaviour Suite for Reinforcement LearningSpotlight215 citations
188. Depth-Adaptive TransformerPoster215 citations
189. Functional Regularisation for Continual Learning with Gaussian ProcessesPoster215 citations
190. Rethinking Softmax Cross-Entropy Loss for Adversarial RobustnessPoster214 citations
191. Iterative energy-based projection on a normal data manifold for anomaly localizationPoster213 citations
192. GenDICE: Generalized Offline Estimation of Stationary ValuesTalk211 citations
193. Implementation Matters in Deep RL: A Case Study on PPO and TRPOTalk211 citations
194. Disentangling Factors of Variations Using Few LabelsPoster210 citations
195. Adversarial Training and Provable Defenses: Bridging the GapTalk207 citations
196. Intensity-Free Learning of Temporal Point ProcessesSpotlight206 citations
197. CATER: A diagnostic dataset for Compositional Actions & TEmporal ReasoningTalk205 citations
198. MACER: Attack-free and Scalable Robust Training via Maximizing Certified RadiusPoster205 citations
199. Neural Execution of Graph AlgorithmsPoster205 citations
200. Understanding and Improving Information Transfer in Multi-Task LearningPoster205 citations
201. Fast Task Inference with Variational Intrinsic Successor FeaturesTalk203 citations
202. Harnessing the Power of Infinitely Wide Deep Nets on Small-data TasksSpotlight202 citations
203. NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture SearchPoster202 citations
204. Scalable and Order-robust Continual Learning with Additive Parameter DecompositionPoster200 citations
205. StructBERT: Incorporating Language Structures into Pre-training for Deep Language UnderstandingPoster200 citations
206. Provable Filter Pruning for Efficient Neural NetworksPoster199 citations
207. The Early Phase of Neural Network TrainingPoster199 citations
208. A Signal Propagation Perspective for Pruning Neural Networks at InitializationSpotlight198 citations
209. Certified Defenses for Adversarial PatchesPoster198 citations
210. Learning Disentangled Representations for CounterFactual RegressionPoster197 citations
211. Can gradient clipping mitigate label noise?Poster196 citations
212. Convolutional Conditional Neural ProcessesTalk196 citations
213. Multilingual Alignment of Contextual Word RepresentationsPoster196 citations
214. Finite Depth and Width Corrections to the Neural Tangent KernelSpotlight194 citations
215. Meta-Q-LearningTalk193 citations
216. Quantum Algorithms for Deep Convolutional Neural NetworksPoster192 citations
217. Exploring Model-based Planning with Policy NetworksPoster191 citations
218. The Break-Even Point on Optimization Trajectories of Deep Neural NetworksSpotlight191 citations
219. And the Bit Goes Down: Revisiting the Quantization of Neural NetworksSpotlight190 citations
220. Overlearning Reveals Sensitive AttributesPoster189 citations
221. Editable Neural NetworksPoster188 citations
222. On Robustness of Neural Ordinary Differential EquationsSpotlight188 citations
223. A Theory of Usable Information under Computational ConstraintsTalk186 citations
224. Empirical Bayes Transductive Meta-Learning with Synthetic GradientsPoster186 citations
225. Sequential Latent Knowledge Selection for Knowledge-Grounded DialogueSpotlight186 citations
226. Mogrifier LSTMTalk185 citations
227. Rethinking the Hyperparameters for Fine-tuningPoster184 citations
228. Influence-Based Multi-Agent ExplorationSpotlight183 citations
229. Scale-Equivariant Steerable NetworksPoster183 citations
230. Towards neural networks that provably know when they don't knowPoster181 citations
231. Learning Nearly Decomposable Value Functions Via Communication MinimizationPoster178 citations
232. Unrestricted Adversarial Examples via Semantic ManipulationPoster178 citations
233. A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate CasePoster173 citations
234. A critical analysis of self-supervision, or what we can learn from a single imagePoster171 citations
235. Differentiation of Blackbox Combinatorial SolversSpotlight171 citations
236. Observational Overfitting in Reinforcement LearningPoster171 citations
237. Deep Imitative Models for Flexible Inference, Planning, and ControlPoster170 citations
238. Multi-agent Reinforcement Learning for Networked System ControlPoster170 citations
239. Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical SpacePoster169 citations
240. Neural Module Networks for Reasoning over TextPoster169 citations
241. Weakly Supervised Disentanglement with GuaranteesPoster169 citations
242. B-Spline CNNs on Lie groupsPoster167 citations
243. Efficient Probabilistic Logic Reasoning with Graph Neural NetworksPoster167 citations
244. Model-based reinforcement learning for biological sequence designPoster167 citations
245. Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal GenerationPoster166 citations
246. SEED RL: Scalable and Efficient Deep-RL with Accelerated Central InferenceTalk166 citations
247. Residual Energy-Based Models for Text GenerationPoster164 citations
248. Differentially Private Meta-LearningPoster163 citations
249. On the Equivalence between Positional Node Embeddings and Structural Graph RepresentationsPoster162 citations
250. Diverse Trajectory Forecasting with Determinantal Point ProcessesPoster161 citations
251. Improving Generalization in Meta Reinforcement Learning using Learned ObjectivesSpotlight159 citations
252. Robust And Interpretable Blind Image Denoising Via Bias-Free Convolutional Neural NetworksPoster159 citations
253. Sharing Knowledge in Multi-Task Deep Reinforcement LearningPoster159 citations
254. Adversarially robust transfer learningPoster157 citations
255. Monotonic Multihead AttentionPoster157 citations
256. Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLPPoster157 citations
257. Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear NetworksPoster157 citations
258. Unpaired Point Cloud Completion on Real Scans using Adversarial TrainingPoster157 citations
259. Lipschitz constant estimation of Neural Networks via sparse polynomial optimizationPoster156 citations
260. GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph EmbeddingTalk155 citations
261. A Probabilistic Formulation of Unsupervised Text Style TransferSpotlight154 citations
262. Multiplicative Interactions and Where to Find ThemPoster154 citations
263. Training individually fair ML models with sensitive subspace robustnessSpotlight154 citations
264. Learning Compositional Koopman Operators for Model-Based ControlSpotlight152 citations
265. Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)Spotlight151 citations
266. AtomNAS: Fine-Grained End-to-End Neural Architecture SearchPoster150 citations
267. Black-Box Adversarial Attack with Transferable Model-based EmbeddingPoster150 citations
268. Option Discovery using Deep Skill ChainingPoster150 citations
269. Defending Against Physically Realizable Attacks on Image ClassificationSpotlight149 citations
270. RNA Secondary Structure Prediction By Learning Unrolled AlgorithmsTalk149 citations
271. ES-MAML: Simple Hessian-Free Meta LearningPoster148 citations
272. Encoding word order in complex embeddingsSpotlight148 citations
273. Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural NetworksPoster146 citations
274. Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked LayersPoster146 citations
275. Multi-Scale Representation Learning for Spatial Feature Distributions using Grid CellsSpotlight146 citations
276. Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution TasksTalk144 citations
277. Reinforced active learning for image segmentationPoster143 citations
278. Efficient and Information-Preserving Future Frame Prediction and BeyondPoster142 citations
279. LambdaNet: Probabilistic Type Inference using Graph Neural NetworksPoster141 citations
280. Neural Machine Translation with Universal Visual RepresentationSpotlight141 citations
281. Robustness Verification for TransformersPoster141 citations
282. DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity MeasuresPoster140 citations
283. SCALOR: Generative World Models with Scalable Object RepresentationsPoster140 citations
284. Enhancing Adversarial Defense by k-Winners-Take-AllSpotlight139 citations
285. Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement LearningPoster139 citations
286. Asymptotics of Wide Networks from Feynman DiagramsSpotlight137 citations
287. Mixup Inference: Better Exploiting Mixup to Defend Adversarial AttacksPoster136 citations
288. V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous ControlPoster136 citations
289. Robust Reinforcement Learning for Continuous Control with Model MisspecificationPoster135 citations
290. Graph Constrained Reinforcement Learning for Natural Language Action SpacesPoster132 citations
291. Pay Attention to Features, Transfer Learn Faster CNNsPoster132 citations
292. Transformer-XH: Multi-Evidence Reasoning with eXtra Hop AttentionPoster132 citations
293. Controlling generative models with continuous factors of variationsPoster131 citations
294. Conditional Learning of Fair RepresentationsSpotlight129 citations
295. Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading ComprehensionSpotlight129 citations
296. Permutation Equivariant Models for Compositional Generalization in LanguagePoster129 citations
297. Disagreement-Regularized Imitation LearningSpotlight128 citations
298. Explanation by Progressive ExaggerationSpotlight128 citations
299. Fooling Detection Alone is Not Enough: Adversarial Attack against Multiple Object TrackingPoster128 citations
300. Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence ModelsSpotlight128 citations
301. A Generalized Training Approach for Multiagent LearningTalk127 citations
302. Lookahead: A Far-sighted Alternative of Magnitude-based PruningPoster127 citations
303. Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language ModelPoster127 citations
304. Reconstructing continuous distributions of 3D protein structure from cryo-EM imagesSpotlight127 citations
305. Generalization bounds for deep convolutional neural networksPoster125 citations
306. Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDPPoster125 citations
307. BackPACK: Packing more into BackpropTalk124 citations
308. Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement LearningPoster124 citations
309. Understanding Architectures Learnt by Cell-based Neural Architecture SearchPoster124 citations
310. V4D: 4D Convolutional Neural Networks for Video-level Representation LearningPoster123 citations
311. VideoFlow: A Conditional Flow-Based Model for Stochastic Video GenerationPoster123 citations
312. On Solving Minimax Optimization Locally: A Follow-the-Ridge ApproachPoster122 citations
313. AssembleNet: Searching for Multi-Stream Neural Connectivity in Video ArchitecturesPoster121 citations
314. CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement LearningPoster120 citations
315. Counterfactuals uncover the modular structure of deep generative modelsPoster120 citations
316. You Only Train Once: Loss-Conditional Training of Deep NetworksPoster120 citations
317. AutoQ: Automated Kernel-Wise Neural Network QuantizationPoster119 citations
318. Automated Relational Meta-learningPoster119 citations
319. Learning deep graph matching with channel-independent embedding and Hungarian attentionPoster118 citations
320. Memory-Based Graph NetworksPoster118 citations
321. Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley TransformPoster117 citations
322. Low-Resource Knowledge-Grounded Dialogue GenerationPoster117 citations
323. DeepSphere: a graph-based spherical CNNSpotlight116 citations
324. Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar InductionPoster115 citations
325. Capsules with Inverted Dot-Product Attention RoutingPoster115 citations
326. Compositional languages emerge in a neural iterated learning modelPoster115 citations
327. Rényi Fair InferencePoster115 citations
328. RaPP: Novelty Detection with Reconstruction along Projection PathwayPoster114 citations
329. Stochastic AUC Maximization with Deep Neural NetworksPoster114 citations
330. CoPhy: Counterfactual Learning of Physical DynamicsSpotlight113 citations
331. Measuring the Reliability of Reinforcement Learning AlgorithmsSpotlight113 citations
332. Sample Efficient Policy Gradient Methods with Recursive Variance ReductionPoster113 citations
333. Environmental drivers of systematicity and generalization in a situated agentPoster112 citations
334. Identity Crisis: Memorization and Generalization Under Extreme OverparameterizationPoster112 citations
335. Learning Space Partitions for Nearest Neighbor SearchPoster112 citations
336. Adaptive Structural Fingerprints for Graph Attention NetworksPoster111 citations
337. Model-Augmented Actor-Critic: Backpropagating through PathsPoster110 citations
338. Accelerating SGD with momentum for over-parameterized learningPoster109 citations
339. Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized SmoothingPoster108 citations
340. Learning Hierarchical Discrete Linguistic Units from Visually-Grounded SpeechTalk108 citations
341. Theory and Evaluation Metrics for Learning Disentangled RepresentationsPoster108 citations
342. Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule ReconstructionsPoster107 citations
343. Making Efficient Use of Demonstrations to Solve Hard Exploration ProblemsPoster107 citations
344. Robust Local Features for Improving the Generalization of Adversarial TrainingPoster106 citations
345. Simplified Action Decoder for Deep Multi-Agent Reinforcement LearningSpotlight106 citations
346. Sub-policy Adaptation for Hierarchical Reinforcement LearningPoster106 citations
347. Distributed Bandit Learning: Near-Optimal Regret with Efficient CommunicationPoster105 citations
348. Learn to Explain Efficiently via Neural Logic Inductive LearningPoster105 citations
349. Towards Fast Adaptation of Neural Architectures with Meta LearningPoster104 citations
350. Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive InferencePoster104 citations
351. Differentiable Reasoning over a Virtual Knowledge BaseTalk103 citations
352. State Alignment-based Imitation LearningPoster102 citations
353. Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network CompilationPoster101 citations
354. Continual Learning with Bayesian Neural Networks for Non-Stationary DataPoster101 citations
355. Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill DiscoveryPoster100 citations
356. Meta-Learning Acquisition Functions for Transfer Learning in Bayesian OptimizationSpotlight100 citations
357. Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep NetworksPoster100 citations
358. Transferable Perturbations of Deep Feature DistributionsPoster100 citations
359. Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature AttributionPoster99 citations
360. Query-efficient Meta Attack to Deep Neural NetworksPoster99 citations
361. A Closer Look at Deep Policy GradientsTalk98 citations
362. BayesOpt Adversarial AttackPoster98 citations
363. Continual Learning with Adaptive Weights (CLAW)Poster98 citations
364. Learning from Rules Generalizing Labeled ExemplarsSpotlight98 citations
365. On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex LearningPoster98 citations
366. On the Weaknesses of Reinforcement Learning for Neural Machine TranslationPoster98 citations
367. Denoising and Regularization via Exploiting the Structural Bias of Convolutional GeneratorsPoster97 citations
368. Generalization of Two-layer Neural Networks: An Asymptotic ViewpointSpotlight97 citations
369. Improving Neural Language Generation with Spectrum ControlPoster96 citations
370. Learning to Coordinate Manipulation Skills via Skill Behavior DiversificationPoster96 citations
371. A Theoretical Analysis of the Number of Shots in Few-Shot LearningPoster95 citations
372. Variational Recurrent Models for Solving Partially Observable Control TasksPoster95 citations
373. FSPool: Learning Set Representations with Featurewise Sort PoolingPoster94 citations
374. Batch-shaping for learning conditional channel gated networksPoster93 citations
375. Deep neuroethology of a virtual rodentSpotlight93 citations
376. Sign Bits Are All You Need for Black-Box AttacksPoster93 citations
377. Tree-Structured Attention with Hierarchical AccumulationPoster93 citations
378. Jacobian Adversarially Regularized Networks for RobustnessPoster92 citations
379. Principled Weight Initialization for HypernetworksTalk92 citations
380. Unsupervised Model Selection for Variational Disentangled Representation LearningPoster92 citations
381. FEW-SHOT LEARNING ON GRAPHS VIA SUPER-CLASSES BASED ON GRAPH SPECTRAL MEASURESPoster91 citations
382. Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization GuaranteePoster91 citations
383. On Bonus Based Exploration Methods In The Arcade Learning EnvironmentPoster88 citations
384. EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness Against Adversarial AttacksPoster87 citations
385. Linear Symmetric Quantization of Neural Networks for Low-precision Integer HardwarePoster87 citations
386. Dynamically Pruned Message Passing Networks for Large-scale Knowledge Graph ReasoningPoster86 citations
387. Maximum Likelihood Constraint Inference for Inverse Reinforcement LearningSpotlight86 citations
388. Economy Statistical Recurrent Units For Inferring Nonlinear Granger CausalityPoster85 citations
389. Robust Subspace Recovery Layer for Unsupervised Anomaly DetectionPoster85 citations
390. The Implicit Bias of Depth: How Incremental Learning Drives GeneralizationPoster85 citations
391. BREAKING CERTIFIED DEFENSES: SEMANTIC ADVERSARIAL EXAMPLES WITH SPOOFED ROBUSTNESS CERTIFICATESPoster84 citations
392. Curvature Graph NetworkPoster84 citations
393. A Closer Look at the Optimization Landscapes of Generative Adversarial NetworksPoster83 citations
394. Meta-learning curiosity algorithmsPoster83 citations
395. Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial NetsPoster83 citations
396. Gradientless Descent: High-Dimensional Zeroth-Order OptimizationSpotlight81 citations
397. HiLLoC: lossless image compression with hierarchical latent variable modelsPoster81 citations
398. Program Guided AgentSpotlight81 citations
399. Scalable Neural Methods for Reasoning With a Symbolic Knowledge BasePoster81 citations
400. Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified FrameworkPoster80 citations
401. Deformable Kernels: Adapting Effective Receptive Fields for Object DeformationPoster80 citations
402. BlockSwap: Fisher-guided Block Substitution for Network Compression on a BudgetPoster79 citations
403. Conservative Uncertainty Estimation By Fitting Prior NetworksPoster79 citations
404. Smoothness and Stability in GANsPoster79 citations
405. Doubly Robust Bias Reduction in Infinite Horizon Off-Policy EstimationSpotlight78 citations
406. Neural Network Branching for Neural Network VerificationTalk78 citations
407. Physics-aware Difference Graph Networks for Sparsely-Observed DynamicsPoster78 citations
408. A Mutual Information Maximization Perspective of Language Representation LearningSpotlight77 citations
409. Deep Orientation Uncertainty Learning based on a Bingham LossPoster77 citations
410. Minimizing FLOPs to Learn Efficient Sparse RepresentationsPoster77 citations
411. On Universal Equivariant Set NetworksPoster77 citations
412. On the interaction between supervision and self-play in emergent communicationPoster77 citations
413. Reinforced Genetic Algorithm Learning for Optimizing Computation GraphsPoster77 citations
414. PAC Confidence Sets for Deep Neural Networks via Calibrated PredictionPoster76 citations
415. Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction DetectionPoster75 citations
416. Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O KernelPoster75 citations
417. Actor-Critic Provably Finds Nash Equilibria of Linear-Quadratic Mean-Field GamesPoster74 citations
418. Ridge Regression: Structure, Cross-Validation, and SketchingSpotlight74 citations
419. Structured Object-Aware Physics Prediction for Video Modeling and PlanningPoster73 citations
420. Data-Independent Neural Pruning via CoresetsPoster72 citations
421. The intriguing role of module criticality in the generalization of deep networksSpotlight72 citations
422. Image-guided Neural Object RenderingPoster71 citations
423. Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear MapsSpotlight71 citations
424. Abstract Diagrammatic Reasoning with Multiplex Graph NetworksPoster70 citations
425. Data-dependent Gaussian Prior Objective for Language GenerationTalk69 citations
426. Double Neural Counterfactual Regret MinimizationPoster69 citations
427. Learning to solve the credit assignment problemPoster69 citations
428. Watch, Try, Learn: Meta-Learning from Demonstrations and RewardsPoster69 citations
429. A Target-Agnostic Attack on Deep Models: Exploiting Security Vulnerabilities of Transfer LearningPoster68 citations
430. Demystifying Inter-Class DisentanglementPoster68 citations
431. RNNs Incrementally Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients?Poster68 citations
432. RTFM: Generalising to New Environment Dynamics via ReadingPoster68 citations
433. Discovering Motor Programs by Recomposing DemonstrationsPoster66 citations
434. Exploration in Reinforcement Learning with Deep Covering OptionsPoster66 citations
435. Gradient $\ell_1$ Regularization for Quantization RobustnessPoster66 citations
436. AE-OT: A NEW GENERATIVE MODEL BASED ON EXTENDED SEMI-DISCRETE OPTIMAL TRANSPORTPoster65 citations
437. Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based OptimizationPoster65 citations
438. Combining Q-Learning and Search with Amortized Value EstimatesPoster65 citations
439. Stochastic Weight Averaging in Parallel: Large-Batch Training That Generalizes WellPoster65 citations
440. A FRAMEWORK FOR ROBUSTNESS CERTIFICATION OF SMOOTHED CLASSIFIERS USING F-DIVERGENCESPoster64 citations
441. CLN2INV: Learning Loop Invariants with Continuous Logic NetworksPoster64 citations
442. Dynamics-Aware EmbeddingsPoster64 citations
443. Energy-based models for atomic-resolution protein conformationsSpotlight64 citations
444. Four Things Everyone Should Know to Improve Batch NormalizationPoster64 citations
445. Learning to Plan in High Dimensions via Neural Exploration-Exploitation TreesSpotlight64 citations
446. Locality and Compositionality in Zero-Shot LearningPoster64 citations
447. SNODE: Spectral Discretization of Neural ODEs for System IdentificationPoster63 citations
448. Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural NetworksPoster63 citations
449. The Shape of Data: Intrinsic Distance for Data DistributionsPoster63 citations
450. Budgeted Training: Rethinking Deep Neural Network Training Under Resource ConstraintsPoster62 citations
451. CAQL: Continuous Action Q-LearningPoster62 citations
452. Non-Autoregressive Dialog State TrackingPoster62 citations
453. Synthesizing Programmatic Policies that Inductively GeneralizePoster62 citations
454. Neural Arithmetic UnitsSpotlight61 citations
455. Semi-Supervised Generative Modeling for Controllable Speech SynthesisPoster61 citations
456. State-only Imitation with Transition Dynamics MismatchPoster61 citations
457. Understanding Why Neural Networks Generalize Well Through GSNR of ParametersSpotlight61 citations
458. Estimating Gradients for Discrete Random Variables by Sampling without ReplacementSpotlight60 citations
459. GAT: Generative Adversarial Training for Adversarial Example Detection and Robust ClassificationPoster60 citations
460. Meta Dropout: Learning to Perturb Latent Features for GeneralizationPoster60 citations
461. Disentangling neural mechanisms for perceptual groupingSpotlight59 citations
462. Understanding the Limitations of Conditional Generative ModelsPoster59 citations
463. Hypermodels for ExplorationPoster58 citations
464. Meta Reinforcement Learning with Autonomous Inference of Subtask DependenciesPoster58 citations
465. Neural tangent kernels, transportation mappings, and universal approximationPoster58 citations
466. PROGRESSIVE LEARNING AND DISENTANGLEMENT OF HIERARCHICAL REPRESENTATIONSSpotlight58 citations
467. Episodic Reinforcement Learning with Associative MemoryPoster57 citations
468. Probability Calibration for Knowledge Graph Embedding ModelsPoster57 citations
469. Deep Network Classification by Scattering and Homotopy Dictionary LearningPoster56 citations
470. Recurrent neural circuits for contour detectionPoster56 citations
471. Adversarial Lipschitz RegularizationPoster55 citations
472. BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary ActivationsPoster55 citations
473. Convergence of Gradient Methods on Bilinear Zero-Sum GamesPoster55 citations
474. Network DeconvolutionSpotlight55 citations
475. Reinforcement Learning with Competitive Ensembles of Information-Constrained PrimitivesPoster55 citations
476. Stable Rank Normalization for Improved Generalization in Neural Networks and GANsSpotlight55 citations
477. Variational Template Machine for Data-to-Text GenerationPoster55 citations
478. Learning-Augmented Data Stream AlgorithmsPoster53 citations
479. Deep probabilistic subsampling for task-adaptive compressed sensingPoster52 citations
480. Making Sense of Reinforcement Learning and Probabilistic InferenceSpotlight52 citations
481. Reanalysis of Variance Reduced Temporal Difference LearningPoster52 citations
482. SAdam: A Variant of Adam for Strongly Convex FunctionsPoster52 citations
483. Towards Stabilizing Batch Statistics in Backward Propagation of Batch NormalizationPoster52 citations
484. Differentiable learning of numerical rules in knowledge graphsPoster51 citations
485. Scalable Model Compression by Entropy Penalized ReparameterizationPoster51 citations
486. Sparse Coding with Gated Learned ISTASpotlight51 citations
487. GLAD: Learning Sparse Graph RecoveryPoster50 citations
488. Gradients as Features for Deep Representation LearningPoster50 citations
489. On Computation and Generalization of Generative Adversarial Imitation LearningPoster50 citations
490. Physics-as-Inverse-Graphics: Unsupervised Physical Parameter Estimation from VideoPoster50 citations
491. Population-Guided Parallel Policy Search for Reinforcement LearningPoster50 citations
492. The Local Elasticity of Neural NetworksPoster50 citations
493. Thinking While Moving: Deep Reinforcement Learning with Concurrent ControlPoster50 citations
494. Distance-Based Learning from Errors for Confidence CalibrationPoster49 citations
495. Empirical Studies on the Properties of Linear Regions in Deep Neural NetworksPoster49 citations
496. Action Semantics Network: Considering the Effects of Actions in Multiagent SystemsPoster48 citations
497. SpikeGrad: An ANN-equivalent Computation Model for Implementing Backpropagation with SpikesPoster48 citations
498. Vid2Game: Controllable Characters Extracted from Real-World VideosPoster48 citations
499. Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural networkSpotlight47 citations
500. End to End Trainable Active Contours via Differentiable RenderingPoster47 citations
501. Finding and Visualizing Weaknesses of Deep Reinforcement Learning AgentsPoster47 citations
502. Functional vs. parametric equivalence of ReLU networksPoster47 citations
503. Latent Normalizing Flows for Many-to-Many Cross-Domain MappingsPoster47 citations
504. Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural NetworksPoster47 citations
505. On the Global Convergence of Training Deep Linear ResNetsPoster46 citations
506. Order Learning and Its Application to Age EstimationPoster46 citations
507. Truth or backpropaganda? An empirical investigation of deep learning theorySpotlight46 citations
508. Understanding Generalization in Recurrent Neural NetworksPoster46 citations
509. Discriminative Particle Filter Reinforcement Learning for Complex Partial observationsPoster45 citations
510. How to 0wn the NAS in Your Spare TimePoster45 citations
511. Infinite-Horizon Differentiable Model Predictive ControlPoster45 citations
512. Interpretable Complex-Valued Neural Networks for Privacy ProtectionPoster45 citations
513. Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen CategoriesPoster45 citations
514. Mirror-Generative Neural Machine TranslationTalk45 citations
515. Sliced Cramer Synaptic Consolidation for Preserving Deeply Learned RepresentationsSpotlight45 citations
516. word2ket: Space-efficient Word Embeddings inspired by Quantum EntanglementSpotlight45 citations
517. Automated curriculum generation through setter-solver interactionsPoster44 citations
518. Fast Neural Network Adaptation via Parameter Remapping and Architecture SearchPoster44 citations
519. Improved Sample Complexities for Deep Neural Networks and Robust Classification via an All-Layer MarginPoster44 citations
520. In Search for a SAT-friendly Binarized Neural Network ArchitecturePoster43 citations
521. Mixed-curvature Variational AutoencodersPoster43 citations
522. Implicit Bias of Gradient Descent based Adversarial Training on Separable DataPoster42 citations
523. Learning to Move with Affordance MapsPoster42 citations
524. One-Shot Pruning of Recurrent Neural Networks by Jacobian Spectrum EvaluationPoster42 citations
525. Single Episode Policy Transfer in Reinforcement LearningPoster42 citations
526. Knowledge Consistency between Neural Networks and BeyondPoster41 citations
527. Learning Heuristics for Quantified Boolean Formulas through Reinforcement LearningPoster41 citations
528. Learning from Explanations with Neural Execution TreePoster41 citations
529. Mathematical Reasoning in Latent SpaceTalk41 citations
530. Novelty Detection Via BlurringPoster41 citations
531. Building Deep Equivariant Capsule NetworksTalk40 citations
532. Computation Reallocation for Object DetectionPoster40 citations
533. Deep Audio Priors Emerge From Harmonic Convolutional NetworksPoster40 citations
534. Harnessing Structures for Value-Based Planning and Reinforcement LearningTalk40 citations
535. Jelly Bean World: A Testbed for Never-Ending LearningPoster40 citations
536. Learning to Represent Programs with Property SignaturesPoster40 citations
537. Pure and Spurious Critical Points: a Geometric Study of Linear NetworksPoster40 citations
538. Emergence of functional and structural properties of the head direction system by optimization of recurrent neural networksSpotlight39 citations
539. Graph inference learning for semi-supervised classificationPoster39 citations
540. Neural Outlier Rejection for Self-Supervised Keypoint LearningPoster39 citations
541. Watch the Unobserved: A Simple Approach to Parallelizing Monte Carlo Tree SearchTalk39 citations
542. Meta-Learning Deep Energy-Based Memory ModelsPoster38 citations
543. RaCT: Toward Amortized Ranking-Critical Training For Collaborative FilteringPoster38 citations
544. Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog HistoryPoster37 citations
545. Compositional Language Continual LearningPoster37 citations
546. LEARNING EXECUTION THROUGH NEURAL CODE FUSIONPoster37 citations
547. Short and Sparse Deconvolution --- A Geometric ApproachPoster37 citations
548. Black-box Off-policy Estimation for Infinite-Horizon Reinforcement LearningPoster36 citations
549. Effect of Activation Functions on the Training of Overparametrized Neural NetsPoster36 citations
550. Neural Stored-program MemoryPoster36 citations
551. Piecewise linear activations substantially shape the loss surfaces of neural networksPoster36 citations
552. Toward Evaluating Robustness of Deep Reinforcement Learning with Continuous ControlPoster36 citations
553. Unbiased Contrastive Divergence Algorithm for Training Energy-Based Latent Variable ModelsSpotlight36 citations
554. Adversarially Robust Representations with Smooth EncodersPoster35 citations
555. Oblique Decision Trees from Derivatives of ReLU NetworksPoster35 citations
556. A Stochastic Derivative Free Optimization Method with MomentumPoster34 citations
557. Composing Task-Agnostic Policies with Deep Reinforcement LearningPoster34 citations
558. From Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from SpeechPoster34 citations
559. Inductive and Unsupervised Representation Learning on Graph Structured ObjectsPoster34 citations
560. NeurQuRI: Neural Question Requirement Inspector for Answerability Prediction in Machine Reading ComprehensionPoster34 citations
561. Universal Approximation with Certified NetworksPoster34 citations
562. Depth-Width Trade-offs for ReLU Networks via Sharkovsky's TheoremSpotlight33 citations
563. Geometric Analysis of Nonconvex Optimization Landscapes for Overcomplete LearningTalk33 citations
564. Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision ActivationsPoster33 citations
565. Prediction, Consistency, Curvature: Representation Learning for Locally-Linear ControlPoster33 citations
566. The asymptotic spectrum of the Hessian of DNN throughout trainingPoster33 citations
567. Intrinsic Motivation for Encouraging Synergistic BehaviorPoster32 citations
568. Phase Transitions for the Information Bottleneck in Representation LearningPoster32 citations
569. Progressive Memory Banks for Incremental Domain AdaptationPoster32 citations
570. RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image SynthesisPoster32 citations
571. SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable ModelsSpotlight32 citations
572. Unsupervised Clustering using Pseudo-semi-supervised LearningPoster32 citations
573. A closer look at the approximation capabilities of neural networksPoster31 citations
574. MetaPix: Few-Shot Video RetargetingPoster31 citations
575. Robust training with ensemble consensusPoster31 citations
576. Self-Adversarial Learning with Comparative Discrimination for Text GenerationPoster31 citations
577. Learning from Unlabelled Videos Using Contrastive Predictive Neural 3D MappingPoster30 citations
578. ProxSGD: Training Structured Neural Networks under Regularization and ConstraintsPoster30 citations
579. A Latent Morphology Model for Open-Vocabulary Neural Machine TranslationSpotlight29 citations
580. Detecting Extrapolation with Local EnsemblesPoster29 citations
581. Extreme Classification via Adversarial Softmax ApproximationPoster29 citations
582. Spike-based causal inference for weight alignmentPoster29 citations
583. Adjustable Real-time Style TransferPoster28 citations
584. An Inductive Bias for Distances: Neural Nets that Respect the Triangle InequalityPoster28 citations
585. DeFINE: Deep Factorized Input Token Embeddings for Neural Sequence ModelingPoster28 citations
586. Mutual Information Gradient Estimation for Representation LearningPoster28 citations
587. Variance Reduction With Sparse GradientsPoster28 citations
588. Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring in DataPoster27 citations
589. Intrinsically Motivated Discovery of Diverse Patterns in Self-Organizing SystemsTalk27 citations
590. Multi-Agent Interactions Modeling with Correlated PoliciesPoster27 citations
591. AMRL: Aggregated Memory For Reinforcement LearningPoster26 citations
592. Bayesian Meta Sampling for Fast Uncertainty AdaptationPoster25 citations
593. Generalized Convolutional Forest Networks for Domain Generalization and Visual RecognitionPoster25 citations
594. Geometric Insights into the Convergence of Nonlinear TD LearningPoster25 citations
595. Kernelized Wasserstein Natural GradientSpotlight25 citations
596. Understanding l4-based Dictionary Learning: Interpretation, Stability, and RobustnessPoster25 citations
597. Biologically inspired sleep algorithm for increased generalization and adversarial robustness in deep neural networksPoster24 citations
598. Higher-Order Function Networks for Learning Composable 3D Object RepresentationsPoster24 citations
599. Learning transport cost from subset correspondencePoster24 citations
600. Online and stochastic optimization beyond Lipschitz continuity: A Riemannian approachSpotlight24 citations
601. Posterior sampling for multi-agent reinforcement learning: solving extensive games with imperfect informationTalk24 citations
602. The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information BudgetPoster24 citations
603. Escaping Saddle Points Faster with Stochastic MomentumPoster23 citations
604. Learning to LinkPoster23 citations
605. I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers AdaptivelyPoster22 citations
606. Information Geometry of Orthogonal Initializations and TrainingPoster22 citations
607. Learning to Guide Random SearchPoster22 citations
608. Stochastic Conditional Generative Networks with Basis DecompositionPoster22 citations
609. At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks?Spotlight21 citations
610. FSNet: Compression of Deep Convolutional Neural Networks by Filter SummaryPoster21 citations
611. Gap-Aware Mitigation of Gradient StalenessPoster21 citations
612. Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative SamplingPoster21 citations
613. Pruned Graph Scattering TransformsPoster21 citations
614. Target-Embedding Autoencoders for Supervised Representation LearningTalk21 citations
615. Guiding Program Synthesis by Learning to Generate ExamplesPoster20 citations
616. Learning to Learn by Zeroth-Order OraclePoster20 citations
617. Domain Adaptive Multibranch NetworksPoster19 citations
618. On the Need for Topology-Aware Generative Models for Manifold-Based DefensesPoster19 citations
619. Smooth markets: A basic mechanism for organizing gradient-based learnersPoster19 citations
620. Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point CloudsSpotlight19 citations
621. Improved memory in recurrent neural networks with sequential non-normal dynamicsPoster18 citations
622. Kernel of CycleGAN as a principal homogeneous spacePoster18 citations
623. Frequency-based Search-control in DynaPoster17 citations
624. Neural Epitome Search for Architecture-Agnostic Network CompressionPoster16 citations
625. SVQN: Sequential Variational Soft Q-Learning NetworksPoster16 citations
626. Dynamic Time Lag Regression: Predicting What & WhenPoster15 citations
627. Identifying through Flows for Recovering Latent RepresentationsPoster15 citations
628. Lazy-CFR: fast and near-optimal regret minimization for extensive games with imperfect informationPoster15 citations
629. Rotation-invariant clustering of neuronal responses in primary visual cortexTalk15 citations
630. Variational Autoencoders for Highly Multivariate Spatial Point Processes IntensitiesPoster15 citations
631. Expected Information Maximization: Using the I-Projection for Mixture Density EstimationPoster14 citations
632. IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target NetworksPoster14 citations
633. Ranking Policy GradientPoster14 citations
634. Self-Supervised Learning of Appliance UsagePoster14 citations
635. AdvectiveNet: An Eulerian-Lagrangian Fluidic Reservoir for Point Cloud ProcessingPoster13 citations
636. Extreme Tensoring for Low-Memory PreconditioningPoster13 citations
637. Generative Ratio Matching NetworksPoster13 citations
638. Masked Based Unsupervised Content TransferPoster13 citations
639. To Relieve Your Headache of Training an MRF, Take AdVILPoster13 citations
640. Regularizing activations in neural networks via distribution matching with the Wasserstein metricPoster12 citations
641. White Noise Analysis of Neural NetworksSpotlight12 citations
642. Learning Expensive Coordination: An Event-Based Deep RL ApproachPoster11 citations
643. Bounds on Over-Parameterization for Guaranteed Existence of Descent Paths in Shallow ReLU NetworksPoster10 citations
644. Decoding As Dynamic Programming For Recurrent Autoregressive ModelsPoster10 citations
645. Discrepancy Ratio: Evaluating Model Performance When Even Experts Disagree on the TruthPoster10 citations
646. Learning Efficient Parameter Server Synchronization Policies for Distributed SGDPoster10 citations
647. Relational State-Space Model for Stochastic Multi-Object SystemsPoster10 citations
648. Learning representations for binary-classification without backpropagationPoster9 citations
649. Sampling-Free Learning of Bayesian Quantized Neural NetworksPoster9 citations
650. Analysis of Video Feature Learning in Two-Stream CNNs on the Example of Zebrafish Swim Bout ClassificationPoster8 citations
651. Deep Symbolic Superoptimization Without Human KnowledgePoster8 citations
652. Learning the Arrow of Time for Problems in Reinforcement LearningPoster8 citations
653. Probabilistic Connection Importance Inference and Lossless Compression of Deep Neural NetworksPoster8 citations
654. Infinite-horizon Off-Policy Policy Evaluation with Multiple Behavior PoliciesPoster7 citations
655. Low-dimensional statistical manifold embedding of directed graphsPoster7 citations
656. Weakly Supervised Clustering by Exploiting Unique Class CountPoster7 citations
657. Duration-of-Stay Storage Assignment under UncertaintySpotlight6 citations
658. Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$Poster6 citations
659. Span Recovery for Deep Neural Networks with Applications to Input ObfuscationPoster6 citations
660. Training Recurrent Neural Networks Online by Learning Explicit State VariablesPoster6 citations
661. Difference-Seeking Generative Adversarial Network--Unseen Sample GenerationPoster5 citations
662. PCMC-Net: Feature-based Pairwise Choice Markov ChainsPoster5 citations
663. Spectral Embedding of Regularized Block ModelsSpotlight5 citations
664. Adaptive Correlated Monte Carlo for Contextual Categorical Sequence GenerationPoster4 citations
665. Logic and the 2-Simplicial TransformerPoster4 citations
666. Optimal Strategies Against Generative AttacksTalk4 citations
667. Critical initialisation in continuous approximations of binary neural networksPoster3 citations
668. Deep Learning of Determinantal Point Processes via Proper Spectral Sub-gradientPoster3 citations
669. Towards Verified Robustness under Text Deletion InterventionsPoster3 citations
670. Towards a Deep Network Architecture for Structured SmoothnessPoster3 citations
671. Deep 3D Pan via local adaptive "t-shaped" convolutions with global and local adaptive dilationsPoster2 citations
672. Massively Multilingual Sparse Word RepresentationsPoster2 citations
673. Quantifying the Cost of Reliable Photo Authentication via High-Performance Learned Lossy RepresentationsPoster2 citations
674. SNOW: Subscribing to Knowledge via Channel Pooling for Transfer & Lifelong Learning of Convolutional Neural NetworksPoster2 citations
675. Training Generative Adversarial Networks from Incomplete Observations using Factorised DiscriminatorsPoster2 citations
676. Transferring Optimality Across Data Distributions via Homotopy MethodsPoster2 citations
677. Variational Hetero-Encoder Randomized GANs for Joint Image-Text ModelingPoster1 citations
678. Distributionally Robust Neural NetworksPoster
679. Enhancing Transformation-Based Defenses Against Adversarial Attacks with a Distribution ClassifierPoster
680. Implementing Inductive bias for different navigation tasks through diverse RNN attrractorsPoster
681. MEMO: A Deep Network for Flexible Combination of Episodic MemoriesPoster
682. Measuring and Improving the Use of Graph Information in Graph Neural NetworksPoster
683. Mixed Precision DNNs: All you need is a good parametrizationPoster
684. Optimistic Exploration even with a Pessimistic InitialisationPoster
685. ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation AnchoringPoster
686. Real or Not Real, that is the QuestionSpotlight
687. The Gambler's Problem and BeyondPoster

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