ICLR 2019 Accepted Papers

The full list of 502 papers accepted at ICLR 2019 (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. Decoupled Weight Decay RegularizationPoster27,890 citations
2. How Powerful are Graph Neural Networks?Oral10,619 citations
3. GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language UnderstandingPoster8,516 citations
4. Large Scale GAN Training for High Fidelity Natural Image SynthesisOral6,860 citations
5. DARTS: Differentiable Architecture SearchPoster5,782 citations
6. The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural NetworksOral4,377 citations
7. Benchmarking Neural Network Robustness to Common Corruptions and PerturbationsPoster4,260 citations
8. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnessOral3,448 citations
9. Learning deep representations by mutual information estimation and maximizationOral3,384 citations
10. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex SpacePoster3,076 citations
11. ProxylessNAS: Direct Neural Architecture Search on Target Task and HardwarePoster2,375 citations
12. A Closer Look at Few-shot ClassificationPoster2,355 citations
13. Predict then Propagate: Graph Neural Networks meet Personalized PageRankPoster2,182 citations
14. Robustness May Be at Odds with AccuracyPoster2,099 citations
15. Rethinking the Value of Network PruningPoster1,960 citations
16. Deep Anomaly Detection with Outlier ExposurePoster1,914 citations
17. Attention, Learn to Solve Routing Problems!Poster1,846 citations
18. Efficient Lifelong Learning with A-GEMPoster1,788 citations
19. Meta-Learning with Latent Embedding OptimizationPoster1,771 citations
20. Exploration by random network distillationPoster1,708 citations
21. SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITYPoster1,524 citations
22. The relativistic discriminator: a key element missing from standard GANPoster1,409 citations
23. Diversity is All You Need: Learning Skills without a Reward FunctionPoster1,341 citations
24. Local SGD Converges Fast and Communicates LittlePoster1,278 citations
25. Meta-learning with differentiable closed-form solversPoster1,245 citations
26. SNAS: stochastic neural architecture searchPoster1,190 citations
27. Evaluating Robustness of Neural Networks with Mixed Integer ProgrammingPoster1,123 citations
28. Universal TransformersPoster1,087 citations
29. Wizard of Wikipedia: Knowledge-Powered Conversational AgentsPoster1,074 citations
30. How to train your MAMLPoster1,039 citations
31. Deep Graph InfomaxPoster1,037 citations
32. What do you learn from context? Probing for sentence structure in contextualized word representationsPoster1,017 citations
33. FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative ModelsOral1,014 citations
34. LEARNING TO PROPAGATE LABELS: TRANSDUCTIVE PROPAGATION NETWORK FOR FEW-SHOT LEARNINGPoster990 citations
35. Learning to Learn without Forgetting by Maximizing Transfer and Minimizing InterferencePoster979 citations
36. Large-Scale Study of Curiosity-Driven LearningPoster958 citations
37. The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural SupervisionOral929 citations
38. code2seq: Generating Sequences from Structured Representations of CodePoster919 citations
39. Adversarial Audio SynthesisPoster917 citations
40. PATE-GAN: Generating Synthetic Data with Differential Privacy GuaranteesPoster912 citations
41. Residual Non-local Attention Networks for Image RestorationPoster904 citations
42. Do Deep Generative Models Know What They Don't Know?Poster903 citations
43. Gradient Descent Provably Optimizes Over-parameterized Neural NetworksPoster888 citations
44. Adaptive Gradient Methods with Dynamic Bound of Learning RatePoster877 citations
45. An Empirical Study of Example Forgetting during Deep Neural Network LearningPoster848 citations
46. Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetPoster741 citations
47. Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement LearningPoster740 citations
48. Pay Less Attention with Lightweight and Dynamic ConvolutionsOral734 citations
49. Slimmable Neural NetworksPoster731 citations
50. DyRep: Learning Representations over Dynamic GraphsPoster729 citations
51. Efficient Multi-Objective Neural Architecture Search via Lamarckian EvolutionPoster694 citations
52. GAN Dissection: Visualizing and Understanding Generative Adversarial NetworksPoster694 citations
53. Analyzing Inverse Problems with Invertible Neural NetworksPoster687 citations
54. Reward Constrained Policy OptimizationPoster667 citations
55. Enabling Factorized Piano Music Modeling and Generation with the MAESTRO DatasetOral629 citations
56. Recurrent Experience Replay in Distributed Reinforcement LearningPoster629 citations
57. GANSynth: Adversarial Neural Audio SynthesisPoster604 citations
58. Invariant and Equivariant Graph NetworksPoster599 citations
59. Learning Factorized Multimodal RepresentationsPoster561 citations
60. Learning a SAT Solver from Single-Bit SupervisionPoster541 citations
61. Eidetic 3D LSTM: A Model for Video Prediction and BeyondPoster524 citations
62. Query-Efficient Hard-label Black-box Attack: An Optimization-based ApproachPoster520 citations
63. Attentive Neural ProcessesPoster519 citations
64. Deep Lagrangian Networks: Using Physics as Model Prior for Deep LearningPoster511 citations
65. Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted HardwareOral507 citations
66. Diagnosing and Enhancing VAE ModelsPoster505 citations
67. Analysing Mathematical Reasoning Abilities of Neural ModelsPoster496 citations
68. Context-adaptive Entropy Model for End-to-end Optimized Image CompressionPoster495 citations
69. Graph Wavelet Neural NetworkPoster492 citations
70. Adaptive Input Representations for Neural Language ModelingPoster489 citations
71. A Variational Inequality Perspective on Generative Adversarial NetworksPoster487 citations
72. Phase-Aware Speech Enhancement with Deep Complex U-NetPoster476 citations
73. Prior Convictions: Black-box Adversarial Attacks with Bandits and PriorsPoster471 citations
74. ClariNet: Parallel Wave Generation in End-to-End Text-to-SpeechPoster448 citations
75. Towards the first adversarially robust neural network model on MNISTPoster439 citations
76. Supervised Community Detection with Line Graph Neural NetworksPoster437 citations
77. Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and FluidsPoster435 citations
78. Ordered Neurons: Integrating Tree Structures into Recurrent Neural NetworksOral418 citations
79. Fixup Initialization: Residual Learning Without NormalizationPoster413 citations
80. Dynamic Channel Pruning: Feature Boosting and SuppressionPoster410 citations
81. On the Convergence of A Class of Adam-Type Algorithms for Non-Convex OptimizationPoster406 citations
82. Bayesian Deep Convolutional Networks with Many Channels are Gaussian ProcessesPoster401 citations
83. Are adversarial examples inevitable?Poster392 citations
84. Learning when to Communicate at Scale in Multiagent Cooperative and Competitive TasksPoster391 citations
85. Visual Semantic Navigation using Scene PriorsPoster391 citations
86. Learning protein sequence embeddings using information from structurePoster382 citations
87. Understanding Straight-Through Estimator in Training Activation Quantized Neural NetsPoster382 citations
88. Deep Decoder: Concise Image Representations from Untrained Non-convolutional NetworksPoster374 citations
89. A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and DistillationPoster368 citations
90. Learning Multi-Level Hierarchies with HindsightPoster368 citations
91. Lagging Inference Networks and Posterior Collapse in Variational AutoencodersPoster367 citations
92. Optimistic mirror descent in saddle-point problems: Going the extra (gradient) milePoster366 citations
93. Episodic Curiosity through ReachabilityPoster359 citations
94. Poincare Glove: Hyperbolic Word EmbeddingsPoster357 citations
95. Neural Logic MachinesPoster352 citations
96. BA-Net: Dense Bundle Adjustment NetworksOral351 citations
97. Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation LearningPoster348 citations
98. Understanding and Improving Interpolation in Autoencoders via an Adversarial RegularizerPoster338 citations
99. Graph HyperNetworks for Neural Architecture SearchPoster331 citations
100. Meta-Learning Probabilistic Inference for PredictionPoster330 citations
101. Learning Multimodal Graph-to-Graph Translation for Molecule OptimizationPoster327 citations
102. FUNCTIONAL VARIATIONAL BAYESIAN NEURAL NETWORKSPoster325 citations
103. Three Mechanisms of Weight Decay RegularizationPoster323 citations
104. A Convergence Analysis of Gradient Descent for Deep Linear Neural NetworksPoster322 citations
105. Deep Convolutional Networks as shallow Gaussian ProcessesPoster321 citations
106. Self-Monitoring Navigation Agent via Auxiliary Progress EstimationPoster318 citations
107. Representation Degeneration Problem in Training Natural Language Generation ModelsPoster311 citations
108. Riemannian Adaptive Optimization MethodsPoster311 citations
109. Explaining Image Classifiers by Counterfactual GenerationPoster308 citations
110. LanczosNet: Multi-Scale Deep Graph Convolutional NetworksPoster307 citations
111. Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionalityPoster304 citations
112. Hyperbolic Attention NetworksPoster302 citations
113. Unsupervised Learning via Meta-LearningPoster299 citations
114. Hierarchical Generative Modeling for Controllable Speech SynthesisPoster297 citations
115. MisGAN: Learning from Incomplete Data with Generative Adversarial NetworksPoster295 citations
116. There Are Many Consistent Explanations of Unlabeled Data: Why You Should AveragePoster294 citations
117. DPSNet: End-to-end Deep Plane Sweep StereoPoster288 citations
118. Learning Exploration Policies for NavigationPoster288 citations
119. AntisymmetricRNN: A Dynamical System View on Recurrent Neural NetworksPoster284 citations
120. Gradient descent aligns the layers of deep linear networksPoster284 citations
121. Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based ControlPoster284 citations
122. Towards Understanding Regularization in Batch NormalizationPoster283 citations
123. Robust Conditional Generative Adversarial NetworksPoster282 citations
124. Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information FlowPoster282 citations
125. Multilingual Neural Machine Translation with Knowledge DistillationPoster280 citations
126. Structured Neural SummarizationPoster279 citations
127. Multiple-Attribute Text RewritingPoster278 citations
128. Learning to Schedule Communication in Multi-agent Reinforcement LearningPoster273 citations
129. Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical GuaranteesPoster270 citations
130. Learning Mixed-Curvature Representations in Product SpacesPoster270 citations
131. Learning Robust Representations by Projecting Superficial Statistics OutOral270 citations
132. L-Shapley and C-Shapley: Efficient Model Interpretation for Structured DataPoster268 citations
133. Deep reinforcement learning with relational inductive biasesPoster265 citations
134. RelGAN: Relational Generative Adversarial Networks for Text GenerationPoster265 citations
135. Regularized Learning for Domain Adaptation under Label ShiftsPoster263 citations
136. Differentiable Learning-to-Normalize via Switchable NormalizationPoster262 citations
137. LayoutGAN: Generating Graphic Layouts with Wireframe DiscriminatorsPoster262 citations
138. BabyAI: A Platform to Study the Sample Efficiency of Grounded Language LearningPoster259 citations
139. Near-Optimal Representation Learning for Hierarchical Reinforcement LearningPoster258 citations
140. Optimal Control Via Neural Networks: A Convex ApproachPoster257 citations
141. ProMP: Proximal Meta-Policy SearchPoster255 citations
142. Capsule Graph Neural NetworkPoster254 citations
143. Deep learning generalizes because the parameter-function map is biased towards simple functionsPoster253 citations
144. Diversity-Sensitive Conditional Generative Adversarial NetworksPoster253 citations
145. Predicting the Generalization Gap in Deep Networks with Margin DistributionsPoster249 citations
146. Deterministic Variational Inference for Robust Bayesian Neural NetworksOral248 citations
147. Boosting Robustness Certification of Neural NetworksPoster241 citations
148. Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size InputsPoster238 citations
149. Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RLPoster236 citations
150. The Singular Values of Convolutional LayersPoster234 citations
151. Training for Faster Adversarial Robustness Verification via Inducing ReLU StabilityPoster234 citations
152. Non-vacuous Generalization Bounds at the ImageNet Scale: a PAC-Bayesian Compression ApproachPoster232 citations
153. ALISTA: Analytic Weights Are As Good As Learned Weights in LISTAPoster227 citations
154. Adversarial Reprogramming of Neural NetworksPoster227 citations
155. Generative Code Modeling with GraphsPoster227 citations
156. signSGD with Majority Vote is Communication Efficient and Fault TolerantPoster227 citations
157. Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural NetworkPoster226 citations
158. Multi-step Retriever-Reader Interaction for Scalable Open-domain Question AnsweringPoster225 citations
159. Relaxed Quantization for Discretized Neural NetworksPoster224 citations
160. INVASE: Instance-wise Variable Selection using Neural NetworksPoster218 citations
161. Identifying and Controlling Important Neurons in Neural Machine TranslationPoster218 citations
162. A Mean Field Theory of Batch NormalizationPoster217 citations
163. Characterizing Audio Adversarial Examples Using Temporal DependencyPoster217 citations
164. Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response FunctionsPoster216 citations
165. InstaGAN: Instance-aware Image-to-Image TranslationPoster215 citations
166. Multi-class classification without multi-class labelsPoster215 citations
167. Spherical CNNs on Unstructured GridsPoster215 citations
168. Preventing Posterior Collapse with delta-VAEsPoster214 citations
169. Learning Localized Generative Models for 3D Point Clouds via Graph ConvolutionPoster213 citations
170. Critical Learning Periods in Deep NetworksPoster211 citations
171. Overcoming Catastrophic Forgetting for Continual Learning via Model AdaptationPoster211 citations
172. DELTA: DEEP LEARNING TRANSFER USING FEATURE MAP WITH ATTENTION FOR CONVOLUTIONAL NETWORKSPoster207 citations
173. SOM-VAE: Interpretable Discrete Representation Learning on Time SeriesPoster205 citations
174. Systematic Generalization: What Is Required and Can It Be Learned?Poster202 citations
175. Excessive Invariance Causes Adversarial VulnerabilityPoster201 citations
176. Unsupervised Control Through Non-Parametric Discriminative RewardsPoster201 citations
177. CEM-RL: Combining evolutionary and gradient-based methods for policy searchPoster197 citations
178. Interpolation-Prediction Networks for Irregularly Sampled Time SeriesPoster197 citations
179. Global-to-local Memory Pointer Networks for Task-Oriented DialoguePoster196 citations
180. Probabilistic Recursive Reasoning for Multi-Agent Reinforcement LearningPoster196 citations
181. Stochastic Optimization of Sorting Networks via Continuous RelaxationsPoster195 citations
182. The Limitations of Adversarial Training and the Blind-Spot AttackPoster194 citations
183. Structured Adversarial Attack: Towards General Implementation and Better InterpretabilityPoster193 citations
184. Execution-Guided Neural Program SynthesisPoster192 citations
185. Measuring Compositionality in Representation LearningPoster192 citations
186. Variational Autoencoder with Arbitrary ConditioningPoster192 citations
187. Learning-Based Frequency Estimation AlgorithmsPoster191 citations
188. InfoBot: Transfer and Exploration via the Information BottleneckPoster189 citations
189. Quasi-hyperbolic momentum and Adam for deep learningPoster189 citations
190. Emergent Coordination Through CompetitionPoster186 citations
191. Hierarchical interpretations for neural network predictionsPoster186 citations
192. On the Turing Completeness of Modern Neural Network ArchitecturesPoster186 citations
193. Generalizable Adversarial Training via Spectral NormalizationPoster183 citations
194. Quaternion Recurrent Neural NetworksPoster183 citations
195. Trellis Networks for Sequence ModelingPoster181 citations
196. How Important is a NeuronPoster179 citations
197. Measuring and regularizing networks in function spacePoster179 citations
198. Neural Probabilistic Motor Primitives for Humanoid ControlPoster177 citations
199. Sample Efficient Adaptive Text-to-SpeechPoster177 citations
200. Learning what and where to attendPoster176 citations
201. Learning to Understand Goal Specifications by Modelling RewardPoster175 citations
202. Learning Protein Structure with a Differentiable SimulatorOral174 citations
203. Practical lossless compression with latent variables using bits back codingPoster174 citations
204. Improving Generalization and Stability of Generative Adversarial NetworksPoster173 citations
205. Amortized Bayesian Meta-LearningPoster170 citations
206. Improving the Generalization of Adversarial Training with Domain AdaptationPoster170 citations
207. Learning to Infer and Execute 3D Shape ProgramsPoster169 citations
208. DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-EncoderPoster168 citations
209. Discriminator Rejection SamplingPoster168 citations
210. Neural Program Repair by Jointly Learning to Localize and RepairPoster167 citations
211. Woulda, Coulda, Shoulda: Counterfactually-Guided Policy SearchPoster166 citations
212. Exemplar Guided Unsupervised Image-to-Image Translation with Semantic ConsistencyPoster165 citations
213. Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic TopologyPoster165 citations
214. Stable Recurrent ModelsPoster165 citations
215. GENERATING HIGH FIDELITY IMAGES WITH SUBSCALE PIXEL NETWORKS AND MULTIDIMENSIONAL UPSCALINGOral163 citations
216. Temporal Difference Variational Auto-EncoderOral161 citations
217. A Universal Music Translation NetworkPoster160 citations
218. Universal Successor Features ApproximatorsPoster160 citations
219. Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense TrafficPoster159 citations
220. Learning Neural PDE Solvers with Convergence GuaranteesPoster157 citations
221. From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction FollowingPoster153 citations
222. Learning To SimulatePoster153 citations
223. Bias-Reduced Uncertainty Estimation for Deep Neural ClassifiersPoster150 citations
224. Learning Actionable Representations with Goal Conditioned PoliciesPoster150 citations
225. Meta-Learning Update Rules for Unsupervised Representation LearningOral150 citations
226. SPIGAN: Privileged Adversarial Learning from SimulationPoster150 citations
227. Selfless Sequential LearningPoster150 citations
228. TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre TransferPoster146 citations
229. FlowQA: Grasping Flow in History for Conversational Machine ComprehensionPoster145 citations
230. Reasoning About Physical Interactions with Object-Oriented Prediction and PlanningPoster145 citations
231. Learning from Positive and Unlabeled Data with a Selection BiasPoster143 citations
232. CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the WildPoster141 citations
233. Spreading vectors for similarity searchPoster139 citations
234. Theoretical Analysis of Auto Rate-Tuning by Batch NormalizationPoster139 citations
235. Doubly Reparameterized Gradient Estimators for Monte Carlo ObjectivesPoster137 citations
236. On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step LengthPoster137 citations
237. An analytic theory of generalization dynamics and transfer learning in deep linear networksPoster136 citations
238. Learning to Represent EditsPoster133 citations
239. Modeling Uncertainty with Hedged Instance EmbeddingsPoster133 citations
240. No Training Required: Exploring Random Encoders for Sentence ClassificationPoster133 citations
241. On Self Modulation for Generative Adversarial NetworksPoster133 citations
242. ProxQuant: Quantized Neural Networks via Proximal OperatorsPoster133 citations
243. Stable Opponent Shaping in Differentiable GamesPoster131 citations
244. Generating Multiple Objects at Spatially Distinct LocationsPoster129 citations
245. GamePad: A Learning Environment for Theorem ProvingPoster127 citations
246. Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech RecognitionPoster124 citations
247. Hierarchical Visuomotor Control of HumanoidsPoster124 citations
248. Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resiliencePoster121 citations
249. Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable RendererPoster120 citations
250. Learning To Solve Circuit-SAT: An Unsupervised Differentiable ApproachPoster120 citations
251. Variance Reduction for Reinforcement Learning in Input-Driven EnvironmentsPoster120 citations
252. Diffusion Scattering Transforms on GraphsPoster118 citations
253. Stochastic Prediction of Multi-Agent Interactions from Partial ObservationsPoster118 citations
254. A comprehensive, application-oriented study of catastrophic forgetting in DNNsPoster115 citations
255. ADef: an Iterative Algorithm to Construct Adversarial DeformationsPoster114 citations
256. DHER: Hindsight Experience Replay for Dynamic GoalsPoster114 citations
257. Composing Complex Skills by Learning Transition PoliciesPoster110 citations
258. Improving Sequence-to-Sequence Learning via Optimal TransportPoster110 citations
259. Learning Finite State Representations of Recurrent Policy NetworksPoster110 citations
260. Adaptive Posterior Learning: few-shot learning with a surprise-based memory modulePoster109 citations
261. An Empirical study of Binary Neural Networks' OptimisationPoster109 citations
262. Information asymmetry in KL-regularized RLPoster109 citations
263. Policy Transfer with Strategy OptimizationPoster108 citations
264. The Laplacian in RL: Learning Representations with Efficient ApproximationsPoster108 citations
265. Large Scale Graph Learning From Smooth SignalsPoster107 citations
266. MARGINALIZED AVERAGE ATTENTIONAL NETWORK FOR WEAKLY-SUPERVISED LEARNINGPoster107 citations
267. On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled DataPoster106 citations
268. Smoothing the Geometry of Probabilistic Box EmbeddingsOral106 citations
269. A Statistical Approach to Assessing Neural Network RobustnessPoster105 citations
270. Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticityPoster105 citations
271. Small nonlinearities in activation functions create bad local minima in neural networksPoster105 citations
272. The Unusual Effectiveness of Averaging in GAN TrainingPoster105 citations
273. Time-Agnostic Prediction: Predicting Predictable Video FramesPoster105 citations
274. A Unified Theory of Early Visual Representations from Retina to Cortex through Anatomically Constrained Deep CNNsOral104 citations
275. Information-Directed Exploration for Deep Reinforcement LearningPoster104 citations
276. On the loss landscape of a class of deep neural networks with no bad local valleysPoster104 citations
277. Learning to Design RNAPoster103 citations
278. Learning to Make Analogies by Contrasting Abstract Relational StructurePoster102 citations
279. Caveats for information bottleneck in deterministic scenariosPoster101 citations
280. Generating Multi-Agent Trajectories using Programmatic Weak SupervisionPoster101 citations
281. Kernel Change-point Detection with Auxiliary Deep Generative ModelsPoster100 citations
282. Toward Understanding the Impact of Staleness in Distributed Machine LearningPoster100 citations
283. Improving MMD-GAN Training with Repulsive Loss FunctionPoster99 citations
284. Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization BoundsPoster98 citations
285. Hindsight policy gradientsPoster98 citations
286. Neural Graph Evolution: Towards Efficient Automatic Robot DesignPoster97 citations
287. Contingency-Aware Exploration in Reinforcement LearningPoster96 citations
288. Learning to Learn with Conditional Class DependenciesPoster96 citations
289. Building Dynamic Knowledge Graphs from Text using Machine Reading ComprehensionPoster95 citations
290. Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed InformationPoster95 citations
291. KnockoffGAN: Generating Knockoffs for Feature Selection using Generative Adversarial NetworksOral95 citations
292. Relational Forward Models for Multi-Agent LearningPoster95 citations
293. Approximability of Discriminators Implies Diversity in GANsPoster93 citations
294. L2-Nonexpansive Neural NetworksPoster93 citations
295. StrokeNet: A Neural Painting EnvironmentPoster93 citations
296. Disjoint Mapping Network for Cross-modal Matching of Voices and FacesPoster92 citations
297. Aggregated Momentum: Stability Through Passive DampingPoster91 citations
298. Automatically Composing Representation Transformations as a Means for GeneralizationPoster91 citations
299. Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic FailuresPoster91 citations
300. A Generative Model For Electron PathsPoster90 citations
301. Adversarial Imitation via Variational Inverse Reinforcement LearningPoster90 citations
302. Adversarial Domain Adaptation for Stable Brain-Machine InterfacesPoster89 citations
303. Fluctuation-dissipation relations for stochastic gradient descentPoster89 citations
304. Generative Question Answering: Learning to Answer the Whole QuestionPoster89 citations
305. Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural NetworksPoster89 citations
306. Biologically-Plausible Learning Algorithms Can Scale to Large DatasetsPoster88 citations
307. Learning Implicitly Recurrent CNNs Through Parameter SharingPoster88 citations
308. Minimal Random Code Learning: Getting Bits Back from Compressed Model ParametersPoster88 citations
309. Tree-Structured Recurrent Switching Linear Dynamical Systems for Multi-Scale ModelingPoster88 citations
310. Function Space Particle Optimization for Bayesian Neural NetworksPoster87 citations
311. Multi-Domain Adversarial LearningPoster87 citations
312. Recall Traces: Backtracking Models for Efficient Reinforcement LearningPoster87 citations
313. SGD Converges to Global Minimum in Deep Learning via Star-convex PathPoster86 citations
314. Scalable Unbalanced Optimal Transport using Generative Adversarial NetworksPoster86 citations
315. Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous OutputsPoster86 citations
316. Integer Networks for Data Compression with Latent-Variable ModelsPoster85 citations
317. Knowledge Flow: Improve Upon Your TeachersPoster84 citations
318. Unsupervised Discovery of Parts, Structure, and DynamicsPoster84 citations
319. Unsupervised Hyper-alignment for Multilingual Word EmbeddingsPoster84 citations
320. Environment Probing Interaction PoliciesPoster83 citations
321. signSGD via Zeroth-Order OraclePoster83 citations
322. A Direct Approach to Robust Deep Learning Using Adversarial NetworksPoster82 citations
323. Stochastic Gradient/Mirror Descent: Minimax Optimality and Implicit RegularizationPoster82 citations
324. DeepOBS: A Deep Learning Optimizer Benchmark SuitePoster81 citations
325. STCN: Stochastic Temporal Convolutional NetworksPoster81 citations
326. ARM: Augment-REINFORCE-Merge Gradient for Stochastic Binary NetworksPoster80 citations
327. AdaShift: Decorrelation and Convergence of Adaptive Learning Rate MethodsPoster80 citations
328. Deep, Skinny Neural Networks are not Universal ApproximatorsPoster80 citations
329. Transferring Knowledge across Learning ProcessesOral80 citations
330. K for the Price of 1: Parameter-efficient Multi-task and Transfer LearningPoster79 citations
331. Coarse-grain Fine-grain Coattention Network for Multi-evidence Question AnsweringPoster78 citations
332. Complement Objective TrainingPoster76 citations
333. Guiding Policies with Language via Meta-LearningPoster75 citations
334. Learning Latent Superstructures in Variational Autoencoders for Deep Multidimensional ClusteringPoster75 citations
335. Learning concise representations for regression by evolving networks of treesPoster75 citations
336. Sample Efficient Imitation Learning for Continuous ControlPoster75 citations
337. LEARNING FACTORIZED REPRESENTATIONS FOR OPEN-SET DOMAIN ADAPTATIONPoster74 citations
338. Multilingual Neural Machine Translation With Soft Decoupled EncodingPoster74 citations
339. Competitive experience replayPoster72 citations
340. Preferences Implicit in the State of the WorldPoster72 citations
341. Learning Two-layer Neural Networks with Symmetric InputsPoster71 citations
342. Towards GAN Benchmarks Which Require GeneralizationPoster71 citations
343. Augmented Cyclic Adversarial Learning for Low Resource Domain AdaptationPoster70 citations
344. Learning Self-Imitating Diverse PoliciesPoster70 citations
345. Learning to Navigate the WebPoster70 citations
346. Dynamic Sparse Graph for Efficient Deep LearningPoster69 citations
347. Multi-Agent Dual LearningPoster69 citations
348. Whitening and Coloring Batch Transform for GANsPoster69 citations
349. Differentiable Perturb-and-Parse: Semi-Supervised Parsing with a Structured Variational AutoencoderPoster68 citations
350. On the Sensitivity of Adversarial Robustness to Input Data DistributionsPoster68 citations
351. RNNs implicitly implement tensor-product representationsPoster68 citations
352. Active Learning with Partial FeedbackPoster67 citations
353. Unsupervised Domain Adaptation for Distance Metric LearningPoster66 citations
354. Variational Bayesian Phylogenetic InferencePoster66 citations
355. M^3RL: Mind-aware Multi-agent Management Reinforcement LearningPoster65 citations
356. Soft Q-Learning with Mutual-Information RegularizationPoster65 citations
357. Learning to Describe Scenes with ProgramsPoster64 citations
358. Maximal Divergence Sequential Autoencoder for Binary Software Vulnerability DetectionPoster64 citations
359. A rotation-equivariant convolutional neural network model of primary visual cortexPoster63 citations
360. Subgradient Descent Learns Orthogonal DictionariesPoster61 citations
361. Conditional Network EmbeddingsPoster60 citations
362. Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word VectorsPoster60 citations
363. Feature-Wise Bias AmplificationPoster60 citations
364. Harmonic Unpaired Image-to-image TranslationPoster60 citations
365. Max-MIG: an Information Theoretic Approach for Joint Learning from CrowdsPoster60 citations
366. Bayesian Policy Optimization for Model UncertaintyPoster59 citations
367. Combinatorial Attacks on Binarized Neural NetworksPoster59 citations
368. Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image RestorationPoster59 citations
369. Probabilistic Planning with Sequential Monte Carlo methodsPoster58 citations
370. Universal Stagewise Learning for Non-Convex Problems with Convergence on Averaged SolutionsPoster58 citations
371. A new dog learns old tricks: RL finds classic optimization algorithmsPoster57 citations
372. Per-Tensor Fixed-Point Quantization of the Back-Propagation AlgorithmPoster57 citations
373. Two-Timescale Networks for Nonlinear Value Function ApproximationPoster57 citations
374. Bayesian Prediction of Future Street Scenes using Synthetic LikelihoodsPoster56 citations
375. h-detach: Modifying the LSTM Gradient Towards Better OptimizationPoster56 citations
376. Deep Learning 3D Shapes Using Alt-az Anisotropic 2-Sphere ConvolutionPoster53 citations
377. Optimal Completion Distillation for Sequence LearningPoster53 citations
378. Towards Robust, Locally Linear Deep NetworksPoster53 citations
379. Adaptive Estimators Show Information Compression in Deep Neural NetworksPoster52 citations
380. Learnable Embedding Space for Efficient Neural Architecture CompressionPoster52 citations
381. Solving the Rubik's Cube with Approximate Policy IterationPoster52 citations
382. ANYTIME MINIBATCH: EXPLOITING STRAGGLERS IN ONLINE DISTRIBUTED OPTIMIZATIONPoster51 citations
383. AutoLoss: Learning Discrete Schedule for Alternate OptimizationPoster51 citations
384. Beyond Greedy Ranking: Slate Optimization via List-CVAEPoster51 citations
385. Efficient Training on Very Large Corpora via Gramian EstimationPoster51 citations
386. Synthetic Datasets for Neural Program SynthesisPoster51 citations
387. Meta-Learning For Stochastic Gradient MCMCPoster50 citations
388. ProbGAN: Towards Probabilistic GAN with Theoretical GuaranteesPoster50 citations
389. RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep NetworksPoster50 citations
390. Verification of Non-Linear Specifications for Neural NetworksPoster50 citations
391. Learning Grid Cells as Vector Representation of Self-Position Coupled with Matrix Representation of Self-MotionPoster49 citations
392. Neural Speed Reading with Structural-Jump-LSTMPoster49 citations
393. The Deep Weight PriorPoster49 citations
394. Unsupervised Speech Recognition via Segmental Empirical Output Distribution MatchingPoster48 citations
395. DOM-Q-NET: Grounded RL on Structured LanguagePoster47 citations
396. Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input MaskingPoster47 citations
397. Deep Frank-Wolfe For Neural Network OptimizationPoster46 citations
398. Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content TransferPoster46 citations
399. Neural TTS Stylization with Adversarial and Collaborative GamesPoster45 citations
400. Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data StreamsPoster45 citations
401. Spectral Inference Networks: Unifying Deep and Spectral LearningPoster45 citations
402. ACCELERATING NONCONVEX LEARNING VIA REPLICA EXCHANGE LANGEVIN DIFFUSIONPoster44 citations
403. Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness ControlPoster44 citations
404. Learning Embeddings into Entropic Wasserstein SpacesPoster44 citations
405. Learning a Meta-Solver for Syntax-Guided Program SynthesisPoster44 citations
406. Learning to Remember More with Less MemorizationOral44 citations
407. MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncodersPoster44 citations
408. Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep NetworksPoster43 citations
409. Posterior Attention Models for Sequence to Sequence LearningPoster43 citations
410. Modeling the Long Term Future in Model-Based Reinforcement LearningPoster42 citations
411. Revealing interpretable object representations from human behaviorPoster42 citations
412. Diversity and Depth in Per-Example Routing ModelsPoster41 citations
413. Generative predecessor models for sample-efficient imitation learningPoster41 citations
414. Hierarchical Reinforcement Learning via Advantage-Weighted Information MaximizationPoster41 citations
415. Mode NormalizationPoster41 citations
416. On Random Deep Weight-Tied Autoencoders: Exact Asymptotic Analysis, Phase Transitions, and Implications to TrainingOral41 citations
417. AD-VAT: An Asymmetric Dueling mechanism for learning Visual Active TrackingPoster40 citations
418. Unsupervised Adversarial Image ReconstructionPoster40 citations
419. Towards Metamerism via Foveated Style TransferPoster38 citations
420. Value Propagation NetworksPoster38 citations
421. Analysis of Quantized ModelsPoster37 citations
422. Label super-resolution networksPoster37 citations
423. Variance Networks: When Expectation Does Not Meet Your ExpectationsPoster37 citations
424. Wasserstein Barycenter Model EnsemblingPoster37 citations
425. G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant SpacePoster35 citations
426. Learning Recurrent Binary/Ternary WeightsPoster35 citations
427. Optimal Transport Maps For Distribution Preserving Operations on Latent Spaces of Generative ModelsPoster35 citations
428. A Data-Driven and Distributed Approach to Sparse Signal Representation and RecoveryPoster33 citations
429. Efficient Augmentation via Data SubsamplingPoster33 citations
430. Minimal Images in Deep Neural Networks: Fragile Object Recognition in Natural ImagesPoster33 citations
431. Overcoming the Disentanglement vs Reconstruction Trade-off via Jacobian SupervisionPoster33 citations
432. Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural NetworksPoster33 citations
433. Harmonizing Maximum Likelihood with GANs for Multimodal Conditional GenerationPoster32 citations
434. Learning Representations of Sets through Optimized PermutationsPoster32 citations
435. Auxiliary Variational MCMCPoster31 citations
436. On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural NetworksPoster31 citations
437. Supervised Policy Update for Deep Reinforcement LearningPoster31 citations
438. Human-level Protein Localization with Convolutional Neural NetworksPoster29 citations
439. Latent Convolutional ModelsPoster29 citations
440. Learning sparse relational transition modelsPoster29 citations
441. Variational Autoencoders with Jointly Optimized Latent Dependency StructurePoster29 citations
442. Discovery of Natural Language Concepts in Individual Units of CNNsPoster28 citations
443. Generalized Tensor Models for Recurrent Neural NetworksPoster28 citations
444. Post Selection Inference with Incomplete Maximum Mean Discrepancy EstimatorPoster28 citations
445. Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural NetworksPoster27 citations
446. Learning what you can do before doing anythingPoster27 citations
447. Bounce and Learn: Modeling Scene Dynamics with Real-World BouncesPoster26 citations
448. Cost-Sensitive Robustness against Adversarial ExamplesPoster26 citations
449. Don't let your Discriminator be fooledPoster26 citations
450. Kernel RNN Learning (KeRNL)Poster26 citations
451. On Computation and Generalization of Generative Adversarial Networks under Spectrum ControlPoster26 citations
452. Deep Layers as Stochastic SolversPoster25 citations
453. Detecting Egregious Responses in Neural Sequence-to-sequence ModelsPoster25 citations
454. Feed-forward Propagation in Probabilistic Neural Networks with Categorical and Max LayersPoster25 citations
455. GO Gradient for Expectation-Based ObjectivesPoster25 citations
456. Imposing Category Trees Onto Word-Embeddings Using A Geometric ConstructionPoster24 citations
457. NOODL: Provable Online Dictionary Learning and Sparse CodingPoster24 citations
458. Transfer Learning for Sequences via Learning to CollocatePoster24 citations
459. Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate PolicyPoster23 citations
460. Distribution-Interpolation Trade off in Generative ModelsPoster22 citations
461. A Max-Affine Spline Perspective of Recurrent Neural NetworksPoster21 citations
462. Feature Intertwiner for Object DetectionPoster21 citations
463. Large-Scale Answerer in Questioner's Mind for Visual Dialog Question GenerationPoster21 citations
464. Learning Procedural Abstractions and Evaluating Discrete Latent Temporal StructurePoster21 citations
465. textTOvec: DEEP CONTEXTUALIZED NEURAL AUTOREGRESSIVE TOPIC MODELS OF LANGUAGE WITH DISTRIBUTED COMPOSITIONAL PRIORPoster21 citations
466. From Hard to Soft: Understanding Deep Network Nonlinearities via Vector Quantization and Statistical InferencePoster20 citations
467. Hierarchical RL Using an Ensemble of Proprioceptive Periodic PoliciesPoster20 citations
468. Top-Down Neural Model For FormulaePoster20 citations
469. Visceral Machines: Risk-Aversion in Reinforcement Learning with Intrinsic Physiological RewardsPoster19 citations
470. A2BCD: Asynchronous Acceleration with Optimal ComplexityPoster18 citations
471. CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space ModelPoster18 citations
472. A Kernel Random Matrix-Based Approach for Sparse PCAPoster17 citations
473. Neural network gradient-based learning of black-box function interfacesPoster17 citations
474. Visual Reasoning by Progressive Module NetworksPoster17 citations
475. Convolutional Neural Networks on Non-uniform Geometrical Signals Using Euclidean Spectral TransformationPoster16 citations
476. Preconditioner on Matrix Lie Group for SGDPoster16 citations
477. Dimensionality Reduction for Representing the Knowledge of Probabilistic ModelsPoster15 citations
478. Generating Liquid Simulations with Deformation-aware Neural NetworksPoster15 citations
479. LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videosPoster15 citations
480. Double Viterbi: Weight Encoding for High Compression Ratio and Fast On-Chip Reconstruction for Deep Neural NetworkPoster14 citations
481. Learning Programmatically Structured Representations with Perceptor GradientsPoster13 citations
482. Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with ApplicationsPoster13 citations
483. Minimum Divergence vs. Maximum Margin: an Empirical Comparison on Seq2Seq ModelsPoster12 citations
484. Random mesh projectors for inverse problemsPoster12 citations
485. Understanding Composition of Word Embeddings via Tensor DecompositionPoster12 citations
486. Efficiently testing local optimality and escaping saddles for ReLU networksPoster11 citations
487. Sparse Dictionary Learning by Dynamical Neural NetworksPoster11 citations
488. DISTRIBUTIONAL CONCAVITY REGULARIZATION FOR GANSPoster9 citations
489. Initialized Equilibrium Propagation for Backprop-Free TrainingPoster9 citations
490. NADPEx: An on-policy temporally consistent exploration method for deep reinforcement learningPoster9 citations
491. The Comparative Power of ReLU Networks and Polynomial Kernels in the Presence of Sparse Latent StructurePoster8 citations
492. Unsupervised Learning of the Set of Local MaximaPoster6 citations
493. Information Theoretic lower bounds on negative log likelihoodPoster4 citations
494. ROBUST ESTIMATION VIA GENERATIVE ADVERSARIAL NETWORKSPoster3 citations
495. Variational Smoothing in Recurrent Neural Network Language ModelsPoster3 citations
496. Adversarial Attacks on Graph Neural Networks via Meta LearningPoster
497. Defensive Quantization: When Efficiency Meets RobustnessPoster
498. Equi-normalization of Neural NetworksPoster
499. Music Transformer: Generating Music with Long-Term StructurePoster
500. PeerNets: Exploiting Peer Wisdom Against Adversarial AttacksPoster
501. Sliced Wasserstein Auto-EncodersPoster
502. The role of over-parametrization in generalization of neural networksPoster

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