ICLR 2017 Accepted Papers

The full list of 245 papers accepted at ICLR 2017 (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. Semi-Supervised Classification with Graph Convolutional NetworksPoster45,220 citations
2. SGDR: Stochastic Gradient Descent with Warm RestartsPoster10,671 citations
3. Adversarial examples in the physical worldWorkshop7,407 citations
4. Categorical Reparameterization with Gumbel-SoftmaxPoster7,241 citations
5. Neural Architecture Search with Reinforcement LearningOral7,202 citations
6. beta-VAE: Learning Basic Visual Concepts with a Constrained Variational FrameworkPoster6,129 citations
7. Understanding deep learning requires rethinking generalizationOral5,522 citations
8. Density estimation using Real NVPPoster4,547 citations
9. A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural NetworksPoster4,314 citations
10. Unrolled Generative Adversarial NetworksPoster4,189 citations
11. Optimization as a Model for Few-Shot LearningOral4,112 citations
12. Adversarial Machine Learning at ScalePoster4,015 citations
13. On Large-Batch Training for Deep Learning: Generalization Gap and Sharp MinimaOral4,006 citations
14. Temporal Ensembling for Semi-Supervised LearningPoster3,503 citations
15. Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention TransferPoster3,439 citations
16. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts LayerPoster3,097 citations
17. The Concrete Distribution: A Continuous Relaxation of Discrete Random VariablesPoster3,092 citations
18. A STRUCTURED SELF-ATTENTIVE SENTENCE EMBEDDINGPoster2,949 citations
19. Pointer Sentinel Mixture ModelsPoster2,949 citations
20. Pruning Convolutional Neural Networks for Resource Efficient InferencePoster2,782 citations
21. Adversarial Feature LearningPoster2,673 citations
22. Bidirectional Attention Flow for Machine ComprehensionPoster2,454 citations
23. Deep Variational Information BottleneckPoster2,223 citations
24. Delving into Transferable Adversarial Examples and Black-box AttacksPoster2,183 citations
25. End-to-end Optimized Image CompressionOral2,179 citations
26. Designing Neural Network Architectures using Reinforcement LearningPoster1,983 citations
27. HyperNetworksPoster1,979 citations
28. Adversarially Learned InferencePoster1,907 citations
29. A Simple but Tough-to-Beat Baseline for Sentence EmbeddingsPoster1,817 citations
30. Energy-based Generative Adversarial NetworksPoster1,681 citations
31. Deep Biaffine Attention for Neural Dependency ParsingPoster1,520 citations
32. Reinforcement Learning with Unsupervised Auxiliary TasksOral1,505 citations
33. Adversarial Training Methods for Semi-Supervised Text ClassificationPoster1,425 citations
34. A Learned Representation For Artistic StylePoster1,408 citations
35. Trained Ternary QuantizationPoster1,391 citations
36. Incremental Network Quantization: Towards Lossless CNNs with Low-precision WeightsPoster1,390 citations
37. Lossy Image Compression with Compressive AutoencodersPoster1,381 citations
38. FractalNet: Ultra-Deep Neural Networks without ResidualsPoster1,321 citations
39. Semi-supervised Knowledge Transfer for Deep Learning from Private Training DataOral1,306 citations
40. Unsupervised Cross-Domain Image GenerationPoster1,288 citations
41. PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other ModificationsPoster1,259 citations
42. On Detecting Adversarial PerturbationsPoster1,242 citations
43. Deep Predictive Coding Networks for Video Prediction and Unsupervised LearningPoster1,230 citations
44. Snapshot Ensembles: Train 1, Get M for FreePoster1,227 citations
45. Sample Efficient Actor-Critic with Experience ReplayPoster1,079 citations
46. Learning to Navigate in Complex EnvironmentsPoster1,075 citations
47. Learning End-to-End Goal-Oriented DialogOral1,004 citations
48. Visualizing Deep Neural Network Decisions: Prediction Difference AnalysisPoster930 citations
49. Hadamard Product for Low-rank Bilinear PoolingPoster921 citations
50. Entropy-SGD: Biasing Gradient Descent Into Wide ValleysPoster899 citations
51. Variational Lossy AutoencoderPoster856 citations
52. Training deep neural-networks using a noise adaptation layerPoster847 citations
53. Learning through Dialogue Interactions by Asking QuestionsPoster813 citations
54. Autoencoding Variational Inference For Topic ModelsPoster770 citations
55. Central Moment Discrepancy (CMD) for Domain-Invariant Representation LearningPoster766 citations
56. SampleRNN: An Unconditional End-to-End Neural Audio Generation ModelPoster761 citations
57. An Actor-Critic Algorithm for Sequence PredictionPoster758 citations
58. DeepCoder: Learning to Write ProgramsPoster752 citations
59. Dynamic Coattention Networks For Question AnsweringPoster747 citations
60. Mode Regularized Generative Adversarial NetworksPoster744 citations
61. Decomposing Motion and Content for Natural Video Sequence PredictionPoster740 citations
62. Machine Comprehension Using Match-LSTM and Answer PointerPoster700 citations
63. Hierarchical Multiscale Recurrent Neural NetworksPoster690 citations
64. Structured Attention NetworksPoster674 citations
65. Quasi-Recurrent Neural NetworksPoster669 citations
66. Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction TasksPoster664 citations
67. Offline bilingual word vectors, orthogonal transformations and the inverted softmaxPoster642 citations
68. Steerable CNNsPoster618 citations
69. Modular Multitask Reinforcement Learning with Policy SketchesWorkshop601 citations
70. Neural Photo Editing with Introspective Adversarial NetworksPoster593 citations
71. Dataset Augmentation in Feature SpaceWorkshop583 citations
72. Multi-Agent Cooperation and the Emergence of (Natural) LanguageOral566 citations
73. Towards a Neural StatisticianPoster552 citations
74. Amortised MAP Inference for Image Super-resolutionOral538 citations
75. Revisiting Classifier Two-Sample TestsPoster537 citations
76. Recurrent Batch NormalizationPoster536 citations
77. A Compositional Object-Based Approach to Learning Physical DynamicsPoster530 citations
78. Soft Weight-Sharing for Neural Network CompressionPoster523 citations
79. Learning in Implicit Generative ModelsWorkshop518 citations
80. Gated Multimodal Units for Information FusionWorkshop486 citations
81. Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw DataPoster484 citations
82. Generative Multi-Adversarial NetworksPoster484 citations
83. Deep Information PropagationPoster460 citations
84. Identity Matters in Deep LearningPoster458 citations
85. Why Deep Neural Networks for Function Approximation?Poster458 citations
86. Towards an automatic Turing test: Learning to evaluate dialogue responsesWorkshop453 citations
87. Tying Word Vectors and Word Classifiers: A Loss Framework for Language ModelingPoster448 citations
88. Stochastic Neural Networks for Hierarchical Reinforcement LearningPoster445 citations
89. EPOpt: Learning Robust Neural Network Policies Using Model EnsemblesPoster439 citations
90. Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy CriticOral436 citations
91. Learning to Remember Rare EventsPoster434 citations
92. Transfer Learning for Sequence Tagging with Hierarchical Recurrent NetworksPoster432 citations
93. PixelVAE: A Latent Variable Model for Natural ImagesPoster420 citations
94. Neuro-Symbolic Program SynthesisPoster418 citations
95. Zoneout: Regularizing RNNs by Randomly Preserving Hidden ActivationsPoster397 citations
96. Exploring Sparsity in Recurrent Neural NetworksPoster395 citations
97. Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPUPoster385 citations
98. Learning Invariant Feature Spaces to Transfer Skills with Reinforcement LearningPoster369 citations
99. Improving Neural Language Models with a Continuous CachePoster357 citations
100. Learning to Act by Predicting the FutureOral353 citations
101. Efficient Softmax Approximation for GPUsWorkshop348 citations
102. A Compare-Aggregate Model for Matching Text SequencesPoster332 citations
103. Deep Multi-task Representation Learning: A Tensor Factorisation ApproachPoster330 citations
104. Discrete Variational AutoencodersPoster327 citations
105. Bit-Pragmatic Deep Neural Network ComputingWorkshop322 citations
106. Data Noising as Smoothing in Neural Network Language ModelsPoster321 citations
107. TopicRNN: A Recurrent Neural Network with Long-Range Semantic DependencyPoster310 citations
108. Faster CNNs with Direct Sparse Convolutions and Guided PruningPoster307 citations
109. Learning Curve Prediction with Bayesian Neural NetworksPoster301 citations
110. Surprise-Based Intrinsic Motivation for Deep Reinforcement LearningWorkshop301 citations
111. Do Deep Convolutional Nets Really Need to be Deep and Convolutional?Poster299 citations
112. Tracking the World State with Recurrent Entity NetworksPoster298 citations
113. LR-GAN: Layered Recursive Generative Adversarial Networks for Image GenerationPoster297 citations
114. On the Quantitative Analysis of Decoder-Based Generative ModelsPoster285 citations
115. Third Person Imitation LearningPoster285 citations
116. Training Agent for First-Person Shooter Game with Actor-Critic Curriculum LearningPoster283 citations
117. Topology and Geometry of Half-Rectified Network OptimizationPoster278 citations
118. Highway and Residual Networks learn Unrolled Iterative EstimationPoster277 citations
119. Multiplicative LSTM for sequence modellingWorkshop275 citations
120. A Differentiable Physics Engine for Deep Learning in RoboticsWorkshop274 citations
121. Loss-aware Binarization of Deep NetworksPoster272 citations
122. Learning Features of Music From ScratchPoster266 citations
123. DSD: Dense-Sparse-Dense Training for Deep Neural NetworksPoster265 citations
124. Towards the Limit of Network QuantizationPoster259 citations
125. Paleo: A Performance Model for Deep Neural NetworksPoster254 citations
126. Generative Models and Model Criticism via Optimized Maximum Mean DiscrepancyPoster252 citations
127. Capacity and Trainability in Recurrent Neural NetworksPoster249 citations
128. Deep Probabilistic ProgrammingPoster249 citations
129. Recurrent Environment SimulatorsPoster247 citations
130. Deep Learning with Sets and Point CloudsWorkshop224 citations
131. Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural NetworksPoster224 citations
132. Extrapolation and learning equationsWorkshop222 citations
133. RenderGAN: Generating Realistic Labeled DataWorkshop216 citations
134. Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial LearningWorkshop209 citations
135. Learning to Compose Words into Sentences with Reinforcement LearningPoster208 citations
136. Unsupervised Perceptual Rewards for Imitation LearningWorkshop197 citations
137. Hyperband: Bandit-Based Configuration Evaluation for Hyperparameter OptimizationPoster196 citations
138. Stick-Breaking Variational AutoencodersPoster194 citations
139. Combining policy gradient and Q-learningPoster190 citations
140. Improving Generative Adversarial Networks with Denoising Feature MatchingPoster185 citations
141. Variational Recurrent Adversarial Deep Domain AdaptationPoster185 citations
142. Efficient Vector Representation for Documents through CorruptionPoster179 citations
143. Song From PI: A Musically Plausible Network for Pop Music GenerationWorkshop179 citations
144. Dialogue Learning With Human-in-the-LoopPoster173 citations
145. Deep Learning with Dynamic Computation GraphsPoster172 citations
146. Exponential MachinesWorkshop169 citations
147. Recurrent Mixture Density Network for Spatiotemporal Visual AttentionPoster168 citations
148. Regularizing CNNs with Locally Constrained DecorrelationsPoster163 citations
149. Frustratingly Short Attention Spans in Neural Language ModelingPoster157 citations
150. Making Neural Programming Architectures Generalize via RecursionOral154 citations
151. Inductive Bias of Deep Convolutional Networks through Pooling GeometryPoster147 citations
152. Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement LearningPoster145 citations
153. Learning a Natural Language Interface with Neural ProgrammerPoster139 citations
154. Discovering objects and their relations from entangled scene representationsWorkshop133 citations
155. Automatic Rule Extraction from Long Short Term Memory NetworksPoster131 citations
156. Learning Graphical State TransitionsOral131 citations
157. Learning Continuous Semantic Representations of Symbolic ExpressionsWorkshop128 citations
158. Sparsely-Connected Neural Networks: Towards Efficient VLSI Implementation of Deep Neural NetworksPoster128 citations
159. Distributed Second-Order Optimization using Kronecker-Factored ApproximationsPoster124 citations
160. Programming With a Differentiable Forth InterpreterWorkshop121 citations
161. Calibrating Energy-based Generative Adversarial NetworksPoster118 citations
162. Tree-structured decoding with doubly-recurrent neural networksPoster115 citations
163. Query-Reduction Networks for Question AnsweringPoster114 citations
164. Normalizing the Normalizers: Comparing and Extending Network Normalization SchemesPoster113 citations
165. HolStep: A Machine Learning Dataset for Higher-order Logic Theorem ProvingPoster108 citations
166. Multi-view Recurrent Neural Acoustic Word EmbeddingsPoster104 citations
167. Words or Characters? Fine-grained Gating for Reading ComprehensionPoster100 citations
168. Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality TighteningPoster98 citations
169. Learning Visual Servoing with Deep Features and Fitted Q-IterationPoster94 citations
170. Generalizing Skills with Semi-Supervised Reinforcement LearningPoster93 citations
171. Multilayer Recurrent Network Models of Primate Retinal Ganglion Cell ResponsesPoster93 citations
172. Learning to Perform Physics Experiments via Deep Reinforcement LearningPoster91 citations
173. Tuning Recurrent Neural Networks with Reinforcement LearningWorkshop90 citations
174. Diet Networks: Thin Parameters for Fat GenomicsPoster89 citations
175. Variable Computation in Recurrent Neural NetworksPoster86 citations
176. The Neural Noisy ChannelPoster80 citations
177. A recurrent neural network without chaosPoster77 citations
178. Metacontrol for Adaptive Imagination-Based OptimizationPoster76 citations
179. Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domainPoster75 citations
180. Generating Interpretable Images with Controllable StructureWorkshop73 citations
181. Predicting Medications from Diagnostic Codes with Recurrent Neural NetworksPoster72 citations
182. Learning to OptimizePoster69 citations
183. Latent Sequence DecompositionsPoster68 citations
184. Mollifying NetworksPoster65 citations
185. Dropout with Expectation-linear RegularizationPoster61 citations
186. Incorporating long-range consistency in CNN-based texture generationPoster59 citations
187. Learning Recurrent Representations for Hierarchical Behavior ModelingPoster59 citations
188. Sigma Delta Quantized NetworksPoster56 citations
189. Efficient Representation of Low-Dimensional Manifolds using Deep NetworksPoster52 citations
190. Emergence of foveal image sampling from learning to attend in visual scenesPoster52 citations
191. Improving Policy Gradient by Exploring Under-appreciated RewardsPoster46 citations
192. Learning to Generate Samples from Noise through Infusion TrainingPoster46 citations
193. Learning to superoptimize programsPoster44 citations
194. Semi-supervised deep learning by metric embeddingWorkshop44 citations
195. Neural Taylor Approximations: Convergence and Exploration in Rectifier NetworksWorkshop41 citations
196. FILTER SHAPING FOR CONVOLUTIONAL NEURAL NETWORKSPoster40 citations
197. Learning to Discover Sparse Graphical ModelsWorkshop40 citations
198. A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial SamplesWorkshop39 citations
199. Batch Policy Gradient Methods for Improving Neural Conversation ModelsPoster39 citations
200. Recurrent Hidden Semi-Markov ModelPoster39 citations
201. Online Structure Learning for Sum-Product Networks with Gaussian LeavesWorkshop37 citations
202. Symmetry-Breaking Convergence Analysis of Certain Two-layered Neural Networks with ReLU nonlinearityWorkshop34 citations
203. What does it take to generate natural textures?Poster34 citations
204. Geometry of PolysemyPoster33 citations
205. Neural Program LatticesPoster33 citations
206. Maximum Entropy Flow NetworksPoster32 citations
207. Introspection:Accelerating Neural Network Training By Learning Weight EvolutionPoster31 citations
208. Learning to Query, Reason, and Answer Questions On Ambiguous TextsPoster31 citations
209. Nonparametric Neural NetworksPoster29 citations
210. Automated Generation of Multilingual Clusters for the Evaluation of Distributed RepresentationsWorkshop28 citations
211. Reasoning with Memory Augmented Neural Networks for Language ComprehensionPoster28 citations
212. Online Bayesian Transfer Learning for Sequential Data ModelingPoster25 citations
213. Lie-Access Neural Turing MachinesPoster23 citations
214. Episodic Exploration for Deep Deterministic Policies for StarCraft MicromanagementPoster21 citations
215. Modularized Morphing of Neural NetworksWorkshop21 citations
216. Trusting SVM for Piecewise Linear CNNsPoster21 citations
217. Towards Deep Interpretability (MUS-ROVER II): Learning Hierarchical Representations of Tonal MusicPoster20 citations
218. Shift Aggregate Extract NetworksWorkshop19 citations
219. Generalizable Features From Unsupervised LearningWorkshop17 citations
220. Nonparametrically Learning Activation Functions in Deep Neural NetsWorkshop15 citations
221. DeepDSL: A Compilation-based Domain-Specific Language for Deep LearningPoster14 citations
222. Program Synthesis for Character Level Language ModelingPoster14 citations
223. Neural Functional ProgrammingWorkshop13 citations
224. Recursive Regression with Neural Networks: Approximating the HJI PDE SolutionWorkshop13 citations
225. Transfer of View-manifold Learning to Similarity Perception of Novel ObjectsPoster11 citations
226. Training Compressed Fully-Connected Networks with a Density-Diversity PenaltyPoster10 citations
227. Neural Data Filter for Bootstrapping Stochastic Gradient DescentWorkshop9 citations
228. Pruning Filters for Efficient ConvNetsPoster9 citations
229. Short and Deep: Sketching and Neural NetworksWorkshop9 citations
230. Tighter bounds lead to improved classifiersPoster9 citations
231. Learning Invariant Representations Of Planar CurvesPoster8 citations
232. Compositional Kernel MachinesWorkshop7 citations
233. An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population InfomaxPoster5 citations
234. Fast Chirplet Transform to Enhance CNN Machine Listening - Validation on Animal calls and SpeechWorkshop5 citations
235. Lifelong Perceptual Programming By ExampleWorkshop5 citations
236. Development of JavaScript-based deep learning platform and application to distributed trainingWorkshop3 citations
237. Recurrent Normalization PropagationWorkshop2 citations
238. Support Regularized Sparse Coding and Its Fast EncoderPoster2 citations
239. Adaptive Feature Abstraction for Translating Video to LanguageWorkshop1 citations
240. Optimal Binary Autoencoding with Pairwise CorrelationsPoster1 citations
241. Understanding Trainable Sparse Coding with Matrix FactorizationPoster1 citations
242. Charged Point Normalization: An Efficient Solution to the Saddle Point ProblemWorkshop
243. On Robust Concepts and Small Neural NetsWorkshop
244. Perception Updating Networks: On architectural constraints for interpretable video generative modelsWorkshop
245. Towards Principled Methods for Training Generative Adversarial NetworksOral

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