ICLR 2018 Accepted Papers

The full list of 429 papers accepted at ICLR 2018 (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. Towards Deep Learning Models Resistant to Adversarial AttacksPoster15,225 citations
2. Graph Attention NetworksPoster14,887 citations
3. mixup: Beyond Empirical Risk MinimizationPoster12,891 citations
4. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic ActorWorkshop11,310 citations
5. Progressive Growing of GANs for Improved Quality, Stability, and VariationOral9,833 citations
6. Spectral Normalization for Generative Adversarial NetworksOral5,867 citations
7. Searching for Activation FunctionsWorkshop4,870 citations
8. Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic ForecastingPoster4,697 citations
9. Unsupervised Representation Learning by Predicting Image RotationsPoster4,239 citations
10. Ensemble Adversarial Training: Attacks and DefensesPoster3,557 citations
11. On the Convergence of Adam and BeyondOral3,446 citations
12. Learning to TeachPoster2,782 citations
13. Enhancing The Reliability of Out-of-distribution Image Detection in Neural NetworksPoster2,556 citations
14. Visualizing the Loss Landscape of Neural NetsWorkshop2,486 citations
15. Active Learning for Convolutional Neural Networks: A Core-Set ApproachPoster2,435 citations
16. Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly DetectionPoster2,410 citations
17. Variational image compression with a scale hyperpriorPoster2,215 citations
18. Mixed Precision TrainingPoster2,212 citations
19. A Deep Reinforced Model for Abstractive SummarizationPoster2,047 citations
20. FastGCN: Fast Learning with Graph Convolutional Networks via Importance SamplingPoster1,976 citations
21. Demystifying MMD GANsPoster1,874 citations
22. Countering Adversarial Images using Input TransformationsPoster1,821 citations
23. Meta-Learning for Semi-Supervised Few-Shot ClassificationPoster1,791 citations
24. Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed TrainingPoster1,771 citations
25. Learning Representations and Generative Models for 3D Point CloudsWorkshop1,765 citations
26. Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning ModelsPoster1,732 citations
27. A Simple Neural Attentive Meta-LearnerPoster1,683 citations
28. Learning Differentially Private Recurrent Language ModelsPoster1,654 citations
29. To Prune, or Not to Prune: Exploring the Efficacy of Pruning for Model CompressionWorkshop1,609 citations
30. Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative ModelsPoster1,543 citations
31. Data Augmentation Generative Adversarial NetworksWorkshop1,531 citations
32. Lifelong Learning with Dynamically Expandable NetworksPoster1,448 citations
33. Deep Neural Networks as Gaussian ProcessesPoster1,424 citations
34. Wasserstein Auto-EncodersOral1,423 citations
35. Learning Sparse Neural Networks through L_0 RegularizationPoster1,418 citations
36. Regularizing and Optimizing LSTM Language ModelsPoster1,415 citations
37. Mitigating Adversarial Effects Through RandomizationPoster1,391 citations
38. Word translation without parallel dataPoster1,382 citations
39. Don't Decay the Learning Rate, Increase the Batch SizePoster1,362 citations
40. Matrix capsules with EM routingPoster1,356 citations
41. Towards better understanding of gradient-based attribution methods for Deep Neural NetworksPoster1,347 citations
42. Unsupervised Machine Translation Using Monolingual Corpora OnlyPoster1,332 citations
43. QANet: Combining Local Convolution with Global Self-Attention for Reading ComprehensionPoster1,263 citations
44. Noisy Networks For ExplorationPoster1,259 citations
45. Certifying Some Distributional Robustness with Principled Adversarial TrainingOral1,237 citations
46. Hierarchical Representations for Efficient Architecture SearchPoster1,205 citations
47. Spherical CNNsOral1,203 citations
48. Learning Robust Rewards with Adverserial Inverse Reinforcement LearningPoster1,194 citations
49. Certified Defenses against Adversarial ExamplesPoster1,176 citations
50. Deep Complex NetworksPoster1,142 citations
51. Few-Shot Learning with Graph Neural NetworksPoster1,141 citations
52. A Neural Representation of Sketch DrawingsPoster1,127 citations
53. Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution SamplesPoster1,102 citations
54. The Implicit Bias of Gradient Descent on Separable DataPoster1,096 citations
55. Generating Wikipedia by Summarizing Long SequencesPoster1,080 citations
56. Unsupervised Neural Machine TranslationPoster1,070 citations
57. Learning to Represent Programs with GraphsOral1,066 citations
58. PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial ExamplesPoster1,019 citations
59. PDE-Net: Learning PDEs from DataWorkshop980 citations
60. Model compression via distillation and quantizationPoster960 citations
61. Multi-Scale Dense Networks for Resource Efficient Image ClassificationOral941 citations
62. Non-Autoregressive Neural Machine TranslationPoster933 citations
63. SMASH: One-Shot Model Architecture Search through HyperNetworksPoster925 citations
64. Variational Continual LearningPoster904 citations
65. Characterizing Adversarial Subspaces Using Local Intrinsic DimensionalityOral903 citations
66. Synthetic and Natural Noise Both Break Neural Machine TranslationOral893 citations
67. Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via RankingPoster885 citations
68. Understanding Deep Neural Networks with Rectified Linear UnitsPoster864 citations
69. Parameter Space Noise for ExplorationPoster811 citations
70. Scalable Private Learning with PATEPoster809 citations
71. Learning Deep Generative Models of GraphsWorkshop793 citations
72. Thermometer Encoding: One Hot Way To Resist Adversarial ExamplesPoster771 citations
73. A DIRT-T Approach to Unsupervised Domain AdaptationPoster758 citations
74. Generating Natural Adversarial ExamplesPoster747 citations
75. A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural NetworksPoster736 citations
76. An efficient framework for learning sentence representationsPoster732 citations
77. Stochastic Activation Pruning for Robust Adversarial DefensePoster729 citations
78. Distributed Distributional Deterministic Policy GradientsPoster726 citations
79. On the Information Bottleneck Theory of Deep LearningPoster723 citations
80. Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement LearningPoster701 citations
81. cGANs with Projection DiscriminatorPoster694 citations
82. Self-ensembling for visual domain adaptationPoster690 citations
83. Recasting Gradient-Based Meta-Learning as Hierarchical BayesPoster686 citations
84. Compositional Attention Networks for Machine ReasoningPoster684 citations
85. On the State of the Art of Evaluation in Neural Language ModelsPoster678 citations
86. Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential EquationsWorkshop674 citations
87. Stochastic Variational Video PredictionPoster671 citations
88. MaskGAN: Better Text Generation via Filling in the _______Poster661 citations
89. Spatially Transformed Adversarial ExamplesPoster648 citations
90. Generalizing Across Domains via Cross-Gradient TrainingPoster645 citations
91. Training GANs with OptimismPoster624 citations
92. FearNet: Brain-Inspired Model for Incremental LearningPoster613 citations
93. Variational Inference of Disentangled Latent Concepts from Unlabeled ObservationsPoster607 citations
94. Deep Active Learning for Named Entity RecognitionPoster596 citations
95. Learn to Pay AttentionPoster596 citations
96. Model-Ensemble Trust-Region Policy OptimizationPoster592 citations
97. Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence LearningPoster586 citations
98. Evaluating the Robustness of Neural Networks: An Extreme Value Theory ApproachPoster585 citations
99. Maximum a Posteriori Policy OptimisationPoster580 citations
100. Sensitivity and Generalization in Neural Networks: an Empirical StudyPoster545 citations
101. A Framework for the Quantitative Evaluation of Disentangled RepresentationsPoster537 citations
102. GANITE: Estimation of Individualized Treatment Effects using Generative Adversarial NetsPoster536 citations
103. Large scale distributed neural network training through online distillationPoster535 citations
104. Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution LayersPoster530 citations
105. A Scalable Laplace Approximation for Neural NetworksPoster528 citations
106. Training and Inference with Integers in Deep Neural NetworksOral527 citations
107. Emergent Complexity via Multi-Agent CompetitionPoster524 citations
108. Towards Reverse-Engineering Black-Box Neural NetworksPoster490 citations
109. Gaussian Process Behaviour in Wide Deep Neural NetworksPoster483 citations
110. Measuring the Intrinsic Dimension of Objective LandscapesPoster482 citations
111. Intrinsic Motivation and Automatic Curricula via Asymmetric Self-PlayPoster464 citations
112. META LEARNING SHARED HIERARCHIESPoster456 citations
113. Breaking the Softmax Bottleneck: A High-Rank RNN Language ModelOral452 citations
114. Continuous Adaptation via Meta-Learning in Nonstationary and Competitive EnvironmentsOral451 citations
115. Semi-parametric topological memory for navigationPoster450 citations
116. A Bayesian Perspective on Generalization and Stochastic Gradient DescentPoster448 citations
117. Accelerating Neural Architecture Search using Performance PredictionWorkshop446 citations
118. Syntax-Directed Variational Autoencoder for Structured DataPoster446 citations
119. Adversarial SpheresWorkshop436 citations
120. Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson SamplingPoster435 citations
121. Empirical Analysis of the Hessian of Over-Parametrized Neural NetworksWorkshop435 citations
122. Learning how to explain neural networks: PatternNet and PatternAttributionPoster433 citations
123. i-RevNet: Deep Invertible NetworksPoster426 citations
124. Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-BatchesPoster418 citations
125. Depthwise Separable Convolutions for Neural Machine TranslationPoster416 citations
126. Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task LearningPoster414 citations
127. Deep Learning for Physical Processes: Incorporating Prior Scientific KnowledgePoster412 citations
128. Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network AccuracyPoster410 citations
129. All-but-the-Top: Simple and Effective Postprocessing for Word RepresentationsPoster391 citations
130. Adversarially Regularized AutoencodersWorkshop390 citations
131. Improving GANs Using Optimal TransportPoster388 citations
132. On the importance of single directions for generalizationPoster388 citations
133. SpectralNet: Spectral Clustering using Deep Neural NetworksPoster387 citations
134. WRPN: Wide Reduced-Precision NetworksPoster382 citations
135. Stochastic gradient descent performs variational inference, converges to limit cycles for deep networksPoster375 citations
136. Learning an Embedding Space for Transferable Robot SkillsPoster365 citations
137. FigureQA: An Annotated Figure Dataset for Visual ReasoningWorkshop360 citations
138. COLD FUSION: TRAINING SEQ2SEQ MODELS TOGETHER WITH LANGUAGE MODELSWorkshop358 citations
139. Backpropagation through the Void: Optimizing control variates for black-box gradient estimationPoster353 citations
140. Deep Rewiring: Training very sparse deep networksPoster352 citations
141. Inference Suboptimality in Variational AutoencodersWorkshop349 citations
142. Skip Connections Eliminate SingularitiesPoster349 citations
143. Adversarial Dropout RegularizationPoster347 citations
144. Natural Language Inference over Interaction SpacePoster347 citations
145. Tree-to-tree Neural Networks for Program TranslationWorkshop342 citations
146. Zero-Shot Visual ImitationOral339 citations
147. Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual EffectPoster332 citations
148. Learning from Between-class Examples for Deep Sound RecognitionPoster326 citations
149. NerveNet: Learning Structured Policy with Graph Neural NetworksPoster326 citations
150. Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their InteractionsPoster326 citations
151. Temporal Difference Models: Model-Free Deep RL for Model-Based ControlPoster325 citations
152. Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning AlgorithmPoster324 citations
153. Simple and efficient architecture search for Convolutional Neural NetworksWorkshop323 citations
154. Neural Map: Structured Memory for Deep Reinforcement LearningPoster320 citations
155. Monotonic Chunkwise AttentionPoster319 citations
156. Learning One-hidden-layer Neural Networks with Landscape DesignPoster318 citations
157. CausalGAN: Learning Causal Implicit Generative Models with Adversarial TrainingPoster314 citations
158. On the regularization of Wasserstein GANsPoster309 citations
159. Latent Space Oddity: on the Curvature of Deep Generative ModelsPoster308 citations
160. Learning Latent Permutations with Gumbel-Sinkhorn NetworksPoster307 citations
161. SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable DataPoster305 citations
162. Routing Networks: Adaptive Selection of Non-Linear Functions for Multi-Task LearningPoster302 citations
163. Online Learning Rate Adaptation with Hypergradient DescentPoster301 citations
164. Skip RNN: Learning to Skip State Updates in Recurrent Neural NetworksPoster292 citations
165. Large Scale Optimal Transport and Mapping EstimationPoster291 citations
166. Communication Algorithms via Deep LearningPoster289 citations
167. MGAN: Training Generative Adversarial Nets with Multiple GeneratorsPoster287 citations
168. Wavelet Pooling for Convolutional Neural NetworksPoster285 citations
169. Building Generalizable Agents with a Realistic and Rich 3D EnvironmentWorkshop279 citations
170. Learning to cluster in order to transfer across domains and tasksPoster278 citations
171. Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel InputOral276 citations
172. AmbientGAN: Generative models from lossy measurementsOral273 citations
173. Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMsOral272 citations
174. Reinforcement Learning from Imperfect DemonstrationsWorkshop271 citations
175. Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every StepPoster265 citations
176. Auto-Conditioned Recurrent Networks for Extended Complex Human Motion SynthesisPoster264 citations
177. Learning to Count Objects in Natural Images for Visual Question AnsweringPoster260 citations
178. Emergence of grid-like representations by training recurrent neural networks to perform spatial localizationPoster257 citations
179. Leveraging Grammar and Reinforcement Learning for Neural Program SynthesisPoster257 citations
180. PixelNN: Example-based Image SynthesisPoster255 citations
181. Detecting Statistical Interactions from Neural Network WeightsPoster243 citations
182. The power of deeper networks for expressing natural functionsPoster242 citations
183. Reinforcement Learning on Web Interfaces using Workflow-Guided ExplorationPoster234 citations
184. N2N learning: Network to Network Compression via Policy Gradient Reinforcement LearningPoster232 citations
185. Mixed Precision Training of Convolutional Neural Networks using Integer OperationsPoster226 citations
186. Polar Transformer NetworksPoster225 citations
187. Emergent Communication through NegotiationPoster211 citations
188. A Hierarchical Model for Device PlacementPoster210 citations
189. Investigating Human Priors for Playing Video GamesWorkshop210 citations
190. FusionNet: Fusing via Fully-aware Attention with Application to Machine ComprehensionPoster209 citations
191. Neural Language Modeling by Jointly Learning Syntax and LexiconPoster208 citations
192. Evidence Aggregation for Answer Re-Ranking in Open-Domain Question AnsweringPoster207 citations
193. Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain AdaptationPoster204 citations
194. Learning From Noisy Singly-labeled DataPoster202 citations
195. Multi-level Residual Networks from Dynamical Systems ViewPoster202 citations
196. Auto-Encoding Sequential Monte CarloPoster201 citations
197. Towards Image Understanding from Deep Compression Without DecodingPoster200 citations
198. VoiceLoop: Voice Fitting and Synthesis via a Phonological LoopPoster200 citations
199. Eigenoption Discovery through the Deep Successor RepresentationPoster194 citations
200. Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement LearningPoster194 citations
201. Do GANs learn the distribution? Some Theory and EmpiricsPoster191 citations
202. Ask the Right Questions: Active Question Reformulation with Reinforcement LearningOral190 citations
203. Neural-Guided Deductive Search for Real-Time Program Synthesis from ExamplesPoster190 citations
204. Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence ModelingPoster189 citations
205. Can recurrent neural networks warp time?Poster189 citations
206. Variance Reduction for Policy Gradient with Action-Dependent Factorized BaselinesOral187 citations
207. Hyperparameter optimization: a spectral approachPoster184 citations
208. Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement LearningPoster183 citations
209. Residual Connections Encourage Iterative InferencePoster174 citations
210. Efficient Sparse-Winograd Convolutional Neural NetworksPoster172 citations
211. Latent Constraints: Learning to Generate Conditionally from Unconditional Generative ModelsPoster171 citations
212. Loss-aware Weight Quantization of Deep NetworksPoster171 citations
213. Decision Boundary Analysis of Adversarial ExamplesPoster170 citations
214. Generative Models of Visually Grounded ImaginationPoster170 citations
215. Dynamic Neural Program Embeddings for Program RepairPoster169 citations
216. Compressing Word Embeddings via Deep Compositional Code LearningPoster166 citations
217. Learning Discrete Weights Using the Local Reparameterization TrickPoster164 citations
218. Neural Sketch Learning for Conditional Program GenerationOral164 citations
219. DuoRC: Towards Complex Language Understanding with Paraphrased Reading ComprehensionWorkshop161 citations
220. Learning Intrinsic Sparse Structures within Long Short-Term MemoryPoster161 citations
221. TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement LearningPoster161 citations
222. Sobolev GANPoster160 citations
223. Deep Learning with Logged Bandit FeedbackPoster158 citations
224. Covariant Compositional Networks For Learning GraphsWorkshop157 citations
225. Generalizing Hamiltonian Monte Carlo with Neural NetworksPoster157 citations
226. Can Neural Networks Understand Logical Entailment?Poster154 citations
227. On Unifying Deep Generative ModelsPoster152 citations
228. Understanding Short-Horizon Bias in Stochastic Meta-OptimizationPoster152 citations
229. SCAN: Learning Hierarchical Compositional Visual ConceptsPoster151 citations
230. Some Considerations on Learning to Explore via Meta-Reinforcement LearningWorkshop151 citations
231. On the insufficiency of existing momentum schemes for Stochastic OptimizationOral149 citations
232. When is a Convolutional Filter Easy to Learn?Poster149 citations
233. Variational Network QuantizationPoster148 citations
234. Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network DesignPoster147 citations
235. Smooth Loss Functions for Deep Top-k ClassificationPoster147 citations
236. Word Mover's Embedding: From Word2Vec to Document EmbeddingActive147 citations
237. Simulating Action Dynamics with Neural Process NetworksPoster143 citations
238. Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer OrderingPoster141 citations
239. Semantically Decomposing the Latent Spaces of Generative Adversarial NetworksPoster140 citations
240. Alternating Multi-bit Quantization for Recurrent Neural NetworksPoster138 citations
241. Expressive power of recurrent neural networksPoster138 citations
242. Trust-PCL: An Off-Policy Trust Region Method for Continuous ControlPoster137 citations
243. Divide-and-Conquer Reinforcement LearningPoster136 citations
244. Jointly Learning to Construct and Control Agents using Deep Reinforcement LearningWorkshop134 citations
245. DCN+: Mixed Objective And Deep Residual Coattention for Question AnsweringPoster133 citations
246. HexaConvPoster130 citations
247. Overcoming Catastrophic Interference using Conceptor-Aided BackpropagationPoster127 citations
248. Cascade Adversarial Machine Learning Regularized with a Unified EmbeddingPoster126 citations
249. WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic ModelingPoster126 citations
250. Attacking Binarized Neural NetworksPoster125 citations
251. Gradient Estimators for Implicit ModelsPoster123 citations
252. Global Optimality Conditions for Deep Neural NetworksPoster122 citations
253. Active Neural LocalizationPoster121 citations
254. Memory-based Parameter AdaptationPoster121 citations
255. Stabilizing Adversarial Nets with Prediction MethodsPoster121 citations
256. Fix your classifier: the marginal value of training the last weight layerPoster118 citations
257. Emergent Communication in a Multi-Modal, Multi-Step Referential GamePoster117 citations
258. The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningPoster116 citations
259. Parallelizing Linear Recurrent Neural Nets Over Sequence LengthPoster115 citations
260. Kronecker-factored Curvature Approximations for Recurrent Neural NetworksPoster114 citations
261. Activation Maximization Generative Adversarial NetsPoster112 citations
262. TRUNCATED HORIZON POLICY SEARCH: COMBINING REINFORCEMENT LEARNING & IMITATION LEARNINGPoster112 citations
263. Unbiased Online Recurrent OptimizationPoster112 citations
264. Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal ExplorationPoster112 citations
265. Exponentially vanishing sub-optimal local minima in multilayer neural networksWorkshop110 citations
266. Critical Points of Linear Neural Networks: Analytical Forms and Landscape PropertiesPoster109 citations
267. Towards Neural Phrase-based Machine TranslationPoster106 citations
268. Intriguing Properties of Adversarial ExamplesWorkshop102 citations
269. Exploring Deep Recurrent Models with Reinforcement Learning for Molecule DesignWorkshop101 citations
270. The High-Dimensional Geometry of Binary Neural NetworksPoster101 citations
271. Action-dependent Control Variates for Policy Optimization via Stein IdentityPoster100 citations
272. Few-shot Autoregressive Density Estimation: Towards Learning to Learn DistributionsPoster99 citations
273. Memory Augmented Control NetworksPoster98 citations
274. DNA-GAN: Learning Disentangled Representations from Multi-Attribute ImagesWorkshop95 citations
275. Variance-based Gradient Compression for Efficient Distributed Deep LearningWorkshop94 citations
276. Compositional Obverter Communication Learning from Raw Visual InputPoster93 citations
277. An Online Learning Approach to Generative Adversarial NetworksPoster92 citations
278. Graph Partition Neural Networks for Semi-Supervised ClassificationWorkshop91 citations
279. Multi-Task Learning for Document Ranking and Query SuggestionPoster91 citations
280. Training wide residual networks for deployment using a single bit for each weightPoster89 citations
281. Interactive Grounded Language Acquisition and Generalization in a 2D WorldPoster87 citations
282. Unsupervised Cipher Cracking Using Discrete GANsPoster86 citations
283. Time-Dependent Representation for Neural Event Sequence PredictionWorkshop85 citations
284. Coulomb GANs: Provably Optimal Nash Equilibria via Potential FieldsPoster84 citations
285. Fidelity-Weighted LearningPoster84 citations
286. Quantitatively Evaluating GANs With Divergences Proposed for TrainingPoster84 citations
287. Still not systematic after all these years: On the compositional skills of sequence-to-sequence recurrent networksWorkshop84 citations
288. A New Method of Region Embedding for Text ClassificationPoster83 citations
289. Convolutional Sequence Modeling RevisitedWorkshop80 citations
290. DORA The Explorer: Directed Outreaching Reinforcement Action-SelectionPoster79 citations
291. Interpretable Counting for Visual Question AnsweringPoster79 citations
292. Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion ControlPoster79 citations
293. Adaptive Quantization of Neural NetworksPoster77 citations
294. Emergent Translation in Multi-Agent CommunicationPoster77 citations
295. Learning Wasserstein EmbeddingsPoster73 citations
296. Minimax Curriculum Learning: Machine Teaching with Desirable Difficulties and Scheduled DiversityPoster73 citations
297. Hierarchical Density Order EmbeddingsPoster70 citations
298. Fraternal DropoutPoster69 citations
299. On the limitations of first order approximation in GAN dynamicsWorkshop69 citations
300. Learning Approximate Inference Networks for Structured PredictionPoster68 citations
301. Kernel Implicit Variational InferencePoster67 citations
302. Towards Synthesizing Complex Programs From Input-Output ExamplesPoster67 citations
303. Multiple Source Domain Adaptation with Adversarial LearningWorkshop66 citations
304. Robustness of Classifiers to Universal Perturbations: A Geometric PerspectivePoster66 citations
305. Debiasing Evidence Approximations: On Importance-weighted Autoencoders and Jackknife Variational InferencePoster65 citations
306. Regret Minimization for Partially Observable Deep Reinforcement LearningWorkshop65 citations
307. Consequentialist conditional cooperation in social dilemmas with imperfect informationPoster64 citations
308. Gradients explode - Deep Networks are shallow - ResNet explainedWorkshop64 citations
309. Twin Networks: Matching the Future for Sequence GenerationPoster64 citations
310. Challenges in Disentangling Independent Factors of VariationWorkshop63 citations
311. Learning Deep Mean Field Games for Modeling Large Population BehaviorOral63 citations
312. Memory Architectures in Recurrent Neural Network Language ModelsPoster63 citations
313. DLVM: A modern compiler infrastructure for deep learning systemsWorkshop62 citations
314. LEARNING TO SHARE: SIMULTANEOUS PARAMETER TYING AND SPARSIFICATION IN DEEP LEARNINGPoster58 citations
315. Learning Awareness ModelsPoster58 citations
316. Learning Parametric Closed-Loop Policies for Markov Potential GamesPoster58 citations
317. Weightless: Lossy Weight Encoding For Deep Neural Network CompressionWorkshop58 citations
318. Neural Speed Reading via Skim-RNNPoster57 citations
319. Confidence Scoring Using Whitebox Meta-models with Linear Classifier ProbesActive54 citations
320. The Kanerva Machine: A Generative Distributed MemoryPoster54 citations
321. A Compressed Sensing View of Unsupervised Text Embeddings, Bag-of-n-Grams, and LSTMsPoster53 citations
322. Combining Symbolic Expressions and Black-box Function Evaluations in Neural ProgramsPoster52 citations
323. Semantic Code Repair using Neuro-Symbolic Transformation NetworksWorkshop52 citations
324. Implicit Causal Models for Genome-wide Association StudiesPoster51 citations
325. Memorization Precedes Generation: Learning Unsupervised GANs with Memory NetworksPoster51 citations
326. Learning Deep Models: Critical Points and Local OpennessWorkshop50 citations
327. Kronecker Recurrent UnitsWorkshop49 citations
328. Variational Message Passing with Structured Inference NetworksPoster49 citations
329. Boosting the Actor with Dual CriticPoster48 citations
330. On the Expressive Power of Overlapping Architectures of Deep LearningPoster48 citations
331. Deep Sensing: Active Sensing using Multi-directional Recurrent Neural NetworksPoster46 citations
332. Proximal BackpropagationPoster46 citations
333. Generative networks as inverse problems with Scattering transformsPoster45 citations
334. Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity RegularizationPoster43 citations
335. Learning to Multi-Task by Active SamplingPoster43 citations
336. Policy Optimization by Genetic DistillationPoster43 citations
337. Reinforcement Learning Algorithm SelectionPoster43 citations
338. An image representation based convolutional network for DNA classificationPoster42 citations
339. Can Deep Reinforcement Learning solve Erdos-Selfridge-Spencer Games?Workshop42 citations
340. Multi-Mention Learning for Reading Comprehension with Neural CascadesPoster41 citations
341. Natural Language Inference with External KnowledgeWorkshop41 citations
342. Adaptive Dropout with Rademacher Complexity RegularizationPoster40 citations
343. Synthesizing realistic neural population activity patterns using Generative Adversarial NetworksPoster40 citations
344. Sparse Persistent RNNs: Squeezing Large Recurrent Networks On-ChipPoster39 citations
345. Value Propagation NetworksWorkshop38 citations
346. Analyzing and Exploiting NARX Recurrent Neural Networks for Long-Term DependenciesWorkshop36 citations
347. Learning Sparse Latent Representations with the Deep Copula Information BottleneckPoster35 citations
348. Parametrized Hierarchical Procedures for Neural ProgrammingPoster35 citations
349. The loss surface and expressivity of deep convolutional neural networksWorkshop35 citations
350. Distributional Adversarial NetworksWorkshop32 citations
351. Mastering the Dungeon: Grounded Language Learning by Mechanical Turker DescentPoster32 citations
352. Guide Actor-Critic for Continuous ControlPoster30 citations
353. Towards Provable Control for Unknown Linear Dynamical SystemsWorkshop29 citations
354. Not-So-Random FeaturesPoster28 citations
355. Semantic Interpolation in Implicit ModelsPoster28 citations
356. Deep Learning as a Mixed Convex-Combinatorial Optimization ProblemPoster27 citations
357. Learning a Generative Model for Validity in Complex Discrete StructuresPoster27 citations
358. Temporally Efficient Deep Learning with SpikesPoster27 citations
359. Deep learning mutation prediction enables early stage lung cancer detection in liquid biopsyWorkshop26 citations
360. Fast and Accurate Text Classification: Skimming, Rereading and Early StoppingWorkshop26 citations
361. Initialization matters: Orthogonal Predictive State Recurrent Neural NetworksPoster26 citations
362. Benefits of Depth for Long-Term Memory of Recurrent NetworksWorkshop25 citations
363. The Role of Minimal Complexity Functions in Unsupervised Learning of Semantic MappingsPoster25 citations
364. Divide and Conquer NetworksPoster24 citations
365. Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural NetworksPoster24 citations
366. Shifting Mean Activation Towards Zero with Bipolar Activation FunctionsWorkshop24 citations
367. Viterbi-based Pruning for Sparse Matrix with Fixed and High Index Compression RatioPoster24 citations
368. Boosting Dilated Convolutional Networks with Mixed Tensor DecompositionsOral23 citations
369. Empirical Risk Landscape Analysis for Understanding Deep Neural NetworksPoster23 citations
370. A Flexible Approach to Automated RNN Architecture GenerationWorkshop22 citations
371. Distributed Fine-tuning of Language Models on Private DataPoster22 citations
372. Fast Node Embeddings: Learning Ego-Centric RepresentationsWorkshop22 citations
373. Multi-View Data Generation Without View SupervisionPoster22 citations
374. TD or not TD: Analyzing the Role of Temporal Differencing in Deep Reinforcement LearningPoster22 citations
375. Ensemble Robustness and Generalization of Stochastic Deep Learning AlgorithmsWorkshop21 citations
376. Simulated+Unsupervised Learning With Adaptive Data Generation and Bidirectional MappingsPoster21 citations
377. Feature Incay for Representation RegularizationWorkshop20 citations
378. Predicting Floor-Level for 911 Calls with Neural Networks and Smartphone Sensor DataPoster18 citations
379. TRAINING GENERATIVE ADVERSARIAL NETWORKS VIA PRIMAL-DUAL SUBGRADIENT METHODS: A LAGRANGIAN PERSPECTIVE ON GANPoster18 citations
380. Faster Discovery of Neural Architectures by Searching for Paths in a Large ModelWorkshop17 citations
381. Improving GAN Training via Binarized Representation Entropy (BRE) RegularizationPoster17 citations
382. Espresso: Efficient Forward Propagation for Binary Deep Neural NetworksPoster16 citations
383. Deep Mean Field Theory: Layerwise Variance and Width Variation as Methods to Control Gradient ExplosionWorkshop15 citations
384. Imitation Learning from Visual Data with Multiple IntentionsPoster15 citations
385. AUTOMATED DESIGN USING NEURAL NETWORKS AND GRADIENT DESCENTWorkshop14 citations
386. Identifying Analogies Across DomainsPoster14 citations
387. Improving the Universality and Learnability of Neural Programmer-Interpreters with Combinator AbstractionPoster14 citations
388. Predict Responsibly: Increasing Fairness by Learning to DeferWorkshop14 citations
389. LSH-SAMPLING BREAKS THE COMPUTATIONAL CHICKEN-AND-EGG LOOP IN ADAPTIVE STOCHASTIC GRADIENT ESTIMATIONWorkshop13 citations
390. No Spurious Local Minima in a Two Hidden Unit ReLU NetworkWorkshop13 citations
391. Hierarchical Subtask Discovery with Non-Negative Matrix FactorizationPoster12 citations
392. Automatically Inferring Data Quality for Spatiotemporal ForecastingPoster9 citations
393. Neural Program Search: Solving Data Processing Tasks from Description and ExamplesWorkshop9 citations
394. Adversarial Policy Gradient for Alternating Markov GamesWorkshop8 citations
395. Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity TasksWorkshop8 citations
396. Capturing Human Category Representations by Sampling in Deep Feature SpacesWorkshop7 citations
397. Learning a neural response metric for retinal prosthesisPoster7 citations
398. Learning to InferWorkshop7 citations
399. THE EFFECTIVENESS OF A TWO-LAYER NEURAL NETWORK FOR RECOMMENDATIONSWorkshop7 citations
400. Autoregressive Generative Adversarial NetworksWorkshop6 citations
401. Extending the Framework of Equilibrium Propagation to General DynamicsWorkshop6 citations
402. GeoSeq2Seq: Information Geometric Sequence-to-Sequence NetworksWorkshop6 citations
403. Neuron as an AgentWorkshop6 citations
404. Not-So-CLEVR: Visual Relations Strain Feedforward Neural NetworksWorkshop6 citations
405. Residual Loss Prediction: Reinforcement Learning With No Incremental FeedbackPoster6 citations
406. Rotational Unit of MemoryWorkshop6 citations
407. Universal Agent for Disentangling Environments and TasksPoster6 citations
408. Cross-View Training for Semi-Supervised LearningWorkshop5 citations
409. Topic-Based Question GenerationWorkshop5 citations
410. Understanding image motion with group representationsPoster5 citations
411. Parametric Adversarial Divergences are Good Task Losses for Generative ModelingWorkshop4 citations
412. Stable Distribution Alignment Using the Dual of the Adversarial DistanceWorkshop4 citations
413. THINK VISUALLY: QUESTION ANSWERING THROUGH VIRTUAL IMAGERYActive4 citations
414. Decoupling the Layers in Residual NetworksPoster2 citations
415. DropMax: Adaptive Stochastic SoftmaxWorkshop2 citations
416. Cross-Corpus Training with TreeLSTM for the Extraction of Biomedical Relationships from TextWorkshop1 citations
417. Modular Continual Learning in a Unified Visual EnvironmentPoster1 citations
418. Adaptive Memory NetworksWorkshop
419. Boundary Seeking GANsPoster
420. Critical Percolation as a Framework to Analyze the Training of Deep NetworksPoster
421. Deep contextualized word representationsPoster
422. Distributed Prioritized Experience ReplayPoster
423. LEARNING TO ORGANIZE KNOWLEDGE WITH N-GRAM MACHINESWorkshop
424. Learning to Write by Learning the ObjectiveWorkshop
425. On the Discrimination-Generalization Tradeoff in GANsPoster
426. Regularization Neural Networks via Constrained Virtual Movement FieldWorkshop
427. SEARNN: Training RNNs with global-local lossesPoster
428. Towards Effective GANs for Data Distributions with Diverse ModesWorkshop
429. WSNet: Learning Compact and Efficient Networks with Weight SamplingWorkshop

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