ICML 2017 Accepted Papers

The full list of 433 papers accepted at ICML 2017 (International Conference on Machine Learning). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

1. Wasserstein Generative Adversarial NetworksPoster19,098 citations
2. Model-Agnostic Meta-Learning for Fast Adaptation of Deep NetworksPoster15,661 citations
3. Neural Message Passing for Quantum ChemistryPoster10,347 citations
4. Axiomatic Attribution for Deep NetworksPoster8,039 citations
5. On Calibration of Modern Neural NetworksPoster7,417 citations
6. Learning Important Features Through Propagating Activation DifferencesPoster5,417 citations
7. Convolutional Sequence to Sequence LearningPoster4,576 citations
8. Conditional Image Synthesis with Auxiliary Classifier GANsPoster4,533 citations
9. Understanding Black-box Predictions via Influence FunctionsPoster3,615 citations
10. Continual Learning Through Synaptic IntelligencePoster3,346 citations
11. Language Modeling with Gated Convolutional NetworksPoster3,245 citations
12. Curiosity-driven Exploration by Self-supervised PredictionPoster3,233 citations
13. Deep Transfer Learning with Joint Adaptation NetworksPoster3,217 citations
14. Learning to Discover Cross-Domain Relations with Generative Adversarial NetworksPoster2,810 citations
15. A Closer Look at Memorization in Deep NetworksPoster2,324 citations
16. Deep Bayesian Active Learning with Image DataPoster2,203 citations
17. Large-Scale Evolution of Image ClassifiersPoster2,148 citations
18. A Distributional Perspective on Reinforcement LearningPoster2,118 citations
19. Constrained Policy OptimizationPoster1,815 citations
20. Reinforcement Learning with Deep Energy-Based PoliciesPoster1,695 citations
21. Meta NetworksPoster1,399 citations
22. Estimating individual treatment effect: generalization bounds and algorithmsPoster1,331 citations
23. Grammar Variational AutoencoderPoster1,256 citations
24. OptNet: Differentiable Optimization as a Layer in Neural NetworksPoster1,228 citations
25. Towards K-means-friendly Spaces: Simultaneous Deep Learning and ClusteringPoster1,220 citations
26. Toward Controlled Generation of TextPoster1,212 citations
27. FeUdal Networks for Hierarchical Reinforcement LearningPoster1,192 citations
28. Robust Adversarial Reinforcement LearningPoster1,161 citations
29. Variational Dropout Sparsifies Deep Neural NetworksPoster1,146 citations
30. How to Escape Saddle Points EfficientlyPoster1,074 citations
31. On the Expressive Power of Deep Neural NetworksPoster1,057 citations
32. Compressed Sensing using Generative ModelsPoster1,019 citations
33. Parseval Networks: Improving Robustness to Adversarial ExamplesPoster958 citations
34. Soft-DTW: a Differentiable Loss Function for Time-SeriesPoster956 citations
35. Minimax Regret Bounds for Reinforcement LearningPoster939 citations
36. Sharp Minima Can Generalize For Deep NetsPoster893 citations
37. Deep Voice: Real-time Neural Text-to-SpeechPoster877 citations
38. Generalization and Equilibrium in Generative Adversarial Nets (GANs)Poster867 citations
39. Input Convex Neural NetworksPoster858 citations
40. Neural Audio Synthesis of Musical Notes with WaveNet AutoencodersPoster827 citations
41. Stabilising Experience Replay for Deep Multi-Agent Reinforcement LearningPoster819 citations
42. Count-Based Exploration with Neural Density ModelsPoster806 citations
43. Asymmetric Tri-training for Unsupervised Domain AdaptationPoster765 citations
44. SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive GradientPoster763 citations
45. Accelerating Eulerian Fluid Simulation With Convolutional NetworksPoster741 citations
46. Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial ObservabilityPoster706 citations
47. Real-Time Adaptive Image CompressionPoster692 citations
48. Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial NetworksPoster679 citations
49. Automated Curriculum Learning for Neural NetworksPoster671 citations
50. Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge GraphsPoster658 citations
51. DeepBach: a Steerable Model for Bach Chorales GenerationPoster651 citations
52. Modular Multitask Reinforcement Learning with Policy SketchesPoster602 citations
53. Learning Discrete Representations via Information Maximizing Self-Augmented TrainingPoster597 citations
54. Multiplicative Normalizing Flows for Variational Bayesian Neural NetworksPoster593 citations
55. Gradient Coding: Avoiding Stragglers in Distributed LearningPoster590 citations
56. Recurrent Highway NetworksPoster573 citations
57. Forward and Reverse Gradient-Based Hyperparameter OptimizationPoster569 citations
58. DARLA: Improving Zero-Shot Transfer in Reinforcement LearningPoster560 citations
59. On Kernelized Multi-armed BanditsPoster558 citations
60. Device Placement Optimization with Reinforcement LearningPoster556 citations
61. No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric AnalysisPoster554 citations
62. Max-value Entropy Search for Efficient Bayesian OptimizationPoster552 citations
63. Contextual Decision Processes with low Bellman rank are PAC-LearnablePoster528 citations
64. Video Pixel NetworksPoster528 citations
65. The Shattered Gradients Problem: If resnets are the answer, then what is the question?Poster527 citations
66. Analogical Inference for Multi-relational EmbeddingsPoster514 citations
67. Adaptive Neural Networks for Efficient InferencePoster490 citations
68. Adversarial Feature Matching for Text GenerationPoster487 citations
69. Dynamic Word EmbeddingsPoster486 citations
70. Improved Variational Autoencoders for Text Modeling using Dilated ConvolutionsPoster485 citations
71. RobustFill: Neural Program Learning under Noisy I/OPoster483 citations
72. Neural Optimizer Search with Reinforcement LearningPoster482 citations
73. Learning to Generate Long-term Future via Hierarchical PredictionPoster459 citations
74. Decoupled Neural Interfaces using Synthetic GradientsPoster457 citations
75. Neural Episodic ControlPoster448 citations
76. Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement LearningPoster432 citations
77. Distributed Mean Estimation with Limited CommunicationPoster424 citations
78. Deep IV: A Flexible Approach for Counterfactual PredictionPoster413 citations
79. Provably Optimal Algorithms for Generalized Linear Contextual BanditsPoster402 citations
80. Discovering Discrete Latent Topics with Neural Variational InferencePoster399 citations
81. Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in NetworksPoster389 citations
82. Interactive Learning from Policy-Dependent Human FeedbackPoster387 citations
83. AdaNet: Adaptive Structural Learning of Artificial Neural NetworksPoster379 citations
84. Variants of RMSProp and Adagrad with Logarithmic Regret BoundsPoster377 citations
85. Recovery Guarantees for One-hidden-layer Neural NetworksPoster374 citations
86. Asynchronous Stochastic Gradient Descent with Delay CompensationPoster359 citations
87. Stochastic Modified Equations and Adaptive Stochastic Gradient AlgorithmsPoster350 citations
88. Unsupervised Learning by Predicting NoisePoster350 citations
89. Learned Optimizers that Scale and GeneralizePoster349 citations
90. Efficient softmax approximation for GPUsPoster348 citations
91. Learning to Learn without Gradient Descent by Gradient DescentPoster345 citations
92. Globally Optimal Gradient Descent for a ConvNet with Gaussian InputsPoster340 citations
93. A Laplacian Framework for Option Discovery in Reinforcement LearningPoster334 citations
94. Zero-Shot Task Generalization with Multi-Task Deep Reinforcement LearningPoster333 citations
95. Online and Linear-Time Attention by Enforcing Monotonic AlignmentsPoster331 citations
96. The Loss Surface of Deep and Wide Neural NetworksPoster331 citations
97. The Predictron: End-To-End Learning and PlanningPoster327 citations
98. Learning Sleep Stages from Radio Signals: A Conditional Adversarial ArchitecturePoster325 citations
99. Sliced Wasserstein Kernel for Persistence DiagramsPoster323 citations
100. Resource-efficient Machine Learning in 2 KB RAM for the Internet of ThingsPoster317 citations
101. Guarantees for Greedy Maximization of Non-submodular Functions with ApplicationsPoster311 citations
102. Tensor-Train Recurrent Neural Networks for Video ClassificationPoster311 citations
103. A Unified View of Multi-Label Performance MeasuresPoster310 citations
104. Equivariance Through Parameter-SharingPoster305 citations
105. Image-to-Markup Generation with Coarse-to-Fine AttentionPoster301 citations
106. Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive PhysicsPoster300 citations
107. Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential PredictionPoster299 citations
108. Practical Gauss-Newton Optimisation for Deep LearningPoster295 citations
109. Why is Posterior Sampling Better than Optimism for Reinforcement Learning?Poster295 citations
110. Being Robust (in High Dimensions) Can Be PracticalPoster293 citations
111. Multi-fidelity Bayesian Optimisation with Continuous ApproximationsPoster285 citations
112. On orthogonality and learning recurrent networks with long term dependenciesPoster281 citations
113. Measuring Sample Quality with KernelsPoster268 citations
114. An Alternative Softmax Operator for Reinforcement LearningPoster267 citations
115. Scalable Bayesian Rule ListsPoster265 citations
116. Parallel Multiscale Autoregressive Density EstimationPoster261 citations
117. Cognitive Psychology for Deep Neural Networks: A Shape Bias Case StudyPoster260 citations
118. Dropout Inference in Bayesian Neural Networks with Alpha-divergencesPoster259 citations
119. Coordinated Multi-Agent Imitation LearningPoster258 citations
120. Optimal and Adaptive Off-policy Evaluation in Contextual BanditsPoster254 citations
121. Failures of Gradient-Based Deep LearningPoster249 citations
122. An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point AnalysisPoster247 citations
123. World of Bits: An Open-Domain Platform for Web-Based AgentsPoster244 citations
124. Fairness in Reinforcement LearningPoster241 citations
125. Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta DistributionPoster241 citations
126. Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical SpacePoster239 citations
127. Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNsPoster232 citations
128. Learning to Detect Sepsis with a Multitask Gaussian Process RNN ClassifierPoster228 citations
129. Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement LearningPoster227 citations
130. ProtoNN: Compressed and Accurate kNN for Resource-scarce DevicesPoster227 citations
131. ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep LearningPoster227 citations
132. Fake News Mitigation via Point Process Based InterventionPoster222 citations
133. Stochastic Variance Reduction Methods for Policy EvaluationPoster218 citations
134. Sub-sampled Cubic Regularization for Non-convex OptimizationPoster218 citations
135. Learning Algorithms for Active LearningPoster215 citations
136. Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-controlPoster213 citations
137. Depth-Width Tradeoffs in Approximating Natural Functions with Neural NetworksPoster210 citations
138. meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced OverfittingPoster203 citations
139. Learning the Structure of Generative Models without Labeled DataPoster202 citations
140. Combined Group and Exclusive Sparsity for Deep Neural NetworksPoster200 citations
141. Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical GuaranteesPoster199 citations
142. Efficient Distributed Learning with SparsityPoster196 citations
143. Learning Texture Manifolds with the Periodic Spatial GANPoster190 citations
144. Gradient Boosted Decision Trees for High Dimensional Sparse OutputPoster186 citations
145. Latent Intention Dialogue ModelsPoster185 citations
146. Dual Supervised LearningPoster184 citations
147. “Convex Until Proven Guilty”: Dimension-Free Acceleration of Gradient Descent on Non-Convex FunctionsPoster181 citations
148. Random Feature Expansions for Deep Gaussian ProcessesPoster180 citations
149. Geometry of Neural Network Loss Surfaces via Random Matrix TheoryPoster178 citations
150. Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over NetworksPoster178 citations
151. Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder ReflectionsPoster177 citations
152. McGan: Mean and Covariance Feature Matching GANPoster177 citations
153. Iterative Machine TeachingPoster175 citations
154. Multilevel Clustering via Wasserstein MeansPoster175 citations
155. Self-Paced Co-trainingPoster172 citations
156. On Context-Dependent Clustering of BanditsPoster168 citations
157. Deep Spectral Clustering LearningPoster164 citations
158. MEC: Memory-efficient Convolution for Deep Neural NetworkPoster162 citations
159. Attentive Recurrent ComparatorsPoster161 citations
160. Deriving Neural Architectures from Sequence and Graph KernelsPoster160 citations
161. Differentially Private Ordinary Least SquaresPoster155 citations
162. Global optimization of Lipschitz functionsPoster153 citations
163. Batched High-dimensional Bayesian Optimization via Structural Kernel LearningPoster151 citations
164. End-to-End Learning for Structured Prediction Energy NetworksPoster151 citations
165. Dissipativity Theory for Nesterov’s Accelerated MethodPoster150 citations
166. High Dimensional Bayesian Optimization with Elastic Gaussian ProcessPoster142 citations
167. Stochastic Generative HashingPoster142 citations
168. Preferential Bayesian OptimizationPoster141 citations
169. Deciding How to Decide: Dynamic Routing in Artificial Neural NetworksPoster138 citations
170. Semi-Supervised Classification Based on Classification from Positive and Unlabeled DataPoster138 citations
171. Learning Gradient Descent: Better Generalization and Longer HorizonsPoster134 citations
172. Learning Deep Latent Gaussian Models with Markov Chain Monte CarloPoster132 citations
173. Multichannel End-to-end Speech RecognitionPoster129 citations
174. Learning Continuous Semantic Representations of Symbolic ExpressionsPoster128 citations
175. Warped Convolutions: Efficient Invariance to Spatial TransformationsPoster128 citations
176. End-to-End Differentiable Adversarial Imitation LearningPoster125 citations
177. Nearly Optimal Robust Matrix CompletionPoster124 citations
178. Sequence to Better Sequence: Continuous Revision of Combinatorial StructuresPoster124 citations
179. Analytical Guarantees on Numerical Precision of Deep Neural NetworksPoster123 citations
180. Coherent Probabilistic Forecasts for Hierarchical Time SeriesPoster123 citations
181. Online Learning to Rank in Stochastic Click ModelsPoster123 citations
182. Unifying Task Specification in Reinforcement LearningPoster122 citations
183. Programming with a Differentiable Forth InterpreterPoster121 citations
184. Uncovering Causality from Multivariate Hawkes Integrated CumulantsPoster121 citations
185. Efficient Regret Minimization in Non-Convex GamesPoster118 citations
186. Recursive Partitioning for Personalization using Observational DataPoster118 citations
187. The Price of Differential Privacy for Online LearningPoster118 citations
188. Consistent On-Line Off-Policy EvaluationPoster116 citations
189. Learning Hierarchical Features from Deep Generative ModelsPoster115 citations
190. Robust Probabilistic Modeling with Bayesian Data ReweightingPoster115 citations
191. Active Learning for Cost-Sensitive ClassificationPoster114 citations
192. Uniform Convergence Rates for Kernel Density EstimationPoster114 citations
193. Neural Networks and Rational FunctionsPoster111 citations
194. Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model AveragingPoster109 citations
195. Algorithmic Stability and Hypothesis ComplexityPoster106 citations
196. Convergence Analysis of Proximal Gradient with Momentum for Nonconvex OptimizationPoster106 citations
197. Differentially Private Clustering in High-Dimensional Euclidean SpacesPoster106 citations
198. Unimodal Probability Distributions for Deep Ordinal ClassificationPoster103 citations
199. Natasha: Faster Non-Convex Stochastic Optimization via Strongly Non-Convex ParameterPoster102 citations
200. SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model ParallelizationPoster101 citations
201. Deletion-Robust Submodular Maximization: Data Summarization with “the Right to be Forgotten”Poster97 citations
202. Learning in POMDPs with Monte Carlo Tree SearchPoster96 citations
203. Convexified Convolutional Neural NetworksPoster94 citations
204. Identifying Best Interventions through Online Importance SamplingPoster94 citations
205. Understanding Synthetic Gradients and Decoupled Neural InterfacesPoster94 citations
206. Projection-free Distributed Online Learning in NetworksPoster91 citations
207. Adaptive Consensus ADMM for Distributed OptimizationPoster89 citations
208. Counterfactual Data-Fusion for Online Reinforcement LearnersPoster89 citations
209. Safety-Aware Algorithms for Adversarial Contextual BanditPoster85 citations
210. Cost-Optimal Learning of Causal GraphsPoster84 citations
211. Delta Networks for Optimized Recurrent Network ComputationPoster82 citations
212. Bayesian Optimization with Tree-structured DependenciesPoster81 citations
213. Learning Hawkes Processes from Short Doubly-Censored Event SequencesPoster81 citations
214. Joint Dimensionality Reduction and Metric Learning: A Geometric TakePoster80 citations
215. Optimal Densification for Fast and Accurate Minwise HashingPoster79 citations
216. Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement RankPoster79 citations
217. Latent LSTM Allocation: Joint Clustering and Non-Linear Dynamic Modeling of Sequence DataPoster78 citations
218. Prediction and Control with Temporal Segment ModelsPoster78 citations
219. Near-Optimal Design of Experiments via Regret MinimizationPoster77 citations
220. Robust Submodular Maximization: A Non-Uniform Partitioning ApproachPoster77 citations
221. Deep Value Networks Learn to Evaluate and Iteratively Refine Structured OutputsPoster76 citations
222. Differentiable Programs with Neural LibrariesPoster75 citations
223. On Relaxing Determinism in Arithmetic CircuitsPoster74 citations
224. Algebraic Variety Models for High-Rank Matrix CompletionPoster73 citations
225. Maximum Selection and Ranking under Noisy ComparisonsPoster73 citations
226. Meritocratic Fairness for Cross-Population SelectionPoster73 citations
227. Just Sort It! A Simple and Effective Approach to Active Preference LearningPoster72 citations
228. Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk PrognosisPoster72 citations
229. Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMCPoster71 citations
230. Kernelized Support Tensor MachinesPoster71 citations
231. The Statistical Recurrent UnitPoster70 citations
232. Dance Dance ConvolutionPoster68 citations
233. Efficient Nonmyopic Active SearchPoster68 citations
234. Algorithms for $\ell_p$ Low-Rank ApproximationPoster67 citations
235. Beyond Filters: Compact Feature Map for Portable Deep ModelPoster67 citations
236. Developing Bug-Free Machine Learning Systems With Formal MathematicsPoster67 citations
237. Graph-based Isometry Invariant Representation LearningPoster67 citations
238. Confident Multiple Choice LearningPoster66 citations
239. Re-revisiting Learning on Hypergraphs: Confidence Interval and Subgradient MethodPoster66 citations
240. Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence LabellingPoster65 citations
241. Priv’IT: Private and Sample Efficient Identity TestingPoster65 citations
242. Clustering High Dimensional Dynamic Data StreamsPoster64 citations
243. State-Frequency Memory Recurrent Neural NetworksPoster64 citations
244. Communication-efficient Algorithms for Distributed Stochastic Principal Component AnalysisPoster63 citations
245. Probabilistic Path Hamiltonian Monte CarloPoster63 citations
246. On Mixed Memberships and Symmetric Nonnegative Matrix FactorizationsPoster62 citations
247. Robust Budget Allocation via Continuous Submodular FunctionsPoster62 citations
248. Active Learning for Top-$K$ Rank Aggregation from Noisy ComparisonsPoster61 citations
249. Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for Markov Chain Monte CarloPoster61 citations
250. High-dimensional Non-Gaussian Single Index Models via Thresholded Score Function EstimationPoster61 citations
251. Lazifying Conditional Gradient AlgorithmsPoster61 citations
252. Distributed Batch Gaussian Process OptimizationPoster60 citations
253. Co-clustering through Optimal TransportPoster59 citations
254. An Adaptive Test of Independence with Analytic Kernel EmbeddingsPoster58 citations
255. Clustering by Sum of Norms: Stochastic Incremental Algorithm, Convergence and Cluster RecoveryPoster58 citations
256. Improving Viterbi is Hard: Better Runtimes Imply Faster Clique AlgorithmsPoster58 citations
257. Local-to-Global Bayesian Network Structure LearningPoster58 citations
258. Multi-objective Bandits: Optimizing the Generalized Gini IndexPoster58 citations
259. Doubly Accelerated Methods for Faster CCA and Generalized EigendecompositionPoster57 citations
260. Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical UsePoster57 citations
261. Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning PossiblePoster56 citations
262. Data-Efficient Policy Evaluation Through Behavior Policy SearchPoster55 citations
263. Differentially Private Submodular Maximization: Data Summarization in DisguisePoster55 citations
264. PixelCNN Models with Auxiliary Variables for Natural Image ModelingPoster54 citations
265. Selective Inference for Sparse High-Order Interaction ModelsPoster54 citations
266. Boosted Fitted Q-IterationPoster52 citations
267. Coupling Distributed and Symbolic Execution for Natural Language QueriesPoster52 citations
268. Emulating the Expert: Inverse Optimization through Online LearningPoster52 citations
269. Logarithmic Time One-Against-SomePoster52 citations
270. Nonnegative Matrix Factorization for Time Series Recovery From a Few Temporal AggregatesPoster52 citations
271. Pain-Free Random Differential Privacy with Sensitivity SamplingPoster52 citations
272. Stochastic Convex Optimization: Faster Local Growth Implies Faster Global ConvergencePoster52 citations
273. Consistent k-ClusteringPoster51 citations
274. Nyström Method with Kernel K-means++ Samples as LandmarksPoster51 citations
275. Sequence Modeling via SegmentationsPoster50 citations
276. Capacity Releasing Diffusion for Speed and LocalityPoster49 citations
277. Exploiting Strong Convexity from Data with Primal-Dual First-Order AlgorithmsPoster49 citations
278. Learning Deep Architectures via Generalized Whitened Neural NetworksPoster49 citations
279. Adaptive Sampling Probabilities for Non-Smooth OptimizationPoster48 citations
280. Deep Tensor Convolution on MulticoresPoster48 citations
281. Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWUPoster48 citations
282. Multi-task Learning with Labeled and Unlabeled TasksPoster48 citations
283. Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and ControlPoster48 citations
284. Second-Order Kernel Online Convex Optimization with Adaptive SketchingPoster48 citations
285. Magnetic Hamiltonian Monte CarloPoster47 citations
286. Automatic Discovery of the Statistical Types of Variables in a DatasetPoster46 citations
287. Risk Bounds for Transferring Representations With and Without Fine-TuningPoster46 citations
288. Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample ReductionPoster46 citations
289. Conditional Accelerated Lazy Stochastic Gradient DescentPoster45 citations
290. Hierarchy Through Composition with Multitask LMDPsPoster45 citations
291. Leveraging Node Attributes for Incomplete Relational DataPoster45 citations
292. Probabilistic Submodular Maximization in Sub-Linear TimePoster45 citations
293. Uncorrelation and Evenness: a New Diversity-Promoting RegularizerPoster45 citations
294. Bayesian Boolean Matrix FactorisationPoster43 citations
295. Gradient Projection Iterative Sketch for Large-Scale Constrained Least-SquaresPoster43 citations
296. Simultaneous Learning of Trees and Representations for Extreme Classification and Density EstimationPoster42 citations
297. Analysis and Optimization of Graph Decompositions by Lifted MulticutsPoster41 citations
298. Input Switched Affine Networks: An RNN Architecture Designed for InterpretabilityPoster41 citations
299. Neural Taylor Approximations: Convergence and Exploration in Rectifier NetworksPoster41 citations
300. Scalable Generative Models for Multi-label Learning with Missing LabelsPoster41 citations
301. Tight Bounds for Approximate Carathéodory and BeyondPoster41 citations
302. Breaking Locality Accelerates Block Gauss-SeidelPoster40 citations
303. Learning to Discover Sparse Graphical ModelsPoster40 citations
304. Reduced Space and Faster Convergence in Imperfect-Information Games via PruningPoster40 citations
305. Understanding the Representation and Computation of Multilayer Perceptrons: A Case Study in Speech Recognition40 citations
306. Differentially Private Learning of Undirected Graphical Models Using Collective Graphical ModelsPoster39 citations
307. Distributed and Provably Good Seedings for k-Means in Constant RoundsPoster39 citations
308. Stochastic Bouncy Particle SamplerPoster39 citations
309. Consistency Analysis for Binary Classification RevisitedPoster38 citations
310. Fast k-Nearest Neighbour Search via Prioritized DCIPoster38 citations
311. Source-Target Similarity Modelings for Multi-Source Transfer Gaussian Process RegressionPoster38 citations
312. A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete DistributionsPoster37 citations
313. Lost Relatives of the Gumbel TrickPoster37 citations
314. Multi-Class Optimal Margin Distribution MachinePoster37 citations
315. On the Iteration Complexity of Support Recovery via Hard Thresholding PursuitPoster37 citations
316. Density Level Set Estimation on Manifolds with DBSCANPoster36 citations
317. Regret Minimization in Behaviorally-Constrained Zero-Sum GamesPoster36 citations
318. Diameter-Based Active LearningPoster35 citations
319. Hyperplane Clustering via Dual Principal Component PursuitPoster35 citations
320. Oracle Complexity of Second-Order Methods for Finite-Sum ProblemsPoster35 citations
321. Stochastic Gradient MCMC Methods for Hidden Markov ModelsPoster35 citations
322. Identification and Model Testing in Linear Structural Equation Models using Auxiliary VariablesPoster34 citations
323. Stochastic DCA for the Large-sum of Non-convex Functions Problem and its Application to Group Variable Selection in ClassificationPoster34 citations
324. Learning Determinantal Point Processes with Moments and CyclesPoster33 citations
325. Tensor Balancing on Statistical ManifoldPoster33 citations
326. Variational Inference for Sparse and Undirected ModelsPoster33 citations
327. Dueling Bandits with Weak RegretPoster32 citations
328. Follow the Moving Leader in Deep LearningPoster32 citations
329. A Semismooth Newton Method for Fast, Generic Convex ProgrammingPoster31 citations
330. Bottleneck Conditional Density EstimationPoster31 citations
331. Differentially Private Chi-squared Test by Unit Circle MechanismPoster31 citations
332. Fast Bayesian Intensity Estimation for the Permanental ProcessPoster31 citations
333. High-Dimensional Variance-Reduced Stochastic Gradient Expectation-Maximization AlgorithmPoster31 citations
334. Learning Stable Stochastic Nonlinear Dynamical SystemsPoster31 citations
335. Relative Fisher Information and Natural Gradient for Learning Large Modular ModelsPoster31 citations
336. Stochastic Adaptive Quasi-Newton Methods for Minimizing Expected ValuesPoster31 citations
337. Asynchronous Distributed Variational Gaussian Process for RegressionPoster30 citations
338. Learning to Align the Source Code to the Compiled Object CodePoster30 citations
339. Spherical Structured Feature Maps for Kernel ApproximationPoster30 citations
340. Strong NP-Hardness for Sparse Optimization with Concave Penalty FunctionsPoster30 citations
341. Variational Policy for Guiding Point ProcessesPoster30 citations
342. iSurvive: An Interpretable, Event-time Prediction Model for mHealthPoster30 citations
343. Tensor Decomposition with SmoothnessPoster29 citations
344. Forest-type Regression with General Losses and Robust ForestPoster28 citations
345. Active Heteroscedastic RegressionPoster27 citations
346. Approximate Newton Methods and Their Local ConvergencePoster27 citations
347. Bayesian Models of Data Streams with Hierarchical Power PriorsPoster27 citations
348. How Close Are the Eigenvectors of the Sample and Actual Covariance Matrices?Poster27 citations
349. Learning Latent Space Models with Angular ConstraintsPoster27 citations
350. Multilabel Classification with Group Testing and CodesPoster27 citations
351. Uniform Deviation Bounds for k-Means ClusteringPoster27 citations
352. Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIPPoster26 citations
353. Local Bayesian Optimization of Motor SkillsPoster26 citations
354. Composing Tree Graphical Models with Persistent Homology Features for Clustering Mixed-Type DataPoster25 citations
355. Adaptive Multiple-Arm IdentificationPoster24 citations
356. Doubly Greedy Primal-Dual Coordinate Descent for Sparse Empirical Risk MinimizationPoster24 citations
357. Evaluating the Variance of Likelihood-Ratio Gradient EstimatorsPoster24 citations
358. Faster Greedy MAP Inference for Determinantal Point ProcessesPoster24 citations
359. Frame-based Data FactorizationsPoster24 citations
360. Nonparanormal Information EstimationPoster24 citations
361. On the Sampling Problem for Kernel QuadraturePoster24 citations
362. Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong CorrelationsPoster24 citations
363. Faster Principal Component Regression and Stable Matrix Chebyshev ApproximationPoster23 citations
364. Scalable Multi-Class Gaussian Process Classification using Expectation PropagationPoster23 citations
365. Statistical Inference for Incomplete Ranking Data: The Case of Rank-Dependent CoarseningPoster23 citations
366. A Richer Theory of Convex Constrained Optimization with Reduced Projections and Improved RatesPoster22 citations
367. ChoiceRank: Identifying Preferences from Node Traffic in NetworksPoster22 citations
368. Deep Generative Models for Relational Data with Side InformationPoster22 citations
369. Leveraging Union of Subspace Structure to Improve Constrained ClusteringPoster22 citations
370. On Approximation Guarantees for Greedy Low Rank OptimizationPoster22 citations
371. Online Learning with Local Permutations and Delayed FeedbackPoster22 citations
372. StingyCD: Safely Avoiding Wasteful Updates in Coordinate DescentPoster22 citations
373. The Sample Complexity of Online One-Class Collaborative FilteringPoster22 citations
374. Approximate Steepest Coordinate DescentPoster21 citations
375. Bidirectional Learning for Time-series Models with Hidden UnitsPoster21 citations
376. Innovation Pursuit: A New Approach to the Subspace Clustering ProblemPoster21 citations
377. Tensor Decomposition via Simultaneous Power IterationPoster21 citations
378. Zonotope Hit-and-run for Efficient Sampling from Projection DPPsPoster21 citations
379. An Efficient, Sparsity-Preserving, Online Algorithm for Low-Rank ApproximationPoster20 citations
380. Convex Phase Retrieval without Lifting via PhaseMaxPoster20 citations
381. Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave MaximizationPoster20 citations
382. Estimating the unseen from multiple populationsPoster20 citations
383. Toward Efficient and Accurate Covariance Matrix Estimation on Compressed DataPoster20 citations
384. Active Learning for Accurate Estimation of Linear ModelsPoster19 citations
385. Robust Guarantees of Stochastic Greedy AlgorithmsPoster19 citations
386. Enumerating Distinct Decision TreesPoster18 citations
387. Minimizing Trust Leaks for Robust Sybil DetectionPoster18 citations
388. Multiple Clustering Views from Multiple Uncertain ExpertsPoster18 citations
389. Ordinal Graphical Models: A Tale of Two ApproachesPoster18 citations
390. When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, $\ell_2$-consistency and Neuroscience ApplicationsPoster18 citations
391. Regularising Non-linear Models Using Feature Side-informationPoster17 citations
392. Connected Subgraph Detection with Mirror Descent on SDPsPoster15 citations
393. Globally Induced Forest: A Prepruning Compression SchemePoster15 citations
394. Robust Gaussian Graphical Model Estimation with Arbitrary CorruptionPoster15 citations
395. Identify the Nash Equilibrium in Static Games with Random PayoffsPoster14 citations
396. Tensor Belief PropagationPoster14 citations
397. Adapting Kernel Representations Online Using Submodular MaximizationPoster12 citations
398. High-Dimensional Structured Quantile RegressionPoster12 citations
399. Stochastic Gradient Monomial Gamma SamplerPoster12 citations
400. Uncertainty Assessment and False Discovery Rate Control in High-Dimensional Granger Causal InferencePoster12 citations
401. Zero-Inflated Exponential Family EmbeddingsPoster12 citations
402. A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix RecoveryPoster11 citations
403. Dictionary Learning Based on Sparse Distribution TomographyPoster11 citations
404. Latent Feature LassoPoster11 citations
405. Post-Inference Prior SwappingPoster11 citations
406. A Simple Multi-Class Boosting Framework with Theoretical Guarantees and Empirical ProficiencyPoster10 citations
407. Canopy Fast Sampling with Cover TreesPoster10 citations
408. Coherence Pursuit: Fast, Simple, and Robust Subspace RecoveryPoster10 citations
409. Coresets for Vector Summarization with Applications to Network GraphsPoster10 citations
410. From Patches to Images: A Nonparametric Generative ModelPoster10 citations
411. Robust Structured Estimation with Single-Index ModelsPoster10 citations
412. Bayesian inference on random simple graphs with power law degree distributionsPoster9 citations
413. Learning to Aggregate Ordinal Labels by Maximizing Separating WidthPoster9 citations
414. Rule-Enhanced Penalized Regression by Column Generation using Rectangular Maximum AgreementPoster9 citations
415. SPLICE: Fully Tractable Hierarchical Extension of ICA with PoolingPoster8 citations
416. A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVIPoster7 citations
417. Exact Inference for Integer Latent-Variable ModelsPoster7 citations
418. GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite OptimizationPoster7 citations
419. Evaluating Bayesian Models with Posterior Dispersion IndicesPoster6 citations
420. Learning Infinite Layer Networks Without the Kernel TrickPoster6 citations
421. Spectral Learning from a Single Trajectory under Finite-State PoliciesPoster6 citations
422. A Simulated Annealing Based Inexact Oracle for Wasserstein Loss MinimizationPoster5 citations
423. Improving Gibbs Sampler Scan Quality with DoGSPoster5 citations
424. Online Partial Least Square Optimization: Dropping Convexity for Better Efficiency and ScalabilityPoster5 citations
425. Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-ConvexityPoster5 citations
426. Exact MAP Inference by Avoiding Fractional VerticesPoster4 citations
427. Strongly-Typed Agents are Guaranteed to Interact SafelyPoster3 citations
428. An Infinite Hidden Markov Model With Similarity-Biased TransitionsPoster2 citations
429. Partitioned Tensor Factorizations for Learning Mixed Membership ModelsPoster2 citations
430. A Birth-Death Process for Feature AllocationPoster1 citations
431. Efficient Online Bandit Multiclass Learning with $\tilde{O}(\sqrt{T})$ RegretPoster
432. On The Projection Operator to A Three-view Cardinality Constrained SetPoster
433. Variational Boosting: Iteratively Refining Posterior ApproximationsPoster

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