ICML 2015 Accepted Papers

The full list of 270 papers accepted at ICML 2015 (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. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftPoster62,227 citations
2. Show, Attend and Tell: Neural Image Caption Generation with Visual AttentionPoster13,573 citations
3. Trust Region Policy OptimizationPoster9,809 citations
4. Deep Unsupervised Learning using Nonequilibrium ThermodynamicsPoster8,219 citations
5. Unsupervised Domain Adaptation by BackpropagationPoster8,165 citations
6. Learning Transferable Features with Deep Adaptation NetworksPoster6,646 citations
7. Variational Inference with Normalizing FlowsPoster5,252 citations
8. Weight Uncertainty in Neural NetworkPoster4,731 citations
9. Unsupervised Learning of Video Representations using LSTMsPoster3,471 citations
10. From Word Embeddings To Document DistancesPoster3,059 citations
11. Deep Learning with Limited Numerical PrecisionPoster2,815 citations
12. DRAW: A Recurrent Neural Network For Image GenerationPoster2,594 citations
13. An Empirical Exploration of Recurrent Network ArchitecturesPoster2,562 citations
14. An embarrassingly simple approach to zero-shot learningPoster1,617 citations
15. Compressing Neural Networks with the Hashing TrickPoster1,494 citations
16. Scalable Bayesian Optimization Using Deep Neural NetworksPoster1,406 citations
17. Universal Value Function ApproximatorsPoster1,370 citations
18. Probabilistic Backpropagation for Scalable Learning of Bayesian Neural NetworksPoster1,265 citations
19. Optimizing Neural Networks with Kronecker-factored Approximate CurvaturePoster1,238 citations
20. On Deep Multi-View Representation LearningPoster1,235 citations
21. Gated Feedback Recurrent Neural NetworksPoster1,213 citations
22. Gradient-based Hyperparameter Optimization through Reversible LearningPoster1,174 citations
23. MADE: Masked Autoencoder for Distribution EstimationPoster1,114 citations
24. Generative Moment Matching NetworksPoster1,101 citations
25. Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural NetworkPoster1,028 citations
26. The Composition Theorem for Differential PrivacyPoster890 citations
27. Markov Chain Monte Carlo and Variational Inference: Bridging the GapPoster767 citations
28. Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP)Poster684 citations
29. Is Feature Selection Secure against Training Data Poisoning?Poster545 citations
30. Stochastic Optimization with Importance Sampling for Regularized Loss MinimizationPoster502 citations
31. Submodularity in Data Subset Selection and Active LearningPoster501 citations
32. Safe Exploration for Optimization with Gaussian ProcessesPoster498 citations
33. High Dimensional Bayesian Optimisation and Bandits via Additive ModelsPoster472 citations
34. Distributed Gaussian ProcessesPoster467 citations
35. Long Short-Term Memory Over Recursive StructuresPoster466 citations
36. BilBOWA: Fast Bilingual Distributed Representations without Word AlignmentsPoster454 citations
37. Fictitious Self-Play in Extensive-Form GamesPoster449 citations
38. Counterfactual Risk Minimization: Learning from Logged Bandit FeedbackPoster425 citations
39. Convex Formulation for Learning from Positive and Unlabeled DataPoster407 citations
40. A General Analysis of the Convergence of ADMMPoster404 citations
41. Cascading Bandits: Learning to Rank in the Cascade ModelPoster338 citations
42. Learning Deep Structured ModelsPoster315 citations
43. Log-Euclidean Metric Learning on Symmetric Positive Definite Manifold with Application to Image Set ClassificationPoster313 citations
44. Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk MinimizationPoster310 citations
45. Privacy for Free: Posterior Sampling and Stochastic Gradient Monte CarloPoster304 citations
46. Learning from Corrupted Binary Labels via Class-Probability EstimationPoster295 citations
47. Coordinate Descent Converges Faster with the Gauss-Southwell Rule Than Random SelectionPoster285 citations
48. DiSCO: Distributed Optimization for Self-Concordant Empirical LossPoster273 citations
49. Deep Edge-Aware FiltersPoster268 citations
50. Bimodal Modelling of Source Code and Natural LanguagePoster257 citations
51. Learning Program Embeddings to Propagate Feedback on Student CodePoster249 citations
52. Learning to Search Better than Your TeacherPoster237 citations
53. High Confidence Policy ImprovementPoster233 citations
54. Faster Rates for the Frank-Wolfe Method over Strongly-Convex SetsPoster231 citations
55. Towards a Learning Theory of Cause-Effect InferencePoster229 citations
56. On Symmetric and Asymmetric LSHs for Inner Product SearchPoster224 citations
57. Adding vs. Averaging in Distributed Primal-Dual OptimizationPoster214 citations
58. Global Convergence of Stochastic Gradient Descent for Some Non-convex Matrix ProblemsPoster206 citations
59. Strongly Adaptive Online LearningPoster205 citations
60. Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple PlaysPoster202 citations
61. Predictive Entropy Search for Bayesian Optimization with Unknown ConstraintsPoster202 citations
62. PU Learning for Matrix CompletionPoster195 citations
63. Yinyang K-Means: A Drop-In Replacement of the Classic K-Means with Consistent SpeedupPoster194 citations
64. Training Deep Convolutional Neural Networks to Play GoPoster193 citations
65. Consistent estimation of dynamic and multi-layer block modelsPoster184 citations
66. A Stochastic PCA and SVD Algorithm with an Exponential Convergence RatePoster182 citations
67. Spectral MLE: Top-K Rank Aggregation from Pairwise ComparisonsPoster182 citations
68. Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimizationPoster177 citations
69. A Lower Bound for the Optimization of Finite SumsPoster164 citations
70. Mind the duality gap: safer rules for the LassoPoster162 citations
71. Phrase-based Image CaptioningPoster160 citations
72. The Ladder: A Reliable Leaderboard for Machine Learning CompetitionsPoster154 citations
73. Subsampling Methods for Persistent HomologyPoster151 citations
74. Variational Inference for Gaussian Process Modulated Poisson ProcessesPoster146 citations
75. Support Matrix MachinesPoster144 citations
76. Approximate Dynamic Programming for Two-Player Zero-Sum Markov GamesPoster140 citations
77. Efficient Learning in Large-Scale Combinatorial Semi-BanditsPoster125 citations
78. Fast Kronecker Inference in Gaussian Processes with non-Gaussian LikelihoodsPoster123 citations
79. HawkesTopic: A Joint Model for Network Inference and Topic Modeling from Text-Based CascadesPoster123 citations
80. A Nearly-Linear Time Framework for Graph-Structured SparsityPoster121 citations
81. Large-scale log-determinant computation through stochastic Chebyshev expansionsPoster121 citations
82. Coresets for Nonparametric Estimation - the Case of DP-MeansPoster120 citations
83. Correlation Clustering in Data StreamsPoster120 citations
84. PASSCoDe: Parallel ASynchronous Stochastic dual Co-ordinate DescentPoster119 citations
85. On the Relationship between Sum-Product Networks and Bayesian NetworksPoster117 citations
86. Simple regret for infinitely many armed banditsPoster116 citations
87. The Power of Randomization: Distributed Submodular Maximization on Massive DatasetsPoster114 citations
88. Sparse Subspace Clustering with Missing EntriesPoster112 citations
89. Scalable Deep Poisson Factor Analysis for Topic ModelingPoster111 citations
90. Discovering Temporal Causal Relations from Subsampled DataPoster110 citations
91. A Unifying Framework of Anytime Sparse Gaussian Process Regression Models with Stochastic Variational Inference for Big DataPoster109 citations
92. Stochastic Dual Coordinate Ascent with Adaptive ProbabilitiesPoster107 citations
93. Finding Linear Structure in Large Datasets with Scalable Canonical Correlation AnalysisPoster102 citations
94. Improving the Gaussian Process Sparse Spectrum Approximation by Representing Uncertainty in Frequency InputsPoster102 citations
95. Online Time Series Prediction with Missing DataPoster100 citations
96. Preference Completion: Large-scale Collaborative Ranking from Pairwise ComparisonsPoster99 citations
97. Optimal and Adaptive Algorithms for Online BoostingPoster98 citations
98. Causal Inference by Identification of Vector Autoregressive Processes with Hidden ComponentsPoster95 citations
99. Convex Learning of Multiple Tasks and their StructurePoster94 citations
100. Abstraction Selection in Model-based Reinforcement LearningPoster93 citations
101. Boosted Categorical Restricted Boltzmann Machine for Computational Prediction of Splice JunctionsPoster93 citations
102. Nested Sequential Monte Carlo MethodsPoster91 citations
103. Approval Voting and Incentives in CrowdsourcingPoster90 citations
104. Hidden Markov Anomaly DetectionPoster90 citations
105. Multiview Triplet Embedding: Learning Attributes in Multiple MapsPoster88 citations
106. Safe Policy Search for Lifelong Reinforcement Learning with Sublinear RegretPoster88 citations
107. Complex Event Detection using Semantic Saliency and Nearly-Isotonic SVMPoster83 citations
108. Feature-Budgeted Random ForestPoster82 citations
109. A Deeper Look at Planning as Learning from ReplayPoster81 citations
110. Spectral Clustering via the Power Method - ProvablyPoster81 citations
111. The Kendall and Mallows Kernels for PermutationsPoster81 citations
112. Accelerated Online Low Rank Tensor Learning for Multivariate Spatiotemporal StreamsPoster79 citations
113. Consistent Multiclass Algorithms for Complex Performance MeasuresPoster78 citations
114. The Fundamental Incompatibility of Scalable Hamiltonian Monte Carlo and Naive Data SubsamplingPoster78 citations
115. Learning Word Representations with Hierarchical Sparse CodingPoster75 citations
116. A Multitask Point Process Predictive ModelPoster74 citations
117. Scaling up Natural Gradient by Sparsely Factorizing the Inverse Fisher MatrixPoster73 citations
118. Blitz: A Principled Meta-Algorithm for Scaling Sparse OptimizationPoster71 citations
119. On Greedy Maximization of EntropyPoster71 citations
120. Modeling Order in Neural Word Embeddings at ScalePoster70 citations
121. Differentially Private Bayesian OptimizationPoster69 citations
122. Fixed-point algorithms for learning determinantal point processesPoster68 citations
123. Inferring Graphs from Cascades: A Sparse Recovery FrameworkPoster67 citations
124. Multi-view Sparse Co-clustering via Proximal Alternating Linearized MinimizationPoster67 citations
125. Telling cause from effect in deterministic linear dynamical systemsPoster67 citations
126. A Provable Generalized Tensor Spectral Method for Uniform Hypergraph PartitioningPoster65 citations
127. Distributed Box-Constrained Quadratic Optimization for Dual Linear SVMPoster65 citations
128. Optimizing Non-decomposable Performance Measures: A Tale of Two ClassesPoster65 citations
129. Asymmetric Transfer Learning with Deep Gaussian ProcessesPoster64 citations
130. Faster cover treesPoster62 citations
131. An Aligned Subtree Kernel for Weighted GraphsPoster61 citations
132. On TD(0) with function approximation: Concentration bounds and a centered variant with exponential convergencePoster61 citations
133. Geometric Conditions for Subspace-Sparse RecoveryPoster60 citations
134. Qualitative Multi-Armed Bandits: A Quantile-Based ApproachPoster60 citations
135. Binary Embedding: Fundamental Limits and Fast AlgorithmPoster58 citations
136. Latent Gaussian Processes for Distribution Estimation of Multivariate Categorical DataPoster58 citations
137. Robust partially observable Markov decision processPoster58 citations
138. Random Coordinate Descent Methods for Minimizing Decomposable Submodular FunctionsPoster57 citations
139. Learning Submodular Losses with the Lovasz HingePoster56 citations
140. Online Learning of EigenvectorsPoster56 citations
141. A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling BanditsPoster55 citations
142. Bayesian and Empirical Bayesian ForestsPoster54 citations
143. Multi-instance multi-label learning in the presence of novel class instancesPoster54 citations
144. Swept Approximate Message Passing for Sparse EstimationPoster52 citations
145. Classification with Low Rank and Missing DataPoster51 citations
146. \ell_1,p-Norm Regularization: Error Bounds and Convergence Rate Analysis of First-Order MethodsPoster51 citations
147. Robust Estimation of Transition Matrices in High Dimensional Heavy-tailed Vector Autoregressive ProcessesPoster50 citations
148. Distributed Inference for Dirichlet Process Mixture ModelsPoster49 citations
149. Following the Perturbed Leader for Online Structured LearningPoster49 citations
150. Complete Dictionary Recovery Using Nonconvex OptimizationPoster48 citations
151. Improved Regret Bounds for Undiscounted Continuous Reinforcement LearningPoster48 citations
152. Surrogate Functions for Maximizing Precision at the TopPoster48 citations
153. CUR Algorithm for Partially Observed MatricesPoster47 citations
154. Scalable Nonparametric Bayesian Inference on Point Processes with Gaussian ProcessesPoster47 citations
155. A Theoretical Analysis of Metric Hypothesis Transfer LearningPoster46 citations
156. Active Nearest Neighbors in Changing EnvironmentsPoster46 citations
157. Celeste: Variational inference for a generative model of astronomical imagesPoster46 citations
158. An Asynchronous Distributed Proximal Gradient Method for Composite Convex OptimizationPoster45 citations
159. Controversy in mechanistic modelling with Gaussian processesPoster44 citations
160. Message Passing for Collective Graphical ModelsPoster44 citations
161. A Deterministic Analysis of Noisy Sparse Subspace Clustering for Dimensionality-reduced DataPoster42 citations
162. Enabling scalable stochastic gradient-based inference for Gaussian processes by employing the Unbiased LInear System SolvEr (ULISSE)Poster42 citations
163. Guaranteed Tensor Decomposition: A Moment ApproachPoster42 citations
164. A Linear Dynamical System Model for TextPoster41 citations
165. A trust-region method for stochastic variational inference with applications to streaming dataPoster41 citations
166. Convergence rate of Bayesian tensor estimator and its minimax optimalityPoster41 citations
167. DP-space: Bayesian Nonparametric Subspace Clustering with Small-variance AsymptoticsPoster41 citations
168. Off-policy Model-based Learning under Unknown Factored DynamicsPoster41 citations
169. Sparse Variational Inference for Generalized GP ModelsPoster41 citations
170. Functional Subspace Clustering with Application to Time SeriesPoster40 citations
171. The Hedge Algorithm on a ContinuumPoster40 citations
172. On the Rate of Convergence and Error Bounds for LSTD(λ)Poster39 citations
173. Streaming Sparse Principal Component AnalysisPoster39 citations
174. How Hard is Inference for Structured Prediction?Poster38 citations
175. Hashing for Distributed DataPoster37 citations
176. Latent Topic Networks: A Versatile Probabilistic Programming Framework for Topic ModelsPoster36 citations
177. Towards a Lower Sample Complexity for Robust One-bit Compressed SensingPoster36 citations
178. How Can Deep Rectifier Networks Achieve Linear Separability and Preserve Distances?Poster34 citations
179. A Probabilistic Model for Dirty Multi-task Feature SelectionPoster33 citations
180. Non-Linear Cross-Domain Collaborative Filtering via Hyper-Structure TransferPoster32 citations
181. Adaptive Stochastic Alternating Direction Method of MultipliersPoster29 citations
182. Distributed Estimation of Generalized Matrix Rank: Efficient Algorithms and Lower BoundsPoster29 citations
183. Vector-Space Markov Random Fields via Exponential FamiliesPoster29 citations
184. Bipartite Edge Prediction via Transductive Learning over Product GraphsPoster28 citations
185. Budget Allocation Problem with Multiple Advertisers: A Game Theoretic ViewPoster28 citations
186. Community Detection Using Time-Dependent Personalized PageRankPoster28 citations
187. Exponential Integration for Hamiltonian Monte CarloPoster28 citations
188. Ranking from Stochastic Pairwise Preferences: Recovering Condorcet Winners and Tournament Solution Sets at the TopPoster28 citations
189. Scalable Variational Inference in Log-supermodular ModelsPoster28 citations
190. An Empirical Study of Stochastic Variational Inference Algorithms for the Beta Bernoulli ProcessPoster27 citations
191. Intersecting Faces: Non-negative Matrix Factorization With New GuaranteesPoster27 citations
192. A Fast Variational Approach for Learning Markov Random Field Language ModelsPoster26 citations
193. PeakSeg: constrained optimal segmentation and supervised penalty learning for peak detection in count dataPoster26 citations
194. A New Generalized Error Path Algorithm for Model SelectionPoster25 citations
195. Harmonic Exponential Families on ManifoldsPoster25 citations
196. Learning Local Invariant Mahalanobis DistancesPoster25 citations
197. Safe Screening for Multi-Task Feature Learning with Multiple Data MatricesPoster24 citations
198. Convex Calibrated Surrogates for Hierarchical ClassificationPoster23 citations
199. Entropy-Based Concentration Inequalities for Dependent VariablesPoster23 citations
200. Multi-Task Learning for Subspace SegmentationPoster23 citations
201. Threshold Influence Model for Allocating Advertising BudgetsPoster23 citations
202. An Explicit Sampling Dependent Spectral Error Bound for Column Subset SelectionPoster22 citations
203. Statistical and Algorithmic Perspectives on Randomized Sketching for Ordinary Least-SquaresPoster22 citations
204. Bayesian Multiple Target LocalizationPoster21 citations
205. Unsupervised Riemannian Metric Learning for Histograms Using Aitchison TransformationsPoster20 citations
206. Cheap BanditsPoster19 citations
207. Entropy evaluation based on confidence intervals of frequency estimates : Application to the learning of decision treesPoster19 citations
208. On the Optimality of Multi-Label Classification under Subset Zero-One Loss for Distributions Satisfying the Composition PropertyPoster19 citations
209. A Convex Optimization Framework for Bi-ClusteringPoster18 citations
210. A Hybrid Approach for Probabilistic Inference using Random ProjectionsPoster18 citations
211. A Modified Orthant-Wise Limited Memory Quasi-Newton Method with Convergence AnalysisPoster18 citations
212. Efficient Training of LDA on a GPU by Mean-for-Mode EstimationPoster18 citations
213. Landmarking Manifolds with Gaussian ProcessesPoster18 citations
214. Large-Scale Markov Decision Problems with KL Control Cost and its Application to CrowdsourcingPoster18 citations
215. Paired-Dual Learning for Fast Training of Latent Variable Hinge-Loss MRFsPoster18 citations
216. Variational Generative Stochastic Networks with Collaborative ShapingPoster18 citations
217. A Divide and Conquer Framework for Distributed Graph ClusteringPoster16 citations
218. Attribute Efficient Linear Regression with Distribution-Dependent SamplingPoster16 citations
219. Non-Stationary Approximate Modified Policy IterationPoster16 citations
220. Rebuilding Factorized Information Criterion: Asymptotically Accurate Marginal LikelihoodPoster16 citations
221. Safe Subspace Screening for Nuclear Norm Regularized Least Squares ProblemsPoster16 citations
222. Low Rank Approximation using Error Correcting Coding MatricesPoster15 citations
223. Theory of Dual-sparse Regularized Randomized ReductionPoster15 citations
224. A Bayesian nonparametric procedure for comparing algorithmsPoster14 citations
225. Distributional Rank Aggregation, and an Axiomatic AnalysisPoster14 citations
226. Generalization error bounds for learning to rank: Does the length of document lists matter?Poster14 citations
227. Large-scale Distributed Dependent Nonparametric TreesPoster14 citations
228. Learning Scale-Free Networks by Dynamic Node Specific Degree PriorPoster14 citations
229. Markov Mixed Membership ModelsPoster14 citations
230. Alpha-Beta Divergences Discover Micro and Macro Structures in DataPoster13 citations
231. Low-Rank Matrix Recovery from Row-and-Column Affine MeasurementsPoster13 citations
232. Manifold-valued Dirichlet ProcessesPoster13 citations
233. Pushing the Limits of Affine Rank Minimization by Adapting Probabilistic PCAPoster13 citations
234. Learning Fast-Mixing Models for Structured PredictionPoster12 citations
235. On Identifying Good Options under Combinatorially Structured Feedback in Finite Noisy EnvironmentsPoster12 citations
236. Proteins, Particles, and Pseudo-Max-Marginals: A Submodular ApproachPoster12 citations
237. Removing systematic errors for exoplanet search via latent causesPoster12 citations
238. Entropic Graph-based Posterior RegularizationPoster11 citations
239. JUMP-Means: Small-Variance Asymptotics for Markov Jump ProcessesPoster11 citations
240. Metadata Dependent Mondrian ProcessesPoster11 citations
241. Rademacher Observations, Private Data, and BoostingPoster11 citations
242. Scalable Model Selection for Large-Scale Factorial Relational ModelsPoster11 citations
243. The Benefits of Learning with Strongly Convex Approximate InferencePoster10 citations
244. A Unified Framework for Outlier-Robust PCA-like AlgorithmsPoster9 citations
245. A low variance consistent test of relative dependencyPoster9 citations
246. Dealing with small data: On the generalization of context treesPoster9 citations
247. K-hyperplane Hinge-Minimax ClassifierPoster9 citations
248. MRA-based Statistical Learning from Incomplete RankingsPoster9 citations
249. A Convex Exemplar-based Approach to MAD-Bayes Dirichlet Process Mixture ModelsPoster8 citations
250. Moderated and Drifting Linear Dynamical SystemsPoster8 citations
251. Non-Gaussian Discriminative Factor Models via the Max-Margin Rank-LikelihoodPoster8 citations
252. Stay on path: PCA along graph pathsPoster8 citations
253. Structural Maxent ModelsPoster8 citations
254. Algorithms for the Hard Pre-Image Problem of String Kernels and the General Problem of String PredictionPoster7 citations
255. Double Nyström Method: An Efficient and Accurate Nyström Scheme for Large-Scale Data SetsPoster7 citations
256. Inference in a Partially Observed Queuing Model with Applications in EcologyPoster7 citations
257. Learning Parametric-Output HMMs with Two Aliased StatesPoster7 citations
258. Risk and Regret of Hierarchical Bayesian LearnersPoster7 citations
259. Tracking Approximate Solutions of Parameterized Optimization Problems over Multi-Dimensional (Hyper-)Parameter DomainsPoster7 citations
260. Adaptive Belief PropagationPoster6 citations
261. Ordinal Mixed Membership ModelsPoster6 citations
262. Finding Galaxies in the Shadows of Quasars with Gaussian ProcessesPoster5 citations
263. Reified Context ModelsPoster5 citations
264. Context-based Unsupervised Data Fusion for Decision MakingPoster4 citations
265. Deterministic Independent Component AnalysisPoster4 citations
266. An Online Learning Algorithm for Bilinear ModelsPoster3 citations
267. Information Geometry and Minimum Description Length NetworksPoster3 citations
268. Atomic Spatial ProcessesPoster2 citations
269. Dynamic Sensing: Better Classification under Acquisition ConstraintsPoster2 citations
270. Ordered Stick-Breaking Prior for Sequential MCMC Inference of Bayesian Nonparametric ModelsPoster1 citations

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