AISTATS 2017 Accepted Papers

The full list of 167 papers accepted at AISTATS 2017 (International Conference on Artificial Intelligence and Statistics). 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. Communication-Efficient Learning of Deep Networks from Decentralized DataPoster23,789 citations
2. Fairness Constraints: Mechanisms for Fair ClassificationPoster1,615 citations
3. Fast Bayesian Optimization of Machine Learning Hyperparameters on Large DatasetsPoster788 citations
4. Linear Thompson Sampling RevisitedPoster310 citations
5. Bayesian Learning and Inference in Recurrent Switching Linear Dynamical SystemsPoster301 citations
6. Decentralized Collaborative Learning of Personalized Models over NetworksPoster288 citations
7. Nonlinear ICA of Temporally Dependent Stationary SourcesPoster276 citations
8. Beta calibration: a well-founded and easily implemented improvement on logistic calibration for binary classifiersPoster262 citations
9. Non-square matrix sensing without spurious local minima via the Burer-Monteiro approachPoster207 citations
10. Guaranteed Non-convex Optimization: Submodular Maximization over Continuous DomainsPoster182 citations
11. Inference Compilation and Universal Probabilistic ProgrammingPoster175 citations
12. Conjugate-Computation Variational Inference : Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate ModelsPoster174 citations
13. Learning from Conditional Distributions via Dual EmbeddingsPoster156 citations
14. Learning Structured Weight Uncertainty in Bayesian Neural NetworksPoster153 citations
15. Phase Retrieval Meets Statistical Learning Theory: A Flexible Convex RelaxationPoster153 citations
16. The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear BanditsPoster151 citations
17. Discovering and Exploiting Additive Structure for Bayesian OptimizationPoster149 citations
18. Value-Aware Loss Function for Model-based Reinforcement LearningPoster149 citations
19. On the Hyperprior Choice for the Global Shrinkage Parameter in the Horseshoe PriorPoster146 citations
20. Scalable Learning of Non-Decomposable ObjectivesPoster144 citations
21. ASAGA: Asynchronous Parallel SAGAPoster141 citations
22. Adaptive ADMM with Spectral Penalty Parameter SelectionPoster141 citations
23. Reparameterization Gradients through Acceptance-Rejection Sampling AlgorithmsPoster141 citations
24. Less than a Single Pass: Stochastically Controlled Stochastic GradientPoster129 citations
25. Diverse Neural Network Learns True Target FunctionsPoster126 citations
26. Learning Cost-Effective and Interpretable Treatment RegimesPoster125 citations
27. Sketchy Decisions: Convex Low-Rank Matrix Optimization with Optimal StoragePoster124 citations
28. Automated Inference with Adaptive BatchesPoster112 citations
29. Scalable Greedy Feature Selection via Weak SubmodularityPoster107 citations
30. Finite-sum Composition Optimization via Variance Reduced Gradient DescentPoster101 citations
31. Frank-Wolfe Algorithms for Saddle Point ProblemsPoster100 citations
32. A Unified Computational and Statistical Framework for Nonconvex Low-rank Matrix EstimationPoster95 citations
33. Generalization Error of Invariant ClassifiersPoster92 citations
34. Improved Strongly Adaptive Online Learning using Coin BettingPoster85 citations
35. Regret Bounds for Lifelong LearningPoster85 citations
36. Black-box Importance SamplingPoster82 citations
37. Nearly Instance Optimal Sample Complexity Bounds for Top-k Arm SelectionPoster82 citations
38. Thompson Sampling for Linear-Quadratic Control ProblemsPoster81 citations
39. Stochastic Rank-1 BanditsPoster79 citations
40. A Unified Optimization View on Generalized Matching Pursuit and Frank-WolfePoster71 citations
41. On the Learnability of Fully-Connected Neural NetworksPoster67 citations
42. Faster Coordinate Descent via Adaptive Importance SamplingPoster65 citations
43. Learning Nash Equilibrium for General-Sum Markov Games from Batch DataPoster64 citations
44. Localized Lasso for High-Dimensional RegressionPoster63 citations
45. DP-EM: Differentially Private Expectation MaximizationPoster62 citations
46. Poisson intensity estimation with reproducing kernelsPoster61 citations
47. ConvNets with Smooth Adaptive Activation Functions for RegressionPoster57 citations
48. Sketching Meets Random Projection in the Dual: A Provable Recovery Algorithm for Big and High-dimensional DataPoster57 citations
49. Contextual Bandits with Latent Confounders: An NMF ApproachPoster55 citations
50. High-dimensional Time Series Clustering via Cross-PredictabilityPoster53 citations
51. Exploration-Exploitation in MDPs with OptionsPoster52 citations
52. Label Filters for Large Scale Multilabel ClassificationPoster51 citations
53. Fast rates with high probability in exp-concave statistical learningPoster49 citations
54. Comparison-Based Nearest Neighbor SearchPoster47 citations
55. Relativistic Monte CarloPoster47 citations
56. A Learning Theory of Ranking AggregationPoster46 citations
57. Regret Bounds for Transfer Learning in Bayesian OptimisationPoster44 citations
58. Structured adaptive and random spinners for fast machine learning computationsPoster42 citations
59. Learning with Feature Feedback: from Theory to PracticePoster41 citations
60. A New Class of Private Chi-Square Hypothesis TestsPoster40 citations
61. Distributed Adaptive Sampling for Kernel Matrix ApproximationPoster40 citations
62. Local Group Invariant Representations via Orbit EmbeddingsPoster40 citations
63. Online Nonnegative Matrix Factorization with General DivergencesPoster40 citations
64. A Framework for Optimal Matching for Causal InferencePoster39 citations
65. Linear Convergence of Stochastic Frank Wolfe VariantsPoster39 citations
66. Minimax-optimal semi-supervised regression on unknown manifoldsPoster39 citations
67. A Sub-Quadratic Exact Medoid AlgorithmPoster38 citations
68. Asymptotically exact inference in differentiable generative modelsPoster38 citations
69. Stochastic Difference of Convex Algorithm and its Application to Training Deep Boltzmann MachinesPoster37 citations
70. Trading off Rewards and Errors in Multi-Armed BanditsPoster35 citations
71. Complementary Sum Sampling for Likelihood Approximation in Large Scale ClassificationPoster34 citations
72. Quantifying the accuracy of approximate diffusions and Markov chainsPoster34 citations
73. Global Convergence of Non-Convex Gradient Descent for Computing Matrix SquarerootPoster33 citations
74. Online Optimization of Smoothed Piecewise Constant FunctionsPoster33 citations
75. Modal-set estimation with an application to clusteringPoster31 citations
76. Convergence Rate of Stochastic k-meansPoster30 citations
77. Information-theoretic limits of Bayesian network structure learningPoster30 citations
78. Communication-efficient Distributed Sparse Linear Discriminant AnalysisPoster29 citations
79. Encrypted Accelerated Least Squares RegressionPoster27 citations
80. Lipschitz Density-Ratios, Structured Data, and Data-driven TuningPoster27 citations
81. Near-optimal Bayesian Active Learning with Correlated and Noisy TestsPoster27 citations
82. CPSG-MCMC: Clustering-Based Preprocessing method for Stochastic Gradient MCMCPoster26 citations
83. Hit-and-Run for Sampling and Planning in Non-Convex SpacesPoster26 citations
84. Learning the Network Structure of Heterogeneous Data via Pairwise Exponential Markov Random FieldsPoster26 citations
85. Linking Micro Event History to Macro Prediction in Point Process ModelsPoster26 citations
86. Minimax Approach to Variable Fidelity Data InterpolationPoster26 citations
87. Tensor Decompositions via Two-Mode Higher-Order SVD (HOSVD)Poster26 citations
88. Distance Covariance AnalysisPoster25 citations
89. Minimax Gaussian Classification & ClusteringPoster24 citations
90. Removing Phase Transitions from Gibbs MeasuresPoster24 citations
91. Spatial Decompositions for Large Scale SVMsPoster24 citations
92. Anomaly Detection in Extreme Regions via Empirical MV-sets on the SpherePoster23 citations
93. Prediction Performance After Learning in Gaussian Process RegressionPoster23 citations
94. Tensor-Dictionary Learning with Deep Kruskal-Factor AnalysisPoster23 citations
95. Gradient Boosting on Stochastic Data StreamsPoster22 citations
96. Fast Classification with Binary PrototypesPoster21 citations
97. Horde of Bandits using Gaussian Markov Random FieldsPoster20 citations
98. Learning Theory for Conditional Risk MinimizationPoster20 citations
99. Belief Propagation in Conditional RBMs for Structured PredictionPoster19 citations
100. Sequential Multiple Hypothesis Testing with Type I Error ControlPoster19 citations
101. Co-Occurring Directions Sketching for Approximate Matrix MultiplyPoster18 citations
102. Generalized Pseudolikelihood Methods for Inverse Covariance EstimationPoster18 citations
103. Hierarchically-partitioned Gaussian Process ApproximationPoster18 citations
104. Active Positive Semidefinite Matrix Completion: Algorithms, Theory and ApplicationsPoster17 citations
105. Data Driven Resource Allocation for Distributed LearningPoster17 citations
106. Efficient Algorithm for Sparse Tensor-variate Gaussian Graphical Models via Gradient DescentPoster17 citations
107. Learning Graphical Games from Behavioral Data: Sufficient and Necessary ConditionsPoster17 citations
108. Random Consensus Robust PCAPoster17 citations
109. An Information-Theoretic Route from Generalization in Expectation to Generalization in ProbabilityPoster16 citations
110. Detecting Dependencies in Sparse, Multivariate Databases Using Probabilistic Programming and Non-parametric BayesPoster16 citations
111. Fast column generation for atomic norm regularizationPoster16 citations
112. Markov Chain Truncation for Doubly-Intractable InferencePoster16 citations
113. Robust and Efficient Computation of Eigenvectors in a Generalized Spectral Method for Constrained ClusteringPoster16 citations
114. Dynamic Collaborative Filtering With Compound Poisson FactorizationPoster15 citations
115. Large-Scale Data-Dependent Kernel ApproximationPoster14 citations
116. Sparse Accelerated Exponential WeightsPoster14 citations
117. Spectral Methods for Correlated Topic ModelsPoster14 citations
118. Learning Time Series Detection Models from Temporally Imprecise LabelsPoster13 citations
119. Online Learning and Blackwell Approachability with Partial Monitoring: Optimal Convergence RatesPoster13 citations
120. Tracking Objects with Higher Order Interactions via Delayed Column GenerationPoster13 citations
121. A Lower Bound on the Partition Function of Attractive Graphical Models in the Continuous CasePoster12 citations
122. Binary and Multi-Bit Coding for Stable Random ProjectionsPoster12 citations
123. Optimal Recovery of Tensor SlicesPoster12 citations
124. Scaling Submodular Maximization via Pruned Submodularity GraphsPoster12 citations
125. Unsupervised Sequential Sensor AcquisitionPoster12 citations
126. A Fast and Scalable Joint Estimator for Learning Multiple Related Sparse Gaussian Graphical ModelsPoster11 citations
127. A Maximum Matching Algorithm for Basis Selection in Spectral LearningPoster11 citations
128. Bayesian Hybrid Matrix Factorisation for Data IntegrationPoster11 citations
129. Learning Optimal InterventionsPoster11 citations
130. Identifying Groups of Strongly Correlated Variables through Smoothed Ordered Weighted $L_1$-normsPoster10 citations
131. Performance Bounds for Graphical Record LinkagePoster10 citations
132. Regression Uncertainty on the GrassmannianPoster10 citations
133. Compressed Least Squares Regression revisitedPoster9 citations
134. Conditions beyond treewidth for tightness of higher-order LP relaxationsPoster9 citations
135. Consistent and Efficient Nonparametric Different-Feature SelectionPoster9 citations
136. Lower Bounds on Active Learning for Graphical Model SelectionPoster9 citations
137. On the Troll-Trust Model for Edge Sign Prediction in Social NetworksPoster9 citations
138. Rank Aggregation and Prediction with Item FeaturesPoster9 citations
139. Rapid Mixing Swendsen-Wang Sampler for Stochastic Partitioned Attractive ModelsPoster9 citations
140. Clustering from Multiple Uncertain ExpertsPoster8 citations
141. Efficient Online Multiclass Prediction on Graphs via Surrogate LossesPoster8 citations
142. Efficient Rank Aggregation via Lehmer CodesPoster8 citations
143. Estimating Density Ridges by Direct Estimation of Density-Derivative-RatiosPoster8 citations
144. Gray-box Inference for Structured Gaussian Process ModelsPoster8 citations
145. Least-Squares Log-Density Gradient Clustering for Riemannian ManifoldsPoster8 citations
146. On the Interpretability of Conditional Probability Estimates in the Agnostic SettingPoster8 citations
147. Random projection design for scalable implicit smoothing of randomly observed stochastic processesPoster8 citations
148. Greedy Direction Method of Multiplier for MAP Inference of Large Output DomainPoster7 citations
149. Initialization and Coordinate Optimization for Multi-way MatchingPoster7 citations
150. Optimistic Planning for the Stochastic Knapsack ProblemPoster7 citations
151. Scalable Variational Inference for Super Resolution MicroscopyPoster7 citations
152. Sparse Randomized Partition Trees for Nearest Neighbor SearchPoster7 citations
153. A Stochastic Nonconvex Splitting Method for Symmetric Nonnegative Matrix FactorizationPoster6 citations
154. Information Projection and Approximate Inference for Structured Sparse VariablesPoster5 citations
155. Signal-based Bayesian Seismic MonitoringPoster5 citations
156. Attributing HacksPoster4 citations
157. Local Perturb-and-MAP for Structured PredictionPoster4 citations
158. Sequential Graph Matching with Sequential Monte CarloPoster4 citations
159. Combinatorial Topic Models using Small-Variance AsymptoticsPoster3 citations
160. Distribution of Gaussian Process Arc LengthsPoster3 citations
161. Frequency Domain Predictive Modelling with Aggregated DataPoster3 citations
162. Learning Nonparametric Forest Graphical Models with Prior InformationPoster2 citations
163. Non-Count Symmetries in Boolean & Multi-Valued Prob. Graphical ModelsPoster2 citations
164. Robust Causal Estimation in the Large-Sample Limit without Strict FaithfulnessPoster2 citations
165. Scalable Convex Multiple Sequence Alignment via Entropy-Regularized Dual DecompositionPoster1 citations
166. Annular Augmentation SamplingPoster
167. Minimax Density Estimation for Growing DimensionPoster

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