AISTATS 2018 Accepted Papers

The full list of 216 papers accepted at AISTATS 2018 (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. A Fast Algorithm for Separated Sparsity via Perturbed LagrangiansPoster
2. A Generic Approach for Escaping Saddle pointsPoster
3. A Nonconvex Proximal Splitting Algorithm under Moreau-Yosida RegularizationPoster
4. A Provable Algorithm for Learning Interpretable Scoring SystemsPoster
5. A Simple Analysis for Exp-concave Empirical Minimization with Arbitrary Convex RegularizerPoster
6. A Stochastic Differential Equation Framework for Guiding Online User Activities in Closed LoopPoster
7. A Unified Dynamic Approach to Sparse Model SelectionPoster
8. A Unified Framework for Nonconvex Low-Rank plus Sparse Matrix RecoveryPoster
9. A fully adaptive algorithm for pure exploration in linear banditsPoster
10. Accelerated Stochastic Mirror Descent: From Continuous-time Dynamics to Discrete-time AlgorithmsPoster
11. Accelerated Stochastic Power IterationPoster
12. Achieving the time of 1-NN, but the accuracy of k-NNPoster
13. Actor-Critic Fictitious Play in Simultaneous Move Multistage GamesPoster
14. AdaGeo: Adaptive Geometric Learning for Optimization and SamplingPoster
15. Adaptive Sampling for Coarse RankingPoster
16. Adaptive balancing of gradient and update computation times using global geometry and approximate subproblemsPoster
17. An Analysis of Categorical Distributional Reinforcement LearningPoster
18. An Optimization Approach to Learning Falling Rule ListsPoster
19. Approximate Bayesian Computation with Kullback-Leibler Divergence as Data DiscrepancyPoster
20. Approximate Ranking from Pairwise ComparisonsPoster
21. Asynchronous Doubly Stochastic Group Regularized LearningPoster
22. Batch-Expansion Training: An Efficient Optimization FrameworkPoster
23. Batched Large-scale Bayesian Optimization in High-dimensional SpacesPoster
24. Bayesian Approaches to Distribution RegressionPoster
25. Bayesian Multi-label Learning with Sparse Features and Labels, and Label Co-occurrencesPoster
26. Bayesian Nonparametric Poisson-Process Allocation for Time-Sequence ModelingPoster
27. Bayesian Structure Learning for Dynamic Brain ConnectivityPoster
28. Beating Monte Carlo Integration: a Nonasymptotic Study of Kernel Smoothing MethodsPoster
29. Benefits from Superposed Hawkes ProcessesPoster
30. Best arm identification in multi-armed bandits with delayed feedbackPoster
31. Boosting Variational Inference: an Optimization PerspectivePoster
32. Bootstrapping EM via Power EM and Convergence in the Naive Bayes ModelPoster
33. Can clustering scale sublinearly with its clusters? A variational EM acceleration of GMMs and k-meansPoster
34. Catalyst for Gradient-based Nonconvex OptimizationPoster
35. Cause-Effect Inference by Comparing Regression ErrorsPoster
36. Cheap Checking for Cloud Computing: Statistical Analysis via Annotated Data StreamsPoster
37. Combinatorial Penalties: Which structures are preserved by convex relaxations?Poster
38. Combinatorial Preconditioners for Proximal Algorithms on GraphsPoster
39. Combinatorial Semi-Bandits with KnapsacksPoster
40. Communication-Avoiding Optimization Methods for Distributed Massive-Scale Sparse Inverse Covariance EstimationPoster
41. Community Detection in Hypergraphs: Optimal Statistical Limit and Efficient AlgorithmsPoster
42. Comparison Based Learning from Weak OraclesPoster
43. Competing with Automata-based Expert SequencesPoster
44. Conditional Gradient Method for Stochastic Submodular Maximization: Closing the GapPoster
45. Conditional independence testing based on a nearest-neighbor estimator of conditional mutual informationPoster
46. Contextual Bandits with Stochastic ExpertsPoster
47. Convergence diagnostics for stochastic gradient descent with constant learning ratePoster
48. Convergence of Value Aggregation for Imitation LearningPoster
49. Convex Optimization over Intersection of Simple Sets: improved Convergence Rate Guarantees via an Exact Penalty ApproachPoster
50. Crowdclustering with Partition LabelsPoster
51. Data-Efficient Reinforcement Learning with Probabilistic Model Predictive ControlPoster
52. Delayed Sampling and Automatic Rao-Blackwellization of Probabilistic ProgramsPoster
53. Derivative Free Optimization Via Repeated ClassificationPoster
54. Differentially Private Regression with Gaussian ProcessesPoster
55. Dimensionality Reduced $\ell^{0}$-Sparse Subspace ClusteringPoster
56. Direct Learning to Rank And RerankPoster
57. Discriminative Learning of Prediction IntervalsPoster
58. Dropout as a Low-Rank Regularizer for Matrix FactorizationPoster
59. Efficient Bandit Combinatorial Optimization Algorithm with Zero-suppressed Binary Decision DiagramsPoster
60. Efficient Bayesian Methods for Counting Processes in Partially Observable EnvironmentsPoster
61. Efficient Weight Learning in High-Dimensional Untied MLNsPoster
62. Efficient and principled score estimation with Nyström kernel exponential familiesPoster
63. Exploiting Strategy-Space Diversity for Batch Bayesian OptimizationPoster
64. FLAG n’ FLARE: Fast Linearly-Coupled Adaptive Gradient MethodsPoster
65. Factor Analysis on a GraphPoster
66. Factorial HMMs with Collapsed Gibbs Sampling for Optimizing Long-term HIV TherapyPoster
67. Factorized Recurrent Neural Architectures for Longer Range DependencePoster
68. Fast Threshold Tests for Detecting DiscriminationPoster
69. Fast and Scalable Learning of Sparse Changes in High-Dimensional Gaussian Graphical Model StructurePoster
70. Fast generalization error bound of deep learning from a kernel perspectivePoster
71. Few-shot Generative Modelling with Generative Matching NetworksPoster
72. Finding Global Optima in Nonconvex Stochastic Semidefinite Optimization with Variance ReductionPoster
73. Frank-Wolfe Splitting via Augmented Lagrangian MethodPoster
74. Gauged Mini-Bucket Elimination for Approximate InferencePoster
75. Gaussian Process Subset Scanning for Anomalous Pattern Detection in Non-iid DataPoster
76. Generalized Binary Search For Split-Neighborly ProblemsPoster
77. Generalized Concomitant Multi-Task Lasso for Sparse Multimodal RegressionPoster
78. Gradient Diversity: a Key Ingredient for Scalable Distributed LearningPoster
79. Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative ModelsPoster
80. Graphical Models for Non-Negative Data Using Generalized Score MatchingPoster
81. Group Invariance Principles for Causal Generative ModelsPoster
82. Growth-Optimal Portfolio Selection under CVaR ConstraintsPoster
83. Guaranteed Sufficient Decrease for Stochastic Variance Reduced Gradient OptimizationPoster
84. HONES: A Fast and Tuning-free Homotopy Method For Online Newton StepPoster
85. High-Dimensional Bayesian Optimization via Additive Models with Overlapping GroupsPoster
86. Human Interaction with Recommendation SystemsPoster
87. IHT dies hard: Provable accelerated Iterative Hard ThresholdingPoster
88. Independently Interpretable Lasso: A New Regularizer for Sparse Regression with Uncorrelated VariablesPoster
89. Inference in Sparse Graphs with Pairwise Measurements and Side InformationPoster
90. Integral Transforms from Finite Data: An Application of Gaussian Process Regression to Fourier AnalysisPoster
91. Intersection-Validation: A Method for Evaluating Structure Learning without Ground TruthPoster
92. Iterative Spectral Method for Alternative ClusteringPoster
93. Iterative Supervised Principal ComponentsPoster
94. Kernel Conditional Exponential FamilyPoster
95. Labeled Graph Clustering via Projected Gradient DescentPoster
96. Large Scale Empirical Risk Minimization via Truncated Adaptive Newton MethodPoster
97. Layerwise Systematic Scan: Deep Boltzmann Machines and BeyondPoster
98. Learning Determinantal Point Processes in Sublinear TimePoster
99. Learning Generative Models with Sinkhorn DivergencesPoster
100. Learning Hidden Quantum Markov ModelsPoster
101. Learning Priors for InvariancePoster
102. Learning Sparse Polymatrix Games in Polynomial Time and Sample ComplexityPoster
103. Learning Structural Weight Uncertainty for Sequential Decision-MakingPoster
104. Learning linear structural equation models in polynomial time and sample complexityPoster
105. Learning to Round for Discrete Labeling ProblemsPoster
106. Learning with Complex Loss Functions and ConstraintsPoster
107. Linear Stochastic Approximation: How Far Does Constant Step-Size and Iterate Averaging Go?Poster
108. Making Tree Ensembles Interpretable: A Bayesian Model Selection ApproachPoster
109. Matrix completability analysis via graph k-connectivityPoster
110. Matrix-normal models for fMRI analysisPoster
111. Medoids in Almost-Linear Time via Multi-Armed BanditsPoster
112. Metrics for Deep Generative ModelsPoster
113. Minimax Reconstruction Risk of Convolutional Sparse Dictionary LearningPoster
114. Minimax-Optimal Privacy-Preserving Sparse PCA in Distributed SystemsPoster
115. Mixed Membership Word Embeddings for Computational Social SciencePoster
116. Multi-objective Contextual Bandit Problem with Similarity InformationPoster
117. Multi-scale Nystrom MethodPoster
118. Multi-view Metric Learning in Vector-valued Kernel SpacesPoster
119. Multimodal Prediction and Personalization of Photo Edits with Deep Generative ModelsPoster
120. Multiphase MCMC Sampling for Parameter Inference in Nonlinear Ordinary Differential EquationsPoster
121. Natural Gradients in Practice: Non-Conjugate Variational Inference in Gaussian Process ModelsPoster
122. Near-Optimal Machine Teaching via Explanatory Teaching SetsPoster
123. Nearly second-order optimality of online joint detection and estimation via one-sample update schemesPoster
124. Nested CRP with Hawkes-Gaussian ProcessesPoster
125. Non-parametric estimation of Jensen-Shannon Divergence in Generative Adversarial Network trainingPoster
126. Nonlinear Structured Signal Estimation in High Dimensions via Iterative Hard ThresholdingPoster
127. Nonlinear Weighted Finite AutomataPoster
128. Nonparametric Bayesian sparse graph linear dynamical systemsPoster
129. Nonparametric Preference CompletionPoster
130. Nonparametric Sharpe Ratio Function Estimation in Heteroscedastic Regression Models via Convex OptimizationPoster
131. On Statistical Optimality of Variational BayesPoster
132. On Truly Block Eigensolvers via Riemannian OptimizationPoster
133. On denoising modulo 1 samples of a functionPoster
134. On how complexity affects the stability of a predictorPoster
135. On the Statistical Efficiency of Compositional Nonparametric PredictionPoster
136. On the challenges of learning with inference networks on sparse, high-dimensional dataPoster
137. One-shot Coresets: The Case of k-ClusteringPoster
138. Online Boosting Algorithms for Multi-label RankingPoster
139. Online Continuous Submodular MaximizationPoster
140. Online Ensemble Multi-kernel Learning Adaptive to Non-stationary and Adversarial EnvironmentsPoster
141. Online Learning with Non-Convex Losses and Non-Stationary RegretPoster
142. Online Regression with Partial Information: Generalization and Linear ProjectionPoster
143. Optimal Cooperative InferencePoster
144. Optimal Submodular Extensions for Marginal EstimationPoster
145. Optimality of Approximate Inference Algorithms on Stable InstancesPoster
146. Outlier Detection and Robust Estimation in Nonparametric RegressionPoster
147. Parallel and Distributed MCMC via Shepherding DistributionsPoster
148. Parallelised Bayesian Optimisation via Thompson SamplingPoster
149. Personalized and Private Peer-to-Peer Machine LearningPoster
150. Plug-in Estimators for Conditional Expectations and ProbabilitiesPoster
151. Policy Evaluation and Optimization with Continuous TreatmentsPoster
152. Post Selection Inference with KernelsPoster
153. Practical Bayesian optimization in the presence of outliersPoster
154. Probability–Revealing SamplesPoster
155. Product Kernel Interpolation for Scalable Gaussian ProcessesPoster
156. Provable Estimation of the Number of Blocks in Block ModelsPoster
157. Proximity Variational InferencePoster
158. Quotient Normalized Maximum Likelihood Criterion for Learning Bayesian Network StructuresPoster
159. Random Subspace with Trees for Feature Selection Under Memory ConstraintsPoster
160. Random Warping Series: A Random Features Method for Time-Series EmbeddingPoster
161. Reducing Crowdsourcing to Graphon Estimation, StatisticallyPoster
162. Regional Multi-Armed BanditsPoster
163. Reparameterizing the Birkhoff Polytope for Variational Permutation InferencePoster
164. Riemannian stochastic quasi-Newton algorithm with variance reduction and its convergence analysisPoster
165. Robust Active Label CorrectionPoster
166. Robust Locally-Linear Controllable EmbeddingPoster
167. Robust Maximization of Non-Submodular ObjectivesPoster
168. Robust Vertex Enumeration for Convex Hulls in High DimensionsPoster
169. Robustness of classifiers to uniform $\ell_p$ and Gaussian noisePoster
170. SDCA-Powered Inexact Dual Augmented Lagrangian Method for Fast CRF LearningPoster
171. Scalable Gaussian Processes with Billions of Inducing Inputs via Tensor Train DecompositionPoster
172. Scalable Generalized Dynamic Topic ModelsPoster
173. Scalable Hash-Based Estimation of Divergence MeasuresPoster
174. Scaling up the Automatic Statistician: Scalable Structure Discovery using Gaussian ProcessesPoster
175. Semi-Supervised Learning with Competitive Infection ModelsPoster
176. Semi-Supervised Prediction-Constrained Topic ModelsPoster
177. Sketching for Kronecker Product Regression and P-splinesPoster
178. Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGDPoster
179. Smooth and Sparse Optimal TransportPoster
180. Solving lp-norm regularization with tensor kernelsPoster
181. Sparse Linear Isotonic ModelsPoster
182. Spectral Algorithms for Computing Fair Support Vector MachinesPoster
183. Statistical Sparse Online Regression: A Diffusion Approximation PerspectivePoster
184. Statistically Efficient Estimation for Non-Smooth Probability DensitiesPoster
185. Stochastic Multi-armed Bandits in Constant SpacePoster
186. Stochastic Three-Composite Convex Minimization with a Linear OperatorPoster
187. Stochastic Zeroth-order Optimization in High DimensionsPoster
188. Stochastic algorithms for entropy-regularized optimal transport problemsPoster
189. Structured Factored Inference for Probabilistic ProgrammingPoster
190. Structured Optimal TransportPoster
191. Submodularity on Hypergraphs: From Sets to SequencesPoster
192. Subsampling for Ridge Regression via Regularized Volume SamplingPoster
193. Sum-Product-Quotient NetworksPoster
194. Symmetric Variational Autoencoder and Connections to Adversarial LearningPoster
195. Teacher Improves Learning by Selecting a Training SubsetPoster
196. Temporally-Reweighted Chinese Restaurant Process Mixtures for Clustering, Imputing, and Forecasting Multivariate Time SeriesPoster
197. Tensor Regression Meets Gaussian ProcessesPoster
198. The Binary Space Partitioning-Tree ProcessPoster
199. The Geometry of Random FeaturesPoster
200. The Power Mean Laplacian for Multilayer Graph ClusteringPoster
201. The emergence of spectral universality in deep networksPoster
202. Topic Compositional Neural Language ModelPoster
203. Towards Memory-Friendly Deterministic Incremental Gradient MethodPoster
204. Towards Provable Learning of Polynomial Neural Networks Using Low-Rank Matrix EstimationPoster
205. Tracking the gradients using the Hessian: A new look at variance reducing stochastic methodsPoster
206. Transfer Learning on fMRI DatasetsPoster
207. Tree-based Bayesian Mixture Model for Competing RisksPoster
208. Turing: A Language for Flexible Probabilistic InferencePoster
209. VAE with a VampPriorPoster
210. Variational Inference based on Robust DivergencesPoster
211. Variational Rejection SamplingPoster
212. Variational Sequential Monte CarloPoster
213. Variational inference for the multi-armed contextual banditPoster
214. Weighted Tensor Decomposition for Learning Latent Variables with Partial DataPoster
215. Why Adaptively Collected Data Have Negative Bias and How to Correct for ItPoster
216. Zeroth-Order Online Alternating Direction Method of Multipliers: Convergence Analysis and ApplicationsPoster

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