AISTATS 2016 Accepted Papers

The full list of 164 papers accepted at AISTATS 2016 (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. Deep Kernel LearningPoster1,181 citations
2. Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and TreePoster868 citations
3. Non-stochastic Best Arm Identification and Hyperparameter OptimizationPoster825 citations
4. How to Learn a Graph from Smooth SignalsPoster614 citations
5. Batch Bayesian Optimization via Local PenalizationPoster476 citations
6. A Linearly-Convergent Stochastic L-BFGS AlgorithmPoster340 citations
7. Breaking Sticks and Ambiguities with Adaptive Skip-gramPoster236 citations
8. Controlling Bias in Adaptive Data Analysis Using Information TheoryPoster226 citations
9. Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data AugmentationPoster193 citations
10. On Sparse Variational Methods and the Kullback-Leibler Divergence between Stochastic ProcessesPoster173 citations
11. Fast Dictionary Learning with a Smoothed Wasserstein LossPoster171 citations
12. Non-Stationary Gaussian Process Regression with Hamiltonian Monte CarloPoster154 citations
13. GLASSES: Relieving The Myopia Of Bayesian OptimisationPoster153 citations
14. Quantization based Fast Inner Product SearchPoster135 citations
15. Time-Varying Gaussian Process Bandit OptimizationPoster121 citations
16. Bridging the Gap between Stochastic Gradient MCMC and Stochastic OptimizationPoster118 citations
17. Back to the Future: Radial Basis Function Networks RevisitedPoster117 citations
18. K2-ABC: Approximate Bayesian Computation with Kernel EmbeddingsPoster117 citations
19. Early Stopping as Nonparametric Variational InferencePoster116 citations
20. PAC-Bayesian Bounds based on the Rényi DivergencePoster114 citations
21. Provable Tensor Methods for Learning Mixtures of Generalized Linear ModelsPoster112 citations
22. Tensor vs. Matrix Methods: Robust Tensor Decomposition under Block Sparse PerturbationsPoster106 citations
23. High Dimensional Bayesian Optimization via Restricted Projection Pursuit ModelsPoster103 citations
24. Robust Covariate Shift RegressionPoster102 citations
25. Strong Coresets for Hard and Soft Bregman Clustering with Applications to Exponential Family MixturesPoster102 citations
26. Top Arm Identification in Multi-Armed Bandits with Batch Arm PullsPoster99 citations
27. Optimization as Estimation with Gaussian Processes in Bandit SettingsPoster95 citations
28. Ordered Weighted L1 Regularized Regression with Strongly Correlated Covariates: Theoretical AspectsPoster95 citations
29. Unbounded Bayesian Optimization via RegularizationPoster92 citations
30. Chained Gaussian ProcessesPoster90 citations
31. Distributed Multi-Task LearningPoster90 citations
32. Bayesian Nonparametric Kernel-LearningPoster89 citations
33. Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and DynamicsPoster89 citations
34. Low-Rank and Sparse Structure Pursuit via Alternating MinimizationPoster86 citations
35. Provable Bayesian Inference via Particle Mirror DescentPoster84 citations
36. Global Convergence of a Grassmannian Gradient Descent Algorithm for Subspace EstimationPoster83 citations
37. A PAC RL Algorithm for Episodic POMDPsPoster78 citations
38. Towards Stability and Optimality in Stochastic Gradient DescentPoster77 citations
39. Variational Gaussian Copula InferencePoster75 citations
40. Random Forest for the Contextual Bandit ProblemPoster72 citations
41. AdaDelay: Delay Adaptive Distributed Stochastic OptimizationPoster68 citations
42. Computationally Efficient Bayesian Learning of Gaussian Process State Space ModelsPoster68 citations
43. Large Scale Distributed Semi-Supervised Learning Using Streaming ApproximationPoster68 citations
44. Mondrian Forests for Large-Scale Regression when Uncertainty MattersPoster67 citations
45. Multi-Level Cause-Effect SystemsPoster67 citations
46. Efficient Sampling for k-Determinantal Point ProcessesPoster66 citations
47. Scalable Gaussian Process Classification via Expectation PropagationPoster65 citations
48. Accelerating Online Convex Optimization via Adaptive PredictionPoster64 citations
49. Graph Sparsification Approaches for Laplacian SmoothingPoster64 citations
50. Simple and Scalable Constrained Clustering: a Generalized Spectral MethodPoster64 citations
51. Online and Distributed Bayesian Moment Matching for Parameter Learning in Sum-Product NetworksPoster63 citations
52. Scalable MCMC for Mixed Membership Stochastic BlockmodelsPoster63 citations
53. Variational TemperingPoster62 citations
54. Pareto Front Identification from Stochastic Bandit FeedbackPoster61 citations
55. Unsupervised Ensemble Learning with Dependent ClassifiersPoster58 citations
56. A Deep Generative Deconvolutional Image ModelPoster55 citations
57. Streaming Kernel Principal Component AnalysisPoster54 citations
58. Online (and Offline) Robust PCA: Novel Algorithms and Performance GuaranteesPoster51 citations
59. Sparse Representation of Multivariate Extremes with Applications to Anomaly RankingPoster50 citations
60. Revealing Graph Bandits for Maximizing Local InfluencePoster49 citations
61. DUAL-LOCO: Distributing Statistical Estimation Using Random ProjectionsPoster48 citations
62. Improved Learning Complexity in Combinatorial Pure Exploration BanditsPoster48 citations
63. Pseudo-Marginal Slice SamplingPoster48 citations
64. Tractable and Scalable Schatten Quasi-Norm Approximations for Rank MinimizationPoster47 citations
65. Graph Connectivity in Noisy Sparse Subspace ClusteringPoster45 citations
66. C3: Lightweight Incrementalized MCMC for Probabilistic Programs using Continuations and Callsite CachingPoster43 citations
67. NYTRO: When Subsampling Meets Early StoppingPoster43 citations
68. Online Learning with Noisy Side ObservationsPoster43 citations
69. Universal Models of Multivariate Temporal Point ProcessesPoster42 citations
70. On Convergence of Model Parallel Proximal Gradient Algorithm for Stale Synchronous Parallel SystemPoster40 citations
71. Rivalry of Two Families of Algorithms for Memory-Restricted Streaming PCAPoster40 citations
72. Precision Matrix Estimation in High Dimensional Gaussian Graphical Models with Faster RatesPoster39 citations
73. Scalable Gaussian Processes for Characterizing Multidimensional Change SurfacesPoster39 citations
74. Accelerated Stochastic Gradient Descent for Minimizing Finite SumsPoster38 citations
75. Stochastic Variational Inference for the HDP-HMMPoster38 citations
76. Supervised Neighborhoods for Distributed Nonparametric RegressionPoster38 citations
77. Randomization and The Pernicious Effects of Limited Budgets on Auction ExperimentsPoster37 citations
78. Learning Probabilistic Submodular Diversity Models Via Noise Contrastive EstimationPoster35 citations
79. Private Causal InferencePoster35 citations
80. Unsupervised Feature Selection by Preserving Stochastic NeighborsPoster35 citations
81. Maximum Likelihood for Variance Estimation in High-Dimensional Linear ModelsPoster34 citations
82. Active Learning Algorithms for Graphical Model SelectionPoster32 citations
83. On Lloyd’s Algorithm: New Theoretical Insights for Clustering in PracticePoster32 citations
84. A Robust-Equitable Copula Dependence Measure for Feature SelectionPoster31 citations
85. Black-Box Policy Search with Probabilistic ProgramsPoster31 citations
86. Control Functionals for Quasi-Monte Carlo IntegrationPoster31 citations
87. Efficient Bregman Projections onto the Permutahedron and Related PolytopesPoster31 citations
88. Scalable and Sound Low-Rank Tensor LearningPoster31 citations
89. Sequential Inference for Deep Gaussian ProcessPoster31 citations
90. Exponential Stochastic Cellular Automata for Massively Parallel InferencePoster30 citations
91. Stochastic Neural Networks with Monotonic Activation FunctionsPoster30 citations
92. Learning Relationships between Data Obtained IndependentlyPoster28 citations
93. Nearly Optimal Classification for SemimetricsPoster28 citations
94. Non-negative Matrix Factorization for Discrete Data with Hierarchical Side-InformationPoster28 citations
95. Nonparametric Budgeted Stochastic Gradient DescentPoster27 citations
96. Consistently Estimating Markov Chains with Noisy Aggregate DataPoster26 citations
97. Learning Structured Low-Rank Representation via Matrix FactorizationPoster26 citations
98. Optimal Statistical and Computational Rates for One Bit Matrix CompletionPoster26 citations
99. Tightness of LP Relaxations for Almost Balanced ModelsPoster26 citations
100. On Searching for Generalized Instrumental VariablesPoster25 citations
101. Communication Efficient Distributed Agnostic BoostingPoster24 citations
102. Discriminative Structure Learning of Arithmetic CircuitsPoster24 citations
103. On the Use of Non-Stationary Strategies for Solving Two-Player Zero-Sum Markov GamesPoster24 citations
104. Unwrapping ADMM: Efficient Distributed Computing via Transpose ReductionPoster24 citations
105. Sketching, Embedding and Dimensionality Reduction in Information Theoretic SpacesPoster23 citations
106. Multiresolution Matrix CompressionPoster22 citations
107. New Resistance Distances with Global Information on Large GraphsPoster22 citations
108. Cut Pursuit: Fast Algorithms to Learn Piecewise Constant FunctionsPoster21 citations
109. Latent Point Process AllocationPoster21 citations
110. Non-Gaussian Component Analysis with Log-Density Gradient EstimationPoster21 citations
111. Probability Inequalities for Kernel Embeddings in Sampling without ReplacementPoster21 citations
112. Fast Convergence of Online Pairwise Learning AlgorithmsPoster20 citations
113. A Column Generation Bound Minimization Approach with PAC-Bayesian Generalization GuaranteesPoster19 citations
114. A Fast and Reliable Policy Improvement AlgorithmPoster19 citations
115. Enumerating Equivalence Classes of Bayesian Networks using EC GraphsPoster19 citations
116. Globally Sparse Probabilistic PCAPoster19 citations
117. One Scan 1-Bit Compressed SensingPoster19 citations
118. (Bandit) Convex Optimization with Biased Noisy Gradient OraclesPoster18 citations
119. Approximate Inference Using DC Programming For Collective Graphical ModelsPoster18 citations
120. Inference for High-dimensional Exponential Family Graphical ModelsPoster18 citations
121. Probabilistic Approximate Least-SquaresPoster18 citations
122. Bethe Learning of Graphical Models via MAP DecodingPoster17 citations
123. Large-Scale Optimization Algorithms for Sparse Conditional Gaussian Graphical ModelsPoster17 citations
124. Improper Deep KernelsPoster16 citations
125. The Nonparametric Kernel Bayes SmootherPoster16 citations
126. Learning Sigmoid Belief Networks via Monte Carlo Expectation MaximizationPoster15 citations
127. No Regret Bound for Extreme BanditsPoster15 citations
128. A Convex Surrogate Operator for General Non-Modular Loss FunctionsPoster13 citations
129. Model-based Co-clustering for High Dimensional Sparse DataPoster13 citations
130. Bayesian Generalised Ensemble Markov Chain Monte CarloPoster12 citations
131. Learning Sparse Additive Models with Interactions in High DimensionsPoster12 citations
132. Bipartite Correlation Clustering: Maximizing AgreementsPoster11 citations
133. Clamping Improves TRW and Mean Field ApproximationsPoster11 citations
134. Fitting Spectral Decay with the k-Support NormPoster11 citations
135. Parallel Markov Chain Monte Carlo via Spectral ClusteringPoster11 citations
136. Scalable Exemplar Clustering and Facility Location via Augmented Block Coordinate Descent with Column GenerationPoster11 citations
137. Topic-Based Embeddings for Learning from Large Knowledge GraphsPoster11 citations
138. An Improved Convergence Analysis of Cyclic Block Coordinate Descent-type Methods for Strongly Convex MinimizationPoster10 citations
139. Survey Propagation beyond Constraint Satisfaction ProblemsPoster10 citations
140. Scalable geometric density estimationPoster9 citations
141. Bayesian Markov Blanket EstimationPoster8 citations
142. Fast Saddle-Point Algorithm for Generalized Dantzig Selector and FDR Control with Ordered L1-NormPoster8 citations
143. Fast and Scalable Structural SVM with Slack RescalingPoster8 citations
144. Geometry Aware Mappings for High Dimensional Sparse FactorsPoster8 citations
145. Low-Rank Approximation of Weighted Tree AutomataPoster8 citations
146. A Fixed-Point Operator for Inference in Variational Bayesian Latent Gaussian ModelsPoster7 citations
147. CRAFT: ClusteR-specific Assorted Feature selecTionPoster7 citations
148. Loss Bounds and Time Complexity for Speed PriorsPoster7 citations
149. Spectral M-estimation with Applications to Hidden Markov ModelsPoster7 citations
150. Tight Variational Bounds via Random Projections and I-ProjectionsPoster7 citations
151. NuC-MKL: A Convex Approach to Non Linear Multiple Kernel LearningPoster6 citations
152. Online Learning to Rank with Feedback at the TopPoster6 citations
153. Score Permutation Based Finite Sample Inference for Generalized AutoRegressive Conditional Heteroskedasticity (GARCH) ModelsPoster6 citations
154. A Lasso-based Sparse Knowledge Gradient Policy for Sequential Optimal LearningPoster5 citations
155. Determinantal Regularization for Ensemble Variable SelectionPoster5 citations
156. Limits on Sparse Support Recovery via Linear Sketching with Random Expander MatricesPoster3 citations
157. Online Relative Entropy Policy Search using Reproducing Kernel Hilbert Space EmbeddingsPoster3 citations
158. Convex Block-sparse Linear Regression with Expanders – ProvablyPoster2 citations
159. Generalized Ideal Parent (GIP): Discovering non-Gaussian Hidden VariablesPoster2 citations
160. Relationship between PreTraining and Maximum Likelihood Estimation in Deep Boltzmann MachinesPoster2 citations
161. Semi-Supervised Learning with Adaptive Spectral TransformPoster2 citations
162. Bayes-Optimal Effort Allocation in Crowdsourcing: Bounds and Index PoliciesPoster1 citations
163. On the Reducibility of Submodular FunctionsPoster1 citations
164. Parallel Majorization Minimization with Dynamically Restricted Domains for Nonconvex OptimizationPoster

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