AISTATS 2020 Accepted Papers

The full list of 422 papers accepted at AISTATS 2020 (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. How To Backdoor Federated LearningPoster2,644 citations
2. FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and QuantizationPoster1,017 citations
3. Variational Autoencoders and Nonlinear ICA: A Unifying FrameworkPoster708 citations
4. Tighter Theory for Local SGD on Identical and Heterogeneous DataPoster539 citations
5. Optimizing Millions of Hyperparameters by Implicit DifferentiationPoster508 citations
6. Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural NetworksPoster453 citations
7. Orthogonal Gradient Descent for Continual LearningPoster448 citations
8. Feature relevance quantification in explainable AI: A causal problemPoster429 citations
9. Model-Agnostic Counterfactual Explanations for Consequential DecisionsPoster418 citations
10. Identifying and Correcting Label Bias in Machine LearningPoster417 citations
11. A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point ApproachPoster405 citations
12. Scalable Gradients for Stochastic Differential EquationsPoster384 citations
13. GP-VAE: Deep Probabilistic Time Series ImputationPoster359 citations
14. Learning Sparse Nonparametric DAGsPoster343 citations
15. Formal Limitations on the Measurement of Mutual InformationPoster331 citations
16. Explaining the Explainer: A First Theoretical Analysis of LIMEPoster310 citations
17. Permutation Invariant Graph Generation via Score-Based Generative ModelingPoster298 citations
18. On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning AlgorithmsPoster287 citations
19. Uncertainty in Neural Networks: Approximately Bayesian EnsemblingPoster281 citations
20. DYNOTEARS: Structure Learning from Time-Series DataPoster251 citations
21. PersLay: A Neural Network Layer for Persistence Diagrams and New Graph Topological SignaturesPoster242 citations
22. Deep Active Learning: Unified and Principled Method for Query and TrainingPoster205 citations
23. Beyond exploding and vanishing gradients: analysing RNN training using attractors and smoothnessPoster192 citations
24. A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate DescentPoster190 citations
25. Optimization Methods for Interpretable Differentiable Decision Trees Applied to Reinforcement LearningPoster172 citations
26. ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable RecommendationsPoster169 citations
27. Sample Complexity of Reinforcement Learning using Linearly Combined Model EnsemblesPoster169 citations
28. Frequentist Regret Bounds for Randomized Least-Squares Value IterationPoster161 citations
29. Randomized Exploration in Generalized Linear BanditsPoster138 citations
30. Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance ReductionPoster136 citations
31. RelatIF: Identifying Explanatory Training Samples via Relative InfluencePoster133 citations
32. Computing Tight Differential Privacy Guarantees Using FFTPoster131 citations
33. Hypothesis Testing Interpretations and Renyi Differential PrivacyPoster131 citations
34. Federated Heavy Hitters Discovery with Differential PrivacyPoster129 citations
35. Competing Bandits in Matching MarketsPoster124 citations
36. Non-Parametric Calibration for ClassificationPoster123 citations
37. A Topology Layer for Machine LearningPoster121 citations
38. ASAP: Architecture Search, Anneal and PrunePoster121 citations
39. Learning Overlapping Representations for the Estimation of Individualized Treatment EffectsPoster121 citations
40. A Tight and Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Differentiable GamesPoster117 citations
41. Equalized odds postprocessing under imperfect group informationPoster112 citations
42. A Simple Approach for Non-stationary Linear BanditsPoster109 citations
43. Learning with minibatch Wasserstein : asymptotic and gradient propertiesPoster107 citations
44. Adaptive, Distribution-Free Prediction Intervals for Deep NetworksPoster106 citations
45. Distributionally Robust Bayesian OptimizationPoster106 citations
46. Persistence Enhanced Graph Neural NetworkPoster101 citations
47. Revisiting Stochastic ExtragradientPoster101 citations
48. Optimal Algorithms for Multiplayer Multi-Armed BanditsPoster100 citations
49. Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement LearningPoster94 citations
50. Fairness Evaluation in Presence of Biased Noisy LabelsPoster92 citations
51. Flexible distribution-free conditional predictive bands using density estimatorsPoster91 citations
52. Fully Decentralized Joint Learning of Personalized Models and Collaboration GraphsPoster90 citations
53. Solving Discounted Stochastic Two-Player Games with Near-Optimal Time and Sample ComplexityPoster88 citations
54. Fair Correlation ClusteringPoster87 citations
55. Graph Coarsening with Preserved Spectral PropertiesPoster87 citations
56. A Unified Stochastic Gradient Approach to Designing Bayesian-Optimal ExperimentsPoster85 citations
57. Fixed-confidence guarantees for Bayesian best-arm identificationPoster83 citations
58. High Dimensional Robust Sparse RegressionPoster83 citations
59. Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk MinimizationPoster83 citations
60. A Deep Generative Model for Fragment-Based Molecule GenerationPoster82 citations
61. A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among PlayersPoster81 citations
62. One Sample Stochastic Frank-WolfePoster81 citations
63. Adaptive Exploration in Linear Contextual BanditPoster80 citations
64. Tight Analysis of Privacy and Utility Tradeoff in Approximate Differential PrivacyPoster79 citations
65. Variational Integrator Networks for Physically Structured EmbeddingsPoster79 citations
66. Asymptotic Analysis of Sampling Estimators for Randomized Numerical Linear Algebra AlgorithmsPoster78 citations
67. Linearly Convergent Frank-Wolfe with Backtracking Line-SearchPoster78 citations
68. Causal Bayesian OptimizationPoster76 citations
69. Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep LearningPoster76 citations
70. How fine can fine-tuning be? Learning efficient language modelsPoster73 citations
71. Neural Topic Model with Attention for Supervised LearningPoster72 citations
72. On the interplay between noise and curvature and its effect on optimization and generalizationPoster72 citations
73. A Double Residual Compression Algorithm for Efficient Distributed LearningPoster71 citations
74. Elimination of All Bad Local Minima in Deep LearningPoster71 citations
75. Entropy Weighted Power k-Means ClusteringPoster71 citations
76. Fair Decisions Despite Imperfect PredictionsPoster71 citations
77. Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction ApproachPoster71 citations
78. Regularization via Structural Label SmoothingPoster71 citations
79. Value Preserving State-Action AbstractionsPoster71 citations
80. Quantitative stability of optimal transport maps and linearization of the 2-Wasserstein spacePoster70 citations
81. A Continuous-time Perspective for Modeling Acceleration in Riemannian OptimizationPoster69 citations
82. Calibrated Prediction with Covariate Shift via Unsupervised Domain AdaptationPoster68 citations
83. Linear Convergence of Adaptive Stochastic Gradient DescentPoster67 citations
84. Corruption-Tolerant Gaussian Process Bandit OptimizationPoster66 citations
85. Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial AttacksPoster66 citations
86. Sparse and Low-rank Tensor Estimation via Cubic SketchingsPoster65 citations
87. Ordering-Based Causal Structure Learning in the Presence of Latent VariablesPoster64 citations
88. The Implicit Regularization of Ordinary Least Squares EnsemblesPoster64 citations
89. Finite-Time Analysis of Decentralized Temporal-Difference Learning with Linear Function ApproximationPoster63 citations
90. Decentralized gradient methods: does topology matter?Poster62 citations
91. Leave-One-Out Cross-Validation for Bayesian Model Comparison in Large DataPoster62 citations
92. The Expressive Power of a Class of Normalizing Flow ModelsPoster62 citations
93. Accelerating Smooth Games by Manipulating Spectral ShapesPoster61 citations
94. An Optimal Algorithm for Adversarial Bandits with Arbitrary DelaysPoster61 citations
95. Asynchronous Gibbs SamplingPoster61 citations
96. The Gossiping Insert-Eliminate Algorithm for Multi-Agent BanditsPoster60 citations
97. Validated Variational Inference via Practical Posterior Error BoundsPoster60 citations
98. Hermitian matrices for clustering directed graphs: insights and applicationsPoster59 citations
99. Sparse Orthogonal Variational Inference for Gaussian ProcessesPoster58 citations
100. Wasserstein Style TransferPoster57 citations
101. EM Converges for a Mixture of Many Linear RegressionsPoster56 citations
102. Multi-attribute Bayesian optimization with interactive preference learningPoster56 citations
103. Optimized Score Transformation for Fair ClassificationPoster56 citations
104. Rep the Set: Neural Networks for Learning Set RepresentationsPoster56 citations
105. Choosing the Sample with Lowest Loss makes SGD RobustPoster55 citations
106. On the Completeness of Causal Discovery in the Presence of Latent Confounding with Tiered Background KnowledgePoster55 citations
107. POPCORN: Partially Observed Prediction Constrained Reinforcement LearningPoster55 citations
108. Accelerating Gradient Boosting MachinesPoster54 citations
109. Bandit Convex Optimization in Non-stationary EnvironmentsPoster54 citations
110. Bandit optimisation of functions in the Matérn kernel RKHSPoster54 citations
111. Langevin Monte Carlo without smoothnessPoster54 citations
112. Robust Variational Autoencoders for Outlier Detection and Repair of Mixed-Type DataPoster54 citations
113. Stochastic Bandits with Delay-Dependent PayoffsPoster54 citations
114. Invertible Generative Modeling using Linear Rational SplinesPoster53 citations
115. Learnable Bernoulli Dropout for Bayesian Deep LearningPoster53 citations
116. Robustness for Non-Parametric Classification: A Generic Attack and DefensePoster53 citations
117. A Lyapunov analysis for accelerated gradient methods: from deterministic to stochastic casePoster51 citations
118. Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence TheoryPoster51 citations
119. Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive ModelsPoster50 citations
120. RATQ: A Universal Fixed-Length Quantizer for Stochastic OptimizationPoster50 citations
121. Two-sample Testing Using Deep LearningPoster50 citations
122. Why Non-myopic Bayesian Optimization is Promising and How Far Should We Look-ahead? A Study via RolloutPoster50 citations
123. Learning Dynamic Hierarchical Topic Graph with Graph Convolutional Network for Document ClassificationPoster49 citations
124. The True Sample Complexity of Identifying Good ArmsPoster49 citations
125. Ensemble Gaussian Processes with Spectral Features for Online Interactive Learning with ScalabilityPoster48 citations
126. RCD: Repetitive causal discovery of linear non-Gaussian acyclic models with latent confoundersPoster48 citations
127. Bayesian Image Classification with Deep Convolutional Gaussian ProcessesPoster47 citations
128. Fenchel Lifted Networks: A Lagrange Relaxation of Neural Network TrainingPoster47 citations
129. OSOM: A simultaneously optimal algorithm for multi-armed and linear contextual banditsPoster47 citations
130. Regularized Autoencoders via Relaxed Injective Probability FlowPoster47 citations
131. Accelerated Primal-Dual Algorithms for Distributed Smooth Convex Optimization over NetworksPoster46 citations
132. Decentralized Multi-player Multi-armed Bandits with No Collision InformationPoster45 citations
133. Infinitely deep neural networks as diffusion processesPoster45 citations
134. Minimizing Dynamic Regret and Adaptive Regret SimultaneouslyPoster45 citations
135. Uncertainty Quantification for Sparse Deep LearningPoster45 citations
136. Fast and Furious Convergence: Stochastic Second Order Methods under InterpolationPoster44 citations
137. A single algorithm for both restless and rested rotting banditsPoster43 citations
138. Deep Structured Mixtures of Gaussian ProcessesPoster43 citations
139. Gaussian-Smoothed Optimal Transport: Metric Structure and Statistical EfficiencyPoster43 citations
140. Gaussianization FlowsPoster43 citations
141. Deontological Ethics By Monotonicity Shape ConstraintsPoster42 citations
142. Fast Algorithms for Computational Optimal Transport and Wasserstein BarycenterPoster42 citations
143. Spatio-temporal alignments: Optimal transport through space and timePoster42 citations
144. Truly Batch Model-Free Inverse Reinforcement Learning about Multiple IntentionsPoster42 citations
145. Sharp Asymptotics and Optimal Performance for Inference in Binary ModelsPoster41 citations
146. Characterization of Overlap in Observational StudiesPoster40 citations
147. Explicit Mean-Square Error Bounds for Monte-Carlo and Linear Stochastic ApproximationPoster40 citations
148. Learning Fair Representations for Kernel ModelsPoster40 citations
149. Noisy-Input Entropy Search for Efficient Robust Bayesian OptimizationPoster40 citations
150. Budget-Constrained Bandits over General Cost and Reward DistributionsPoster39 citations
151. Linear predictor on linearly-generated data with missing values: non consistency and solutionsPoster39 citations
152. Semi-Modular Inference: enhanced learning in multi-modular models by tempering the influence of componentsPoster39 citations
153. Stable behaviour of infinitely wide deep neural networksPoster39 citations
154. Approximate Inference with Wasserstein Gradient FlowsPoster38 citations
155. Integrals over Gaussians under Linear Domain ConstraintsPoster38 citations
156. Kernel Conditional Density OperatorsPoster38 citations
157. Approximate Cross-validation: Guarantees for Model Assessment and SelectionPoster37 citations
158. Distributionally Robust Bayesian Quadrature OptimizationPoster37 citations
159. Fast Noise Removal for k-Means ClusteringPoster37 citations
160. Momentum in Reinforcement LearningPoster37 citations
161. Convex Geometry of Two-Layer ReLU Networks: Implicit Autoencoding and Interpretable ModelsPoster36 citations
162. Old Dog Learns New Tricks: Randomized UCB for Bandit ProblemsPoster36 citations
163. Doubly Sparse Variational Gaussian ProcessesPoster35 citations
164. Online Continuous DR-Submodular Maximization with Long-Term Budget ConstraintsPoster35 citations
165. Safe-Bayesian Generalized Linear RegressionPoster35 citations
166. Stopping criterion for active learning based on deterministic generalization boundsPoster35 citations
167. Conservative Exploration in Reinforcement LearningPoster34 citations
168. Ivy: Instrumental Variable Synthesis for Causal InferencePoster34 citations
169. Approximate Cross-Validation in High Dimensions with GuaranteesPoster33 citations
170. DAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence RatePoster33 citations
171. Improved Regret Bounds for Projection-free Bandit Convex OptimizationPoster33 citations
172. Regularity as Regularization: Smooth and Strongly Convex Brenier Potentials in Optimal TransportPoster33 citations
173. Sharp Analysis of Expectation-Maximization for Weakly Identifiable ModelsPoster33 citations
174. Understanding Generalization in Deep Learning via Tensor MethodsPoster33 citations
175. Causal Mosaic: Cause-Effect Inference via Nonlinear ICA and Ensemble MethodPoster32 citations
176. Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic SpacesPoster32 citations
177. A Hybrid Stochastic Policy Gradient Algorithm for Reinforcement LearningPoster31 citations
178. Alternating Minimization Converges Super-Linearly for Mixed Linear RegressionPoster31 citations
179. Efficient Distributed Hessian Free Algorithm for Large-scale Empirical Risk Minimization via Accumulating Sample StrategyPoster31 citations
180. Stochastic Recursive Variance-Reduced Cubic Regularization MethodsPoster31 citations
181. Tensorized Random ProjectionsPoster31 citations
182. Auditing ML Models for Individual Bias and UnfairnessPoster30 citations
183. Context Mover’s Distance & Barycenters: Optimal Transport of Contexts for Building RepresentationsPoster30 citations
184. On the Convergence of SARAH and BeyondPoster29 citations
185. A Robust Univariate Mean Estimator is All You NeedPoster28 citations
186. Adaptive Trade-Offs in Off-Policy LearningPoster28 citations
187. Convergence Analysis of Block Coordinate Algorithms with Determinantal SamplingPoster28 citations
188. Precision-Recall Curves Using Information Divergence FrontiersPoster28 citations
189. Stein Variational Inference for Discrete DistributionsPoster28 citations
190. The Area of the Convex Hull of Sampled Curves: a Robust Functional Statistical Depth measurePoster28 citations
191. AMAGOLD: Amortized Metropolis Adjustment for Efficient Stochastic Gradient MCMCPoster27 citations
192. Automatic Differentiation of Some First-Order Methods in Parametric OptimizationPoster27 citations
193. Bayesian experimental design using regularized determinantal point processesPoster27 citations
194. Error bounds in estimating the out-of-sample prediction error using leave-one-out cross validation in high-dimensionsPoster27 citations
195. Kernels over Sets of Finite Sets using RKHS Embeddings, with Application to Bayesian (Combinatorial) OptimizationPoster27 citations
196. Learning Dynamic and Personalized Comorbidity Networks from Event Data using Deep Diffusion ProcessesPoster27 citations
197. Learning High-dimensional Gaussian Graphical Models under Total Positivity without Adjustment of Tuning ParametersPoster27 citations
198. “Bring Your Own Greedy”+Max: Near-Optimal 1/2-Approximations for Submodular KnapsackPoster27 citations
199. Contextual Combinatorial Volatile Multi-armed Bandit with Adaptive DiscretizationPoster26 citations
200. Learning Hierarchical Interactions at Scale: A Convex Optimization ApproachPoster26 citations
201. Naive Feature Selection: Sparsity in Naive BayesPoster26 citations
202. Variational Optimization on Lie Groups, with Examples of Leading (Generalized) Eigenvalue ProblemsPoster26 citations
203. A Stein Goodness-of-fit Test for Directional DistributionsPoster25 citations
204. Gain with no Pain: Efficiency of Kernel-PCA by Nyström SamplingPoster25 citations
205. LIBRE: Learning Interpretable Boolean Rule EnsemblesPoster25 citations
206. Learning piecewise Lipschitz functions in changing environmentsPoster25 citations
207. Monotonic Gaussian Process FlowsPoster25 citations
208. On Random Subsampling of Gaussian Process Regression: A Graphon-Based AnalysisPoster25 citations
209. Structured Conditional Continuous Normalizing Flows for Efficient Amortized Inference in Graphical ModelsPoster25 citations
210. Variational Autoencoders for Sparse and Overdispersed Discrete DataPoster25 citations
211. Censored Quantile Regression ForestPoster24 citations
212. Black Box Submodular Maximization: Discrete and Continuous SettingsPoster23 citations
213. Minimax Testing of Identity to a Reference Ergodic Markov ChainPoster23 citations
214. The Sylvester Graphical Lasso (SyGlasso)Poster23 citations
215. Balanced Off-Policy Evaluation in General Action SpacesPoster22 citations
216. Independent Subspace Analysis for Unsupervised Learning of Disentangled RepresentationsPoster22 citations
217. Locally Accelerated Conditional GradientsPoster22 citations
218. Rk-means: Fast Clustering for Relational DataPoster22 citations
219. Statistical Estimation of the Poincaré constant and Application to Sampling Multimodal DistributionsPoster22 citations
220. Adversarial Robustness Guarantees for Classification with Gaussian ProcessesPoster21 citations
221. Adversarial Robustness of Flow-Based Generative ModelsPoster21 citations
222. Balancing Learning Speed and Stability in Policy Gradient via Adaptive ExplorationPoster21 citations
223. Interpretable Companions for Black-Box ModelsPoster21 citations
224. Interpretable Deep Gaussian Processes with MomentsPoster21 citations
225. Learning Rate Adaptation for Differentially Private LearningPoster21 citations
226. Low-rank regularization and solution uniqueness in over-parameterized matrix sensingPoster21 citations
227. Online Learning with Continuous Variations: Dynamic Regret and ReductionsPoster21 citations
228. A Theoretical and Practical Framework for Regression and Classification from Truncated SamplesPoster20 citations
229. Bisect and Conquer: Hierarchical Clustering via Max-Uncut BisectionPoster20 citations
230. Black-Box Inference for Non-Linear Latent Force ModelsPoster20 citations
231. Distributionally Robust Formulation and Model Selection for the Graphical LassoPoster20 citations
232. Greed Meets Sparsity: Understanding and Improving Greedy Coordinate Descent for Sparse OptimizationPoster20 citations
233. Modular Block-diagonal Curvature Approximations for Feedforward ArchitecturesPoster20 citations
234. Obfuscation via Information Density EstimationPoster20 citations
235. Private k-Means Clustering with Stability AssumptionsPoster20 citations
236. Robust Importance Weighting for Covariate ShiftPoster20 citations
237. A Theoretical Case Study of Structured Variational Inference for Community DetectionPoster19 citations
238. Almost-Matching-Exactly for Treatment Effect Estimation under Network InterferencePoster19 citations
239. Calibrated Surrogate Maximization of Linear-fractional Utility in Binary ClassificationPoster19 citations
240. Contextual Constrained Learning for Dose-Finding Clinical TrialsPoster19 citations
241. Laplacian-Regularized Graph Bandits: Algorithms and Theoretical AnalysisPoster19 citations
242. Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context DiscoveryPoster19 citations
243. A Distributional Analysis of Sampling-Based Reinforcement Learning AlgorithmsPoster18 citations
244. A Reduction from Reinforcement Learning to No-Regret Online LearningPoster18 citations
245. A Unified Statistically Efficient Estimation Framework for Unnormalized ModelsPoster18 citations
246. Causal inference in degenerate systems: An impossibility resultPoster18 citations
247. Differentiable Causal Backdoor DiscoveryPoster18 citations
248. Learning Ising and Potts Models with Latent VariablesPoster18 citations
249. Logistic regression with peer-group effects via inference in higher-order Ising modelsPoster18 citations
250. Mixed Strategies for Robust Optimization of Unknown ObjectivesPoster18 citations
251. Prophets, Secretaries, and Maximizing the Probability of Choosing the BestPoster18 citations
252. Stochastic Linear Contextual Bandits with Diverse ContextsPoster18 citations
253. Sublinear Optimal Policy Value Estimation in Contextual BanditsPoster18 citations
254. A Novel Confidence-Based Algorithm for Structured BanditsPoster17 citations
255. Enriched mixtures of generalised Gaussian process expertsPoster17 citations
256. Neighborhood Growth Determines Geometric Priors for Relational Representation LearningPoster17 citations
257. On the optimality of kernels for high-dimensional clusteringPoster17 citations
258. Optimal sampling in unbiased active learningPoster17 citations
259. Quantized Frank-Wolfe: Faster Optimization, Lower Communication, and Projection FreePoster17 citations
260. Taxonomy of Dual Block-Coordinate Ascent Methods for Discrete Energy MinimizationPoster17 citations
261. The Power of Batching in Multiple Hypothesis TestingPoster17 citations
262. Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative ModelsPoster17 citations
263. A Nonparametric Off-Policy Policy GradientPoster16 citations
264. Approximate Inference in Discrete Distributions with Monte Carlo Tree Search and Value FunctionsPoster16 citations
265. BasisVAE: Translation-invariant feature-level clustering with Variational AutoencodersPoster16 citations
266. Guaranteed Validity for Empirical Approaches to Adaptive Data AnalysisPoster16 citations
267. LdSM: Logarithm-depth Streaming Multi-label Decision TreesPoster16 citations
268. Lipschitz Continuous Autoencoders in Application to Anomaly DetectionPoster16 citations
269. Local Differential Privacy for SamplingPoster16 citations
270. Nonparametric Estimation in the Dynamic Bradley-Terry ModelPoster16 citations
271. Scaling up Kernel Ridge Regression via Locality Sensitive HashingPoster16 citations
272. The Fast Loaded Dice Roller: A Near-Optimal Exact Sampler for Discrete Probability DistributionsPoster16 citations
273. An Empirical Study of Stochastic Gradient Descent with Structured Covariance NoisePoster15 citations
274. Best-item Learning in Random Utility Models with Subset ChoicesPoster15 citations
275. Conditional Importance Sampling for Off-Policy LearningPoster15 citations
276. Contextual Online False Discovery Rate ControlPoster15 citations
277. Data Generation for Neural Programming by ExamplePoster15 citations
278. Graph DNA: Deep Neighborhood Aware Graph Encoding for Collaborative FilteringPoster15 citations
279. Nonmyopic Gaussian Process Optimization with Macro-ActionsPoster15 citations
280. On Minimax Optimality of GANs for Robust Mean EstimationPoster15 citations
281. On Pruning for Score-Based Bayesian Network Structure LearningPoster15 citations
282. Statistical and Computational Rates in Graph Logistic RegressionPoster15 citations
283. Validation of Approximate Likelihood and Emulator Models for Computationally Intensive SimulationsPoster15 citations
284. An Optimal Algorithm for Bandit Convex Optimization with Strongly-Convex and Smooth LossPoster14 citations
285. Distributed, partially collapsed MCMC for Bayesian NonparametricsPoster14 citations
286. Fast and Accurate Ranking RegressionPoster14 citations
287. Learning in Gated Neural NetworksPoster14 citations
288. Simulator Calibration under Covariate Shift with KernelsPoster14 citations
289. Accelerated Factored Gradient Descent for Low-Rank Matrix FactorizationPoster13 citations
290. Budget Learning via BracketingPoster13 citations
291. Convergence Rates of Gradient Descent and MM Algorithms for Bradley-Terry ModelsPoster13 citations
292. General Identification of Dynamic Treatment Regimes Under InterferencePoster13 citations
293. MAP Inference for Customized Determinantal Point Processes via Maximum Inner Product SearchPoster13 citations
294. Stepwise Model Selection for Sequence Prediction via Deep Kernel LearningPoster13 citations
295. Variance Reduction for Evolution Strategies via Structured Control VariatesPoster13 citations
296. Efficient Spectrum-Revealing CUR Matrix DecompositionPoster12 citations
297. Expressiveness and Learning of Hidden Quantum Markov ModelsPoster12 citations
298. Hamiltonian Monte Carlo SwindlesPoster12 citations
299. More Powerful Selective Kernel Tests for Feature SelectionPoster12 citations
300. Online Binary Space Partitioning ForestsPoster12 citations
301. Post-Estimation Smoothing: A Simple Baseline for Learning with Side InformationPoster12 citations
302. Private Protocols for U-Statistics in the Local Model and BeyondPoster12 citations
303. Scalable Nonparametric Factorization for High-Order Interaction EventsPoster12 citations
304. Statistical guarantees for local graph clusteringPoster12 citations
305. Stretching the Effectiveness of MLE from Accuracy to Bias for Pairwise ComparisonsPoster12 citations
306. A Primal-Dual Solver for Large-Scale Tracking-by-AssignmentPoster11 citations
307. AP-Perf: Incorporating Generic Performance Metrics in Differentiable LearningPoster11 citations
308. Exploiting Categorical Structure Using Tree-Based MethodsPoster11 citations
309. Gaussian Sketching yields a J-L Lemma in RKHSPoster11 citations
310. Importance Sampling via Local SensitivityPoster11 citations
311. Neural Decomposition: Functional ANOVA with Variational AutoencodersPoster11 citations
312. On casting importance weighted autoencoder to an EM algorithm to learn deep generative modelsPoster11 citations
313. Robust Learning from Discriminative Feature FeedbackPoster11 citations
314. Unconditional Coresets for Regularized Loss MinimizationPoster11 citations
315. A Characterization of Mean Squared Error for Estimator with BaggingPoster10 citations
316. A Wasserstein Minimum Velocity Approach to Learning Unnormalized ModelsPoster10 citations
317. Additive Tree-Structured Covariance Function for Conditional Parameter Spaces in Bayesian OptimizationPoster10 citations
318. Bayesian Reinforcement Learning via Deep, Sparse SamplingPoster10 citations
319. Conditional Linear RegressionPoster10 citations
320. Finite-Time Error Bounds for Biased Stochastic Approximation with Applications to Q-LearningPoster10 citations
321. Functional Gradient Boosting for Learning Residual-like Networks with Statistical GuaranteesPoster10 citations
322. Learning Entangled Single-Sample Distributions via Iterative TrimmingPoster10 citations
323. Online Batch Decision-Making with High-Dimensional CovariatesPoster10 citations
324. Optimal Approximation of Doubly Stochastic MatricesPoster10 citations
325. Optimal Deterministic Coresets for Ridge RegressionPoster10 citations
326. Patient-Specific Effects of Medication Using Latent Force Models with Gaussian ProcessesPoster10 citations
327. Stochastic Neural Network with Kronecker FlowPoster10 citations
328. Stochastic Variance-Reduced Algorithms for PCA with Arbitrary Mini-Batch SizesPoster10 citations
329. An approximate KLD based experimental design for models with intractable likelihoodsPoster9 citations
330. Discrete Action On-Policy Learning with Action-Value CriticPoster9 citations
331. Prediction Focused Topic Models via Feature SelectionPoster9 citations
332. Robust Optimisation Monte CarloPoster9 citations
333. Sparse Hilbert-Schmidt Independence Criterion RegressionPoster9 citations
334. Thresholding Bandit Problem with Both Duels and PullsPoster9 citations
335. Understanding the Effects of Batching in Online Active LearningPoster9 citations
336. Utility/Privacy Trade-off through the lens of Optimal TransportPoster9 citations
337. A Locally Adaptive Bayesian Cubature MethodPoster8 citations
338. A Multiclass Classification Approach to Label RankingPoster8 citations
339. A principled approach for generating adversarial images under non-smooth dissimilarity metricsPoster8 citations
340. Adaptive multi-fidelity optimization with fast learning ratesPoster8 citations
341. Derivative-Free & Order-Robust OptimisationPoster8 citations
342. Deterministic Decoding for Discrete Data in Variational AutoencodersPoster8 citations
343. Guarantees of Stochastic Greedy Algorithms for Non-monotone Submodular Maximization with Cardinality ConstraintPoster8 citations
344. Imputation estimators for unnormalized models with missing dataPoster8 citations
345. Learning spectrograms with convolutional spectral kernelsPoster8 citations
346. Linear Dynamics: Clustering without identificationPoster8 citations
347. Nested-Wasserstein Self-Imitation Learning for Sequence GenerationPoster8 citations
348. Sample Complexity of Estimating the Policy Gradient for Nearly Deterministic Dynamical SystemsPoster8 citations
349. Support recovery and sup-norm convergence rates for sparse pivotal estimationPoster8 citations
350. Thresholding Graph Bandits with GrAPLPoster8 citations
351. A nonasymptotic law of iterated logarithm for general M-estimatorsPoster7 citations
352. Communication-Efficient Asynchronous Stochastic Frank-Wolfe over Nuclear-norm BallsPoster7 citations
353. Hyperbolic Manifold RegressionPoster7 citations
354. Improving Maximum Likelihood Training for Text Generation with Density Ratio EstimationPoster7 citations
355. On Thompson Sampling for Smoother-than-Lipschitz BanditsPoster7 citations
356. Sketching Transformed Matrices with Applications to Natural Language ProcessingPoster7 citations
357. Thompson Sampling for Linearly Constrained BanditsPoster7 citations
358. A Diversity-aware Model for Majority Vote Ensemble AccuracyPoster6 citations
359. A Three Sample Hypothesis Test for Evaluating Generative ModelsPoster6 citations
360. An Asymptotic Rate for the LASSO LossPoster6 citations
361. An Inverse-free Truncated Rayleigh-Ritz Method for Sparse Generalized Eigenvalue ProblemPoster6 citations
362. Coping With Simulators That Don’t Always ReturnPoster6 citations
363. Differentiable Feature Selection by Discrete RelaxationPoster6 citations
364. Long-and Short-Term Forecasting for Portfolio Selection with Transaction CostsPoster6 citations
365. Non-exchangeable feature allocation models with sublinear growth of the feature sizesPoster6 citations
366. Risk Bounds for Learning Multiple Components with Permutation-Invariant LossesPoster6 citations
367. Sequential no-Substitution k-Median-ClusteringPoster6 citations
368. A Rule for Gradient Estimator Selection, with an Application to Variational InferencePoster5 citations
369. AsyncQVI: Asynchronous-Parallel Q-Value Iteration for Discounted Markov Decision Processes with Near-Optimal Sample ComplexityPoster5 citations
370. Automated Augmented Conjugate Inference for Non-conjugate Gaussian Process ModelsPoster5 citations
371. Dynamical Systems Theory for Causal Inference with Application to Synthetic Control MethodsPoster5 citations
372. Fast and Bayes-consistent nearest neighborsPoster5 citations
373. Learning Gaussian Graphical Models via Multiplicative WeightsPoster5 citations
374. On the Sample Complexity of Learning Sum-Product NetworksPoster5 citations
375. Prior-aware Composition Inference for Spectral Topic ModelsPoster5 citations
376. Revisiting the Landscape of Matrix FactorizationPoster5 citations
377. Solving the Robust Matrix Completion Problem via a System of Nonlinear EquationsPoster5 citations
378. A Linear-time Independence Criterion Based on a Finite Basis ApproximationPoster4 citations
379. Diameter-based Interactive Structure DiscoveryPoster4 citations
380. Domain-Liftability of Relational Marginal PolytopesPoster4 citations
381. Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral LearningPoster4 citations
382. GAIT: A Geometric Approach to Information TheoryPoster4 citations
383. Minimax Bounds for Structured Prediction Based on Factor GraphsPoster4 citations
384. Optimization of Graph Total Variation via Active-Set-based Combinatorial ReconditioningPoster4 citations
385. Scalable Feature Selection for (Multitask) Gradient Boosted TreesPoster4 citations
386. A Farewell to Arms: Sequential Reward Maximization on a Budget with a Giving Up OptionPoster3 citations
387. Assessing Local Generalization Capability in Deep ModelsPoster3 citations
388. Better Long-Range Dependency By Bootstrapping A Mutual Information RegularizerPoster3 citations
389. Convergence Rates of Smooth Message Passing with Rounding in Entropy-Regularized MAP InferencePoster3 citations
390. Dependent randomized rounding for clustering and partition systems with knapsack constraintsPoster3 citations
391. Fast Markov chain Monte Carlo algorithms via Lie groupsPoster3 citations
392. Marginal Densities, Factor Graph Duality, and High-Temperature Series ExpansionsPoster3 citations
393. Measuring Mutual Information Between All Pairs of Variables in Subquadratic ComplexityPoster3 citations
394. Robust Stackelberg buyers in repeated auctionsPoster3 citations
395. A Framework for Sample Efficient Interval Estimation with Control VariatesPoster2 citations
396. Adaptive Discretization for Evaluation of Probabilistic Cost FunctionsPoster2 citations
397. Automatic Differentiation of Sketched RegressionPoster2 citations
398. Multiplicative Gaussian Particle FilterPoster2 citations
399. Online Learning Using Only Peer PredictionPoster2 citations
400. Practical Nonisotropic Monte Carlo Sampling in High Dimensions via Determinantal Point ProcessesPoster2 citations
401. Active Community Detection with Maximal Expected Model ChangePoster1 citations
402. Adaptive Online Kernel Sampling for Vertex ClassificationPoster1 citations
403. Adversarial Risk Bounds through Sparsity based CompressionPoster1 citations
404. Amortized Inference of Variational Bounds for Learning Noisy-ORPoster1 citations
405. Constructing a provably adversarially-robust classifier from a high accuracy onePoster1 citations
406. Inference of Dynamic Graph Changes for Functional ConnectomePoster1 citations
407. Minimax Rank-$1$ Matrix FactorizationPoster1 citations
408. Multi-level Gaussian Graphical Models Conditional on CovariatesPoster1 citations
409. Recommendation on a Budget: Column Space Recovery from Partially Observed Entries with Random or Active SamplingPoster1 citations
410. Sample complexity bounds for localized sketchingPoster1 citations
411. Screening Data Points in Empirical Risk Minimization via Ellipsoidal Regions and Safe Loss FunctionsPoster1 citations
412. The Quantile Snapshot Scan: Comparing Quantiles of Spatial Data from Two Snapshots in TimePoster1 citations
413. Towards Competitive N-gram SmoothingPoster1 citations
414. Unsupervised Neural Universal Denoiser for Finite-Input General-Output Noisy ChannelPoster1 citations
415. A PTAS for the Bayesian Thresholding Bandit ProblemPoster
416. Accelerated Bayesian Optimisation through Weight-Prior TuningPoster
417. Dynamic content based rankingPoster
418. Nonparametric Sequential Prediction While Deep Learning the KernelPoster
419. On Generalization Bounds of a Family of Recurrent Neural NetworksPoster
420. On Maximization of Weakly Modular Functions: Guarantees of Multi-stage Algorithms, Tractability, and HardnessPoster
421. Online Convex Optimization with Perturbed Constraints: Optimal Rates against Stronger BenchmarksPoster
422. Sharp Thresholds of the Information Cascade Fragility Under a Mismatched ModelPoster

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