AISTATS 2021 Accepted Papers

The full list of 455 papers accepted at AISTATS 2021 (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. Federated Learning with Compression: Unified Analysis and Sharp GuaranteesPoster358 citations
2. Approximate Data Deletion from Machine Learning ModelsPoster328 citations
3. Benchmarking Simulation-Based InferencePoster243 citations
4. Shuffled Model of Differential Privacy in Federated LearningPoster234 citations
5. Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast ConvergencePoster221 citations
6. Provably Efficient Safe Exploration via Primal-Dual Policy OptimizationPoster200 citations
7. Improving KernelSHAP: Practical Shapley Value Estimation Using Linear RegressionPoster197 citations
8. Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning AlgorithmsPoster191 citations
9. Efficient Methods for Structured Nonconvex-Nonconcave Min-Max OptimizationPoster186 citations
10. Free-rider Attacks on Model Aggregation in Federated LearningPoster174 citations
11. On Information Gain and Regret Bounds in Gaussian Process BanditsPoster166 citations
12. Does Invariant Risk Minimization Capture Invariance?Poster153 citations
13. On the Importance of Hyperparameter Optimization for Model-based Reinforcement LearningPoster152 citations
14. Scalable Constrained Bayesian OptimizationPoster149 citations
15. Towards Flexible Device Participation in Federated LearningPoster141 citations
16. Local SGD: Unified Theory and New Efficient MethodsPoster136 citations
17. Shapley Flow: A Graph-based Approach to Interpreting Model PredictionsPoster136 citations
18. Causal Autoregressive FlowsPoster128 citations
19. Evaluating Model Robustness and Stability to Dataset ShiftPoster128 citations
20. Neural Enhanced Belief Propagation on Factor GraphsPoster125 citations
21. On the Role of Data in PAC-Bayes BoundsPoster123 citations
22. Understanding and Mitigating Exploding Inverses in Invertible Neural NetworksPoster122 citations
23. DP-MERF: Differentially Private Mean Embeddings with RandomFeatures for Practical Privacy-preserving Data GenerationPoster115 citations
24. Matérn Gaussian Processes on GraphsPoster113 citations
25. Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement LearningPoster110 citations
26. Density of States Estimation for Out of Distribution DetectionPoster108 citations
27. Asymptotics of Ridge(less) Regression under General Source ConditionPoster107 citations
28. Federated Multi-armed Bandits with PersonalizationPoster105 citations
29. LassoNet: Neural Networks with Feature SparsityPoster103 citations
30. SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and InterpolationPoster102 citations
31. A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap MatrixPoster100 citations
32. Finite-Sample Regret Bound for Distributionally Robust Offline Tabular Reinforcement LearningPoster100 citations
33. A Variational Information Bottleneck Approach to Multi-Omics Data IntegrationPoster98 citations
34. Stochastic Bandits with Linear ConstraintsPoster97 citations
35. Interpretable Random Forests via Rule ExtractionPoster95 citations
36. A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free!Poster93 citations
37. Convergence and Accuracy Trade-Offs in Federated Learning and Meta-LearningPoster93 citations
38. Evading the Curse of Dimensionality in Unconstrained Private GLMsPoster92 citations
39. Stochastic Linear Bandits Robust to Adversarial AttacksPoster91 citations
40. Counterfactual Representation Learning with Balancing WeightsPoster89 citations
41. Algorithms for Fairness in Sequential Decision MakingPoster88 citations
42. Differentiable Causal Discovery Under Unmeasured ConfoundingPoster86 citations
43. Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement LearningPoster84 citations
44. On the Effect of Auxiliary Tasks on Representation DynamicsPoster84 citations
45. Efficient Computation and Analysis of Distributional Shapley ValuesPoster80 citations
46. Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations.Poster80 citations
47. CLAR: Contrastive Learning of Auditory RepresentationsPoster78 citations
48. Federated f-Differential PrivacyPoster78 citations
49. Generalized Spectral Clustering via Gromov-Wasserstein LearningPoster78 citations
50. Local Stochastic Gradient Descent Ascent: Convergence Analysis and Communication EfficiencyPoster78 citations
51. Q-learning with Logarithmic RegretPoster78 citations
52. On the Linear Convergence of Policy Gradient Methods for Finite MDPsPoster77 citations
53. Implicit Regularization via Neural Feature AlignmentPoster75 citations
54. vqSGD: Vector Quantized Stochastic Gradient DescentPoster74 citations
55. Differentiable Divergences Between Time SeriesPoster72 citations
56. On Projection Robust Optimal Transport: Sample Complexity and Model MisspecificationPoster72 citations
57. Stable ResNetPoster70 citations
58. Geometrically Enriched Latent SpacesPoster69 citations
59. An Analysis of LIME for Text DataPoster67 citations
60. Learning Infinite-horizon Average-reward MDPs with Linear Function ApproximationPoster67 citations
61. Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFTPoster66 citations
62. Kernel Distributionally Robust Optimization: Generalized Duality Theorem and Stochastic ApproximationPoster64 citations
63. Uniform Consistency of Cross-Validation Estimators for High-Dimensional Ridge RegressionPoster64 citations
64. Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric UncertaintiesPoster63 citations
65. Rate-improved inexact augmented Lagrangian method for constrained nonconvex optimizationPoster62 citations
66. Kernel regression in high dimensions: Refined analysis beyond double descentPoster61 citations
67. Approximate Message Passing with Spectral Initialization for Generalized Linear ModelsPoster60 citations
68. Low-Rank Generalized Linear Bandit ProblemsPoster60 citations
69. Regularization Matters: A Nonparametric Perspective on Overparametrized Neural NetworkPoster60 citations
70. On the proliferation of support vectors in high dimensionsPoster59 citations
71. An Adaptive-MCMC Scheme for Setting Trajectory Lengths in Hamiltonian Monte CarloPoster58 citations
72. Causal Inference under Networked Interference and Intervention Policy EnhancementPoster58 citations
73. Variational Autoencoder with Learned Latent StructurePoster58 citations
74. Longitudinal Variational AutoencoderPoster57 citations
75. All of the Fairness for Edge Prediction with Optimal TransportPoster56 citations
76. Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent ConfoundersPoster56 citations
77. Confident Off-Policy Evaluation and Selection through Self-Normalized Importance WeightingPoster55 citations
78. Distribution Regression for Sequential DataPoster55 citations
79. Logistic Q-LearningPoster54 citations
80. Gaming Helps! Learning from Strategic Interactions in Natural DynamicsPoster53 citations
81. Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapesPoster53 citations
82. Momentum Improves Optimization on Riemannian ManifoldsPoster53 citations
83. Selective Classification via One-Sided PredictionPoster53 citations
84. Online k-means ClusteringPoster51 citations
85. Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time SeriesPoster51 citations
86. Budgeted and Non-Budgeted Causal BanditsPoster50 citations
87. Fast Adaptation with Linearized Neural NetworksPoster49 citations
88. Localizing Changes in High-Dimensional Regression ModelsPoster49 citations
89. On the Minimax Optimality of the EM Algorithm for Learning Two-Component Mixed Linear RegressionPoster49 citations
90. Projection-Free Optimization on Uniformly Convex SetsPoster49 citations
91. Understanding Gradient Clipping In Incremental Gradient MethodsPoster49 citations
92. A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric SpacesPoster48 citations
93. Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High DimensionsPoster48 citations
94. Instance-Wise Minimax-Optimal Algorithms for Logistic BanditsPoster48 citations
95. An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson SamplingPoster47 citations
96. Dominate or Delete: Decentralized Competing Bandits in Serial DictatorshipPoster47 citations
97. Corralling Stochastic Bandit AlgorithmsPoster46 citations
98. Learning with Hyperspherical UniformityPoster46 citations
99. Online Model Selection for Reinforcement Learning with Function ApproximationPoster46 citations
100. Approximating Lipschitz continuous functions with GroupSort neural networksPoster45 citations
101. Bayesian Inference with Certifiable Adversarial RobustnessPoster45 citations
102. On the Privacy Properties of GAN-generated SamplesPoster44 citations
103. Towards a Theoretical Understanding of the Robustness of Variational AutoencodersPoster44 citations
104. Transforming Gaussian Processes With Normalizing FlowsPoster44 citations
105. Generalization Bounds for Stochastic Saddle Point ProblemsPoster43 citations
106. Graphical Normalizing FlowsPoster42 citations
107. Novel Change of Measure Inequalities with Applications to PAC-Bayesian Bounds and Monte Carlo EstimationPoster42 citations
108. On the Generalization Properties of Adversarial TrainingPoster42 citations
109. Continual Learning using a Bayesian Nonparametric Dictionary of Weight FactorsPoster41 citations
110. Kernel Interpolation for Scalable Online Gaussian ProcessesPoster41 citations
111. Sample Complexity Bounds for Two Timescale Value-based Reinforcement Learning AlgorithmsPoster41 citations
112. Sparse Gaussian Processes Revisited: Bayesian Approaches to Inducing-Variable ApproximationsPoster41 citations
113. Tensor Networks for Probabilistic Sequence ModelingPoster41 citations
114. Fast and Smooth Interpolation on Wasserstein SpacePoster40 citations
115. Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror DescentPoster40 citations
116. Latent Derivative Bayesian Last Layer NetworksPoster40 citations
117. Linearly Constrained Gaussian Processes with Boundary ConditionsPoster40 citations
118. Mirrorless Mirror Descent: A Natural Derivation of Mirror DescentPoster40 citations
119. Deep Probabilistic Accelerated Evaluation: A Robust Certifiable Rare-Event Simulation Methodology for Black-Box Safety-Critical SystemsPoster39 citations
120. Online Sparse Reinforcement LearningPoster38 citations
121. Problem-Complexity Adaptive Model Selection for Stochastic Linear BanditsPoster38 citations
122. RankDistil: Knowledge Distillation for RankingPoster38 citations
123. Automatic structured variational inferencePoster37 citations
124. When OT meets MoM: Robust estimation of Wasserstein DistancePoster37 citations
125. Group testing for connected communitiesPoster36 citations
126. Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based InferencePoster36 citations
127. On Data Efficiency of Meta-learningPoster36 citations
128. Reinforcement Learning for Constrained Markov Decision ProcessesPoster36 citations
129. Active Learning under Label ShiftPoster35 citations
130. Learning Complexity of Simulated AnnealingPoster35 citations
131. Learning Fair Scoring Functions: Bipartite Ranking under ROC-based Fairness ConstraintsPoster35 citations
132. Mean-Variance Analysis in Bayesian Optimization under UncertaintyPoster35 citations
133. Reaping the Benefits of Bundling under High Production CostsPoster35 citations
134. A Spectral Analysis of Dot-product KernelsPoster34 citations
135. Calibrated Adaptive Probabilistic ODE SolversPoster34 citations
136. Parametric Programming Approach for More Powerful and General Lasso Selective InferencePoster34 citations
137. Scalable Gaussian Process Variational AutoencodersPoster34 citations
138. Semi-Supervised Aggregation of Dependent Weak Supervision Sources With Performance GuaranteesPoster34 citations
139. Sharp Analysis of a Simple Model for Random ForestsPoster34 citations
140. Animal pose estimation from video data with a hierarchical von Mises-Fisher-Gaussian modelPoster33 citations
141. Mirror Descent View for Neural Network QuantizationPoster33 citations
142. Online Active Model Selection for Pre-trained ClassifiersPoster33 citations
143. Robust Imitation Learning from Noisy DemonstrationsPoster33 citations
144. When MAML Can Adapt Fast and How to Assist When It CannotPoster33 citations
145. PClean: Bayesian Data Cleaning at Scale with Domain-Specific Probabilistic ProgrammingPoster32 citations
146. Quick Streaming Algorithms for Maximization of Monotone Submodular Functions in Linear TimePoster32 citations
147. A Theory of Multiple-Source Adaptation with Limited Target Labeled DataPoster31 citations
148. Automatic Differentiation Variational Inference with MixturesPoster31 citations
149. Convergence Properties of Stochastic HypergradientsPoster31 citations
150. Hidden Cost of Randomized SmoothingPoster31 citations
151. On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient FlowPoster31 citations
152. Optimal Quantisation of Probability Measures Using Maximum Mean DiscrepancyPoster31 citations
153. Multitask Bandit Learning Through Heterogeneous Feedback AggregationPoster30 citations
154. Quantifying the Privacy Risks of Learning High-Dimensional Graphical ModelsPoster30 citations
155. Revisiting Projection-free Online Learning: the Strongly Convex CasePoster30 citations
156. Variational inference for nonlinear ordinary differential equationsPoster30 citations
157. ATOL: Measure Vectorization for Automatic Topologically-Oriented LearningPoster29 citations
158. Adversarially Robust Estimate and Risk Analysis in Linear RegressionPoster29 citations
159. Learn to Expect the Unexpected: Probably Approximately Correct Domain GeneralizationPoster29 citations
160. Online Forgetting Process for Linear Regression ModelsPoster29 citations
161. Contextual Blocking BanditsPoster28 citations
162. Curriculum Learning by Optimizing Learning DynamicsPoster28 citations
163. Deep Fourier Kernel for Self-Attentive Point ProcessesPoster28 citations
164. Improving Adversarial Robustness via Unlabeled Out-of-Domain DataPoster28 citations
165. Learning Temporal Point Processes with Intermittent ObservationsPoster28 citations
166. On the Suboptimality of Negative Momentum for Minimax OptimizationPoster28 citations
167. Bayesian Active Learning by Soft Mean Objective Cost of UncertaintyPoster27 citations
168. Bayesian Coresets: Revisiting the Nonconvex Optimization PerspectivePoster27 citations
169. CADA: Communication-Adaptive Distributed AdamPoster27 citations
170. Hadamard Wirtinger Flow for Sparse Phase RetrievalPoster27 citations
171. Improved Complexity Bounds in Wasserstein Barycenter ProblemPoster27 citations
172. LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient UploadsPoster27 citations
173. Learning Prediction Intervals for Regression: Generalization and CalibrationPoster27 citations
174. Tight Regret Bounds for Infinite-armed Linear Contextual BanditsPoster27 citations
175. A Fast and Robust Method for Global Topological Functional OptimizationPoster26 citations
176. Amortized Bayesian Prototype Meta-learning: A New Probabilistic Meta-learning Approach to Few-shot Image ClassificationPoster26 citations
177. Learning Contact Dynamics using Physically Structured Neural NetworksPoster26 citations
178. Learning to Defend by Learning to AttackPoster26 citations
179. Maximal Couplings of the Metropolis-Hastings AlgorithmPoster26 citations
180. Minimax Estimation of Laplacian Constrained Precision MatricesPoster26 citations
181. Model updating after interventions paradoxically introduces biasPoster26 citations
182. Abstract Value Iteration for Hierarchical Reinforcement LearningPoster25 citations
183. Independent Innovation Analysis for Nonlinear Vector Autoregressive ProcessPoster25 citations
184. Multi-Armed Bandits with Cost SubsidyPoster25 citations
185. Predictive Complexity PriorsPoster25 citations
186. Taming heavy-tailed features by shrinkagePoster25 citations
187. When Will Generative Adversarial Imitation Learning Algorithms Attain Global ConvergencePoster25 citations
188. A Study of Condition Numbers for First-Order OptimizationPoster24 citations
189. Aligning Time Series on Incomparable SpacesPoster24 citations
190. Completing the Picture: Randomized Smoothing Suffers from the Curse of Dimensionality for a Large Family of DistributionsPoster24 citations
191. Fast Statistical Leverage Score Approximation in Kernel Ridge RegressionPoster24 citations
192. Non-asymptotic Performance Guarantees for Neural Estimation of f-DivergencesPoster24 citations
193. Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox AttacksPoster24 citations
194. Regularized Policies are Reward RobustPoster24 citations
195. A Parameter-Free Algorithm for Misspecified Linear Contextual BanditsPoster23 citations
196. Adaptive wavelet pooling for convolutional neural networksPoster23 citations
197. Anderson acceleration of coordinate descentPoster23 citations
198. Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous UpdatesPoster23 citations
199. Provable Hierarchical Imitation Learning via EMPoster23 citations
200. Self-Concordant Analysis of Generalized Linear Bandits with ForgettingPoster23 citations
201. Significance of Gradient Information in Bayesian OptimizationPoster23 citations
202. Stability and Differential Privacy of Stochastic Gradient Descent for Pairwise Learning with Non-Smooth LossPoster23 citations
203. Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?Poster22 citations
204. Learning Partially Known Stochastic Dynamics with Empirical PAC BayesPoster22 citations
205. Minimal enumeration of all possible total effects in a Markov equivalence classPoster22 citations
206. Optimizing Percentile Criterion using Robust MDPsPoster22 citations
207. Top-m identification for linear banditsPoster22 citations
208. Competing AI: How does competition feedback affect machine learning?Poster21 citations
209. Iterative regularization for convex regularizersPoster21 citations
210. Learning Individually Fair Classifier with Path-Specific Causal-Effect ConstraintPoster21 citations
211. Learning with Gradient Descent and Weakly Convex LossesPoster21 citations
212. Local Competition and Stochasticity for Adversarial Robustness in Deep LearningPoster21 citations
213. Minimax Model LearningPoster21 citations
214. No-regret Algorithms for Multi-task Bayesian OptimizationPoster21 citations
215. Differentially Private Analysis on Graph StreamsPoster20 citations
216. Hindsight Expectation Maximization for Goal-conditioned Reinforcement LearningPoster20 citations
217. Measure Transport with Kernel Stein DiscrepancyPoster20 citations
218. Minimax Optimal Regression over Sobolev Spaces via Laplacian Regularization on Neighborhood GraphsPoster20 citations
219. Provably Efficient Actor-Critic for Risk-Sensitive and Robust Adversarial RL: A Linear-Quadratic CasePoster20 citations
220. Quantum Tensor Networks, Stochastic Processes, and Weighted AutomataPoster20 citations
221. Smooth Bandit Optimization: Generalization to Holder SpacePoster20 citations
222. Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous DataPoster20 citations
223. Communication Efficient Primal-Dual Algorithm for Nonconvex Nonsmooth Distributed OptimizationPoster19 citations
224. Learning Smooth and Fair RepresentationsPoster19 citations
225. Linear Models are Robust Optimal Under Strategic BehaviorPoster19 citations
226. Online Robust Control of Nonlinear Systems with Large UncertaintyPoster19 citations
227. γ-ABC: Outlier-Robust Approximate Bayesian Computation Based on a Robust Divergence EstimatorPoster19 citations
228. An Analysis of the Adaptation Speed of Causal ModelsPoster18 citations
229. Bandit algorithms: Letting go of logarithmic regret for statistical robustnessPoster18 citations
230. Distributionally Robust Optimization for Deep Kernel Multiple Instance LearningPoster18 citations
231. Entropy Partial Transport with Tree Metrics: Theory and PracticePoster18 citations
232. Experimental Design for Regret Minimization in Linear BanditsPoster18 citations
233. Foundations of Bayesian Learning from Synthetic DataPoster18 citations
234. Hyperparameter Transfer Learning with Adaptive ComplexityPoster18 citations
235. No-Regret Reinforcement Learning with Heavy-Tailed RewardsPoster18 citations
236. Reinforcement Learning for Mean Field Games with Strategic ComplementaritiesPoster18 citations
237. Variable Selection with Rigorous Uncertainty Quantification using Deep Bayesian Neural Networks: Posterior Concentration and Bernstein-von Mises PhenomenonPoster18 citations
238. A Dynamical View on Optimization Algorithms of Overparameterized Neural NetworksPoster17 citations
239. A Stein Goodness-of-test for Exponential Random Graph ModelsPoster17 citations
240. A Theoretical Characterization of Semi-supervised Learning with Self-training for Gaussian Mixture ModelsPoster17 citations
241. Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable EstimationPoster17 citations
242. Meta Learning in the Continuous Time LimitPoster17 citations
243. Multi-Fidelity High-Order Gaussian Processes for Physical SimulationPoster17 citations
244. On Learning Continuous Pairwise Markov Random FieldsPoster17 citations
245. On Riemannian Stochastic Approximation Schemes with Fixed Step-SizePoster17 citations
246. Product Manifold LearningPoster17 citations
247. Reinforcement Learning in Parametric MDPs with Exponential FamiliesPoster17 citations
248. Revisiting Model-Agnostic Private Learning: Faster Rates and Active LearningPoster17 citations
249. Ridge Regression with Over-parametrized Two-Layer Networks Converge to Ridgelet SpectrumPoster17 citations
250. Stability and Risk Bounds of Iterative Hard ThresholdingPoster17 citations
251. Active Online Learning with Hidden Shifting DomainsPoster16 citations
252. Couplings for Multinomial Hamiltonian Monte CarloPoster16 citations
253. Deep Generative Missingness Pattern-Set Mixture ModelsPoster16 citations
254. Flow-based Alignment Approaches for Probability Measures in Different SpacesPoster16 citations
255. Fork or Fail: Cycle-Consistent Training with Many-to-One MappingsPoster16 citations
256. Latent variable modeling with random featuresPoster16 citations
257. Regret Minimization for Causal Inference on Large Treatment SpacePoster16 citations
258. Robust and Private Learning of HalfspacesPoster16 citations
259. Sparse Algorithms for Markovian Gaussian ProcessesPoster16 citations
260. Towards Understanding the Behaviors of Optimal Deep Active Learning AlgorithmsPoster16 citations
261. Tractable contextual bandits beyond realizabilityPoster16 citations
262. A Change of Variables Method For Rectangular Matrix-Vector ProductsPoster15 citations
263. A Statistical Perspective on Coreset Density EstimationPoster15 citations
264. Accumulations of Projections—A Unified Framework for Random Sketches in Kernel Ridge RegressionPoster15 citations
265. Adaptive Approximate Policy IterationPoster15 citations
266. An Optimal Reduction of TV-Denoising to Adaptive Online LearningPoster15 citations
267. Clustering multilayer graphs with missing nodesPoster15 citations
268. Consistent k-Median: Simpler, Better and RobustPoster15 citations
269. Fisher Auto-EncodersPoster15 citations
270. Fractional moment-preserving initialization schemes for training deep neural networksPoster15 citations
271. Hierarchical Clustering in General Metric Spaces using Approximate Nearest NeighborsPoster15 citations
272. High-Dimensional Feature Selection for Sample Efficient Treatment Effect EstimationPoster15 citations
273. No-Regret Algorithms for Private Gaussian Process Bandit OptimizationPoster15 citations
274. On Multilevel Monte Carlo Unbiased Gradient Estimation for Deep Latent Variable ModelsPoster15 citations
275. Thresholded Adaptive Validation: Tuning the Graphical Lasso for Graph RecoveryPoster15 citations
276. Follow Your Star: New Frameworks for Online Stochastic Matching with Known and Unknown PatiencePoster14 citations
277. Learning User Preferences in Non-Stationary EnvironmentsPoster14 citations
278. Noise Contrastive Meta-Learning for Conditional Density Estimation using Kernel Mean EmbeddingsPoster14 citations
279. Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix FactorizationPoster14 citations
280. Optimal query complexity for private sequential learning against eavesdroppingPoster14 citations
281. Rate-Regularization and Generalization in Variational AutoencodersPoster14 citations
282. Regularized ERM on random subspacesPoster14 citations
283. Unifying Clustered and Non-stationary BanditsPoster14 citations
284. A unified view of likelihood ratio and reparameterization gradientsPoster13 citations
285. Detection and Defense of Topological Adversarial Attacks on GraphsPoster13 citations
286. Differentially Private Online Submodular MaximizationPoster13 citations
287. Direct Loss Minimization for Sparse Gaussian ProcessesPoster13 citations
288. Explore the Context: Optimal Data Collection for Context-Conditional Dynamics ModelsPoster13 citations
289. Fair for All: Best-effort Fairness Guarantees for ClassificationPoster13 citations
290. Fast Learning in Reproducing Kernel Krein Spaces via Signed MeasuresPoster13 citations
291. Faster Kernel Interpolation for Gaussian ProcessesPoster13 citations
292. Inference in Stochastic Epidemic Models via Multinomial ApproximationsPoster13 citations
293. Linear Regression Games: Convergence Guarantees to Approximate Out-of-Distribution SolutionsPoster13 citations
294. Maximizing Agreements for Ranking, Clustering and Hierarchical Clustering via MAX-CUTPoster13 citations
295. On the Absence of Spurious Local Minima in Nonlinear Low-Rank Matrix Recovery ProblemsPoster13 citations
296. Provably Safe PAC-MDP Exploration Using AnalogiesPoster13 citations
297. Rao-Blackwellised parallel MCMCPoster13 citations
298. Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex OptimizationPoster13 citations
299. Spectral Tensor Train Parameterization of Deep Learning LayersPoster13 citations
300. Tracking Regret Bounds for Online Submodular OptimizationPoster13 citations
301. Wyner-Ziv Estimators: Efficient Distributed Mean Estimation with Side-InformationPoster13 citations
302. A Scalable Gradient Free Method for Bayesian Experimental Design with Implicit ModelsPoster12 citations
303. Alternating Direction Method of Multipliers for QuantizationPoster12 citations
304. Continuum-Armed Bandits: A Function Space PerspectivePoster12 citations
305. Convergence of Gaussian-smoothed optimal transport distance with sub-gamma distributions and dependent samplesPoster12 citations
306. Differentiable Greedy Algorithm for Monotone Submodular Maximization: Guarantees, Gradient Estimators, and ApplicationsPoster12 citations
307. Direct-Search for a Class of Stochastic Min-Max ProblemsPoster12 citations
308. Hierarchical Inducing Point Gaussian Process for Inter-domian ObservationsPoster12 citations
309. Non-Volume Preserving Hamiltonian Monte Carlo and No-U-TurnSamplersPoster12 citations
310. One-Round Communication Efficient Distributed M-EstimationPoster12 citations
311. Online probabilistic label treesPoster12 citations
312. Random Coordinate Underdamped Langevin Monte CarloPoster12 citations
313. Regret-Optimal FilteringPoster12 citations
314. Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual CalibrationPoster12 citations
315. SONIA: A Symmetric Blockwise Truncated Optimization AlgorithmPoster12 citations
316. The Base Measure Problem and its SolutionPoster12 citations
317. The Unexpected Deterministic and Universal Behavior of Large Softmax ClassifiersPoster12 citations
318. A Bayesian nonparametric approach to count-min sketch under power-law data streamsPoster11 citations
319. Efficient Balanced Treatment Assignments for ExperimentationPoster11 citations
320. Hierarchical Clustering via Sketches and Hierarchical Correlation ClusteringPoster11 citations
321. Latent Gaussian process with composite likelihoods and numerical quadraturePoster11 citations
322. Non-Stationary Off-Policy OptimizationPoster11 citations
323. One-Sketch-for-All: Non-linear Random Features from Compressed Linear MeasurementsPoster11 citations
324. Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMCPoster11 citations
325. Semi-Supervised Learning with Meta-GradientPoster11 citations
326. TenIPS: Inverse Propensity Sampling for Tensor CompletionPoster11 citations
327. Toward a General Theory of Online Selective Sampling: Trading Off Mistakes and QueriesPoster11 citations
328. Diagnostic Uncertainty Calibration: Towards Reliable Machine Predictions in Medical DomainPoster10 citations
329. Differentially Private Monotone Submodular Maximization Under Matroid and Knapsack ConstraintsPoster10 citations
330. Dual Principal Component Pursuit for Learning a Union of Hyperplanes: Theory and AlgorithmsPoster10 citations
331. Equitable and Optimal Transport with Multiple AgentsPoster10 citations
332. Explicit Regularization of Stochastic Gradient Methods through DualityPoster10 citations
333. False Discovery Rates in Biological NetworksPoster10 citations
334. Faster & More Reliable Tuning of Neural Networks: Bayesian Optimization with Importance SamplingPoster10 citations
335. Fenchel-Young Losses with Skewed Entropies for Class-posterior Probability EstimationPoster10 citations
336. GANs with Conditional Independence Graphs: On Subadditivity of Probability DivergencesPoster10 citations
337. Improving Classifier Confidence using Lossy Label-Invariant TransformationsPoster10 citations
338. Nearest Neighbour Based Estimates of Gradients: Sharp Nonasymptotic Bounds and ApplicationsPoster10 citations
339. Nonlinear Functional Output Regression: A Dictionary ApproachPoster10 citations
340. Private optimization without constraint violationsPoster10 citations
341. Robust hypothesis testing and distribution estimation in Hellinger distancePoster10 citations
342. Sample efficient learning of image-based diagnostic classifiers via probabilistic labelsPoster10 citations
343. Approximation Algorithms for Orthogonal Non-negative Matrix FactorizationPoster9 citations
344. Decision Making Problems with Funnel Structure: A Multi-Task Learning Approach with Application to Email Marketing CampaignsPoster9 citations
345. Good Classifiers are Abundant in the Interpolating RegimePoster9 citations
346. Inductive Mutual Information Estimation: A Convex Maximum-Entropy Copula ApproachPoster9 citations
347. Learning Matching Representations for Individualized Organ Transplantation AllocationPoster9 citations
348. Learning-to-Rank with Partitioned Preference: Fast Estimation for the Plackett-Luce ModelPoster9 citations
349. Location Trace Privacy Under Conditional PriorsPoster9 citations
350. Sample ElicitationPoster9 citations
351. Shadow Manifold Hamiltonian Monte CarloPoster9 citations
352. Sketch based Memory for Neural NetworksPoster9 citations
353. The Multiple Instance Learning Gaussian Process Probit ModelPoster9 citations
354. A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural NetsPoster8 citations
355. A comparative study on sampling with replacement vs Poisson sampling in optimal subsamplingPoster8 citations
356. A constrained risk inequality for general lossesPoster8 citations
357. Aggregating Incomplete and Noisy RankingsPoster8 citations
358. Causal Inference with Selectively Deconfounded DataPoster8 citations
359. Efficient Statistics for Sparse Graphical Models from Truncated SamplesPoster8 citations
360. Graph Community Detection from Coarse Measurements: Recovery Conditions for the Coarsened Weighted Stochastic Block ModelPoster8 citations
361. Improved Exploration in Factored Average-Reward MDPsPoster8 citations
362. Learning with risk-averse feedback under potentially heavy tailsPoster8 citations
363. Power of Hints for Online Learning with Movement CostsPoster8 citations
364. Robustness and scalability under heavy tails, without strong convexityPoster8 citations
365. Sequential Random Sampling Revisited: Hidden Shuffle MethodPoster8 citations
366. Stochastic Gradient Descent Meets Distribution RegressionPoster8 citations
367. The Sample Complexity of Level Set ApproximationPoster8 citations
368. The Teaching Dimension of Kernel PerceptronPoster8 citations
369. Understanding the wiring evolution in differentiable neural architecture searchPoster8 citations
370. A Variational Inference Approach to Learning Multivariate Wold ProcessesPoster7 citations
371. Differentially Private Weighted SamplingPoster7 citations
372. Efficient Designs Of SLOPE Penalty Sequences In Finite DimensionPoster7 citations
373. Efficient Interpolation of Density EstimatorsPoster7 citations
374. Exploiting Equality Constraints in Causal InferencePoster7 citations
375. Generalization of Quasi-Newton Methods: Application to Robust Symmetric Multisecant UpdatesPoster7 citations
376. Goodness-of-Fit Test for Mismatched Self-Exciting ProcessesPoster7 citations
377. Large Scale K-Median Clustering for Stable Clustering InstancesPoster7 citations
378. Learning the Truth From Only One Side of the StoryPoster7 citations
379. Meta-Learning Divergences for Variational InferencePoster7 citations
380. Nonparametric Variable Screening with Optimal Decision StumpsPoster7 citations
381. On the Memory Mechanism of Tensor-Power Recurrent ModelsPoster7 citations
382. Predictive Power of Nearest Neighbors Algorithm under Random PerturbationPoster7 citations
383. Regression Discontinuity Design under Self-selectionPoster7 citations
384. Robust Mean Estimation on Highly Incomplete Data with Arbitrary OutliersPoster7 citations
385. SDF-Bayes: Cautious Optimism in Safe Dose-Finding Clinical Trials with Drug Combinations and Heterogeneous Patient GroupsPoster7 citations
386. The Spectrum of Fisher Information of Deep Networks Achieving Dynamical IsometryPoster7 citations
387. Wasserstein Random Forests and Applications in Heterogeneous Treatment EffectsPoster7 citations
388. Contrastive learning of strong-mixing continuous-time stochastic processesPoster6 citations
389. Dynamic Cutset NetworksPoster6 citations
390. Gradient Descent in RKHS with Importance LabelingPoster6 citations
391. Hogwild! over Distributed Local Data Sets with Linearly Increasing Mini-Batch SizesPoster6 citations
392. Learning Shared Subgraphs in Ising Model PairsPoster6 citations
393. Logical Team Q-learning: An approach towards factored policies in cooperative MARLPoster6 citations
394. Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across LayersPoster6 citations
395. On the High Accuracy Limitation of Adaptive Property EstimationPoster6 citations
396. Cluster Trellis: Data Structures & Algorithms for Exact Inference in Hierarchical ClusteringPoster5 citations
397. Differentiating the Value Function by using Convex DualityPoster5 citations
398. Finding First-Order Nash Equilibria of Zero-Sum Games with the Regularized Nikaido-Isoda FunctionPoster5 citations
399. High-Dimensional Multi-Task Averaging and Application to Kernel Mean EmbeddingPoster5 citations
400. Hyperbolic graph embedding with enhanced semi-implicit variational inference.Poster5 citations
401. On the number of linear functions composing deep neural network: Towards a refined definition of neural networks complexityPoster5 citations
402. The Minecraft Kernel: Modelling correlated Gaussian Processes in the Fourier domainPoster5 citations
403. A Deterministic Streaming Sketch for Ridge RegressionPoster4 citations
404. A Hybrid Approximation to the Marginal LikelihoodPoster4 citations
405. Accelerating Metropolis-Hastings with Lightweight Inference CompilationPoster4 citations
406. Beyond Perturbation Stability: LP Recovery Guarantees for MAP Inference on Noisy Stable InstancesPoster4 citations
407. CONTRA: Contrarian statistics for controlled variable selectionPoster4 citations
408. Collaborative Classification from Noisy LabelsPoster4 citations
409. Deep Neural Networks Are Congestion Games: From Loss Landscape to Wardrop Equilibrium and BeyondPoster4 citations
410. Designing Transportable Experiments Under S-admissabilityPoster4 citations
411. Identification of Matrix Joint Block DiagonalizationPoster4 citations
412. Learning GPLVM with arbitrary kernels using the unscented transformationPoster4 citations
413. Statistical Guarantees for Transformation Based Models with applications to Implicit Variational InferencePoster4 citations
414. Unconstrained MAP Inference, Exponentiated Determinantal Point Processes, and Exponential InapproximabilityPoster4 citations
415. Adaptive Sampling for Fast Constrained Maximization of Submodular FunctionsPoster3 citations
416. Bayesian Model Averaging for Causality Estimation and its Approximation based on Gaussian Scale Mixture DistributionsPoster3 citations
417. Combinatorial Gaussian Process Bandits with Probabilistically Triggered ArmsPoster3 citations
418. DAG-Structured Clustering by Nearest NeighborsPoster3 citations
419. Exponential Convergence Rates of Classification Errors on Learning with SGD and Random FeaturesPoster3 citations
420. Fourier Bases for Solving Permutation PuzzlesPoster3 citations
421. Fully Gap-Dependent Bounds for Multinomial Logit BanditPoster3 citations
422. One-pass Stochastic Gradient Descent in overparametrized two-layer neural networksPoster3 citations
423. Principal Component Regression with Semirandom Observations via Matrix CompletionPoster3 citations
424. Probabilistic Sequential Matrix FactorizationPoster3 citations
425. Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture ModelsPoster3 citations
426. Self-Supervised Steering Angle Prediction for Vehicle Control Using Visual OdometryPoster3 citations
427. Active Learning with Maximum Margin Sparse Gaussian ProcessesPoster2 citations
428. Associative Convolutional LayersPoster2 citations
429. CWY Parametrization: a Solution for Parallelized Optimization of Orthogonal and Stiefel MatricesPoster2 citations
430. Deep Spectral RankingPoster2 citations
431. Dirichlet Pruning for Convolutional Neural NetworksPoster2 citations
432. Influence Decompositions For Neural Network AttributionPoster2 citations
433. Learning Bijective Feature Maps for Linear ICAPoster2 citations
434. List Learning with Attribute NoisePoster2 citations
435. Misspecification in Prediction Problems and Robustness via Improper LearningPoster2 citations
436. Moment-Based Variational Inference for Stochastic Differential EquationsPoster2 citations
437. On the Faster Alternating Least-Squares for CCAPoster2 citations
438. Prediction with Finitely many Errors Almost SurelyPoster2 citations
439. Principal Subspace Estimation Under Information DiffusionPoster2 citations
440. The Sample Complexity of Meta Sparse RegressionPoster2 citations
441. Understanding Robustness in Teacher-Student Setting: A New PerspectivePoster2 citations
442. A Contraction Approach to Model-based Reinforcement LearningPoster1 citations
443. Causal Modeling with Stochastic ConfoundersPoster1 citations
444. Context-Specific Likelihood WeightingPoster1 citations
445. DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural NetworksPoster1 citations
446. Nested Barycentric Coordinate System as an Explicit Feature MapPoster1 citations
447. On the Consistency of Metric and Non-Metric K-MedoidsPoster1 citations
448. Training a Single Bandit ArmPoster1 citations
449. Feedback Coding for Active LearningPoster
450. Graph Gamma Process Linear Dynamical SystemsPoster
451. Improving predictions of Bayesian neural nets via local linearizationPoster
452. Offline detection of change-points in the mean for stationary graph signals.Poster
453. On the convergence of the Metropolis algorithm with fixed-order updates for multivariate binary probability distributionsPoster
454. Robust Learning under Strong Noise via SQsPoster
455. Why did the distribution change?Poster

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