AISTATS 2019 Accepted Papers

The full list of 360 papers accepted at AISTATS 2019 (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. Interpolating between Optimal Transport and MMD using Sinkhorn DivergencesPoster698 citations
2. Towards Efficient Data Valuation Based on the Shapley ValuePoster570 citations
3. Lagrange Coded Computing: Optimal Design for Resiliency, Security, and PrivacyPoster470 citations
4. Subsampled Renyi Differential Privacy and Analytical Moments AccountantPoster463 citations
5. Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive FlowsPoster438 citations
6. Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive LearningPoster405 citations
7. Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated PerceptronPoster390 citations
8. On the Convergence of Stochastic Gradient Descent with Adaptive StepsizesPoster376 citations
9. Sample Complexity of Sinkhorn DivergencesPoster362 citations
10. Truncated Back-propagation for Bilevel OptimizationPoster319 citations
11. Evaluating model calibration in classificationPoster281 citations
12. Fisher-Rao Metric, Geometry, and Complexity of Neural NetworksPoster274 citations
13. Does data interpolation contradict statistical optimality?Poster269 citations
14. Interaction Matters: A Note on Non-asymptotic Local Convergence of Generative Adversarial NetworksPoster249 citations
15. Unsupervised Alignment of Embeddings with Wasserstein ProcrustesPoster248 citations
16. Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic SystemsPoster243 citations
17. Avoiding Latent Variable Collapse with Generative Skip ModelsPoster229 citations
18. Learning Controllable Fair RepresentationsPoster223 citations
19. Negative Momentum for Improved Game DynamicsPoster223 citations
20. Support and Invertibility in Domain-Invariant RepresentationsPoster223 citations
21. Probabilistic Forecasting with Spline Quantile Function RNNsPoster216 citations
22. Optimal Transport for Multi-source Domain Adaptation under Target ShiftPoster198 citations
23. Hadamard Response: Estimating Distributions Privately, Efficiently, and with Little CommunicationPoster197 citations
24. Provable Robustness of ReLU networks via Maximization of Linear RegionsPoster195 citations
25. Deep Neural Networks Learn Non-Smooth Functions EffectivelyPoster192 citations
26. Convergence of Gradient Descent on Separable DataPoster186 citations
27. Attenuating Bias in Word vectorsPoster185 citations
28. Distilling Policy DistillationPoster179 citations
29. Learning to Optimize under Non-StationarityPoster179 citations
30. Preventing Failures Due to Dataset Shift: Learning Predictive Models That TransportPoster174 citations
31. Structured Disentangled RepresentationsPoster169 citations
32. Learning One-hidden-layer ReLU Networks via Gradient DescentPoster163 citations
33. A Continuous-Time View of Early Stopping for Least Squares RegressionPoster157 citations
34. Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field ApproachPoster157 citations
35. A Topological Regularizer for Classifiers via Persistent HomologyPoster156 citations
36. A General Framework for Multi-fidelity Bayesian Optimization with Gaussian ProcessesPoster149 citations
37. Linear Convergence of the Primal-Dual Gradient Method for Convex-Concave Saddle Point Problems without Strong ConvexityPoster147 citations
38. Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary BanditPoster146 citations
39. Resampled Priors for Variational AutoencodersPoster143 citations
40. Local Saddle Point Optimization: A Curvature Exploitation ApproachPoster142 citations
41. An Optimal Algorithm for Stochastic and Adversarial BanditsPoster135 citations
42. Can You Trust This Prediction? Auditing Pointwise Reliability After LearningPoster133 citations
43. A Swiss Army Infinitesimal JackknifePoster130 citations
44. Interpreting Black Box Predictions using Fisher KernelsPoster123 citations
45. Interval Estimation of Individual-Level Causal Effects Under Unobserved ConfoundingPoster122 citations
46. Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning RatePoster120 citations
47. Exponential convergence rates for Batch Normalization: The power of length-direction decoupling in non-convex optimizationPoster112 citations
48. Model-Free Linear Quadratic Control via Reduction to Expert PredictionPoster101 citations
49. Reparameterizing Distributions on Lie GroupsPoster101 citations
50. Auto-Encoding Total Correlation ExplanationPoster100 citations
51. Causal Discovery in the Presence of Missing DataPoster97 citations
52. Defending against Whitebox Adversarial Attacks via Randomized DiscretizationPoster96 citations
53. Large-Margin Classification in Hyperbolic SpacePoster94 citations
54. An Online Algorithm for Smoothed Regression and LQR ControlPoster93 citations
55. Statistical Optimal Transport via Factored CouplingsPoster89 citations
56. Towards Optimal Transport with Global InvariancesPoster87 citations
57. ABCD-Strategy: Budgeted Experimental Design for Targeted Causal Structure DiscoveryPoster86 citations
58. SPONGE: A generalized eigenproblem for clustering signed networksPoster85 citations
59. Variance reduction properties of the reparameterization trickPoster85 citations
60. What made you do this? Understanding black-box decisions with sufficient input subsetsPoster85 citations
61. On Theory for BARTPoster83 citations
62. Sample-Efficient Imitation Learning via Generative Adversarial NetsPoster81 citations
63. XBART: Accelerated Bayesian Additive Regression TreesPoster81 citations
64. A Potential Outcomes Calculus for Identifying Conditional Path-Specific EffectsPoster79 citations
65. Adversarial Variational Optimization of Non-Differentiable SimulatorsPoster76 citations
66. Faster First-Order Methods for Stochastic Non-Convex Optimization on Riemannian ManifoldsPoster76 citations
67. Test without Trust: Optimal Locally Private Distribution TestingPoster75 citations
68. Rotting bandits are no harder than stochastic onesPoster73 citations
69. Stochastic Negative Mining for Learning with Large Output SpacesPoster72 citations
70. Unbiased Implicit Variational InferencePoster72 citations
71. Nonconvex Matrix Factorization from Rank-One MeasurementsPoster70 citations
72. Variable selection for Gaussian processes via sensitivity analysis of the posterior predictive distributionPoster69 citations
73. Knockoffs for the Mass: New Feature Importance Statistics with False Discovery GuaranteesPoster68 citations
74. Locally Private Mean Estimation: $Z$-test and Tight Confidence IntervalsPoster67 citations
75. Stochastic Variance-Reduced Cubic Regularization for Nonconvex OptimizationPoster67 citations
76. Active Exploration in Markov Decision ProcessesPoster65 citations
77. Efficient Bayesian Experimental Design for Implicit ModelsPoster65 citations
78. Matroids, Matchings, and FairnessPoster65 citations
79. The Termination CriticPoster65 citations
80. Uncertainty Autoencoders: Learning Compressed Representations via Variational Information MaximizationPoster63 citations
81. Bayesian optimisation under uncertain inputsPoster62 citations
82. Direct Acceleration of SAGA using Sampled Negative MomentumPoster62 citations
83. Linear Queries Estimation with Local Differential PrivacyPoster62 citations
84. On Multi-Cause Approaches to Causal Inference with Unobserved Counfounding: Two Cautionary Failure Cases and A Promising AlternativePoster62 citations
85. On the Connection Between Learning Two-Layer Neural Networks and Tensor DecompositionPoster60 citations
86. Wasserstein regularization for sparse multi-task regressionPoster60 citations
87. Bandit Online Learning with Unknown DelaysPoster59 citations
88. Doubly Semi-Implicit Variational InferencePoster59 citations
89. Contrasting Exploration in Parameter and Action Space: A Zeroth-Order Optimization PerspectivePoster57 citations
90. Credit Assignment Techniques in Stochastic Computation GraphsPoster56 citations
91. Foundations of Sequence-to-Sequence Modeling for Time SeriesPoster56 citations
92. Online Learning in Kernelized Markov Decision ProcessesPoster56 citations
93. Safe Convex Learning under Uncertain ConstraintsPoster56 citations
94. Deep learning with differential Gaussian process flowsPoster55 citations
95. Fast Gaussian process based gradient matching for parameter identification in systems of nonlinear ODEsPoster55 citations
96. Calibrating Deep Convolutional Gaussian ProcessesPoster54 citations
97. Confidence Scoring Using Whitebox Meta-models with Linear Classifier ProbesPoster54 citations
98. Confidence-based Graph Convolutional Networks for Semi-Supervised LearningPoster54 citations
99. Implicit Kernel LearningPoster54 citations
100. Improving the Stability of the Knockoff Procedure: Multiple Simultaneous Knockoffs and Entropy MaximizationPoster54 citations
101. Training a Spiking Neural Network with Equilibrium PropagationPoster54 citations
102. Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and AlgorithmsPoster53 citations
103. Orthogonal Estimation of Wasserstein DistancesPoster53 citations
104. Revisit Batch Normalization: New Understanding and Refinement via Composition OptimizationPoster53 citations
105. The Gaussian Process Autoregressive Regression Model (GPAR)Poster52 citations
106. Accelerated Decentralized Optimization with Local Updates for Smooth and Strongly Convex ObjectivesPoster51 citations
107. Fast and Robust Shortest Paths on Manifolds Learned from DataPoster51 citations
108. On Connecting Stochastic Gradient MCMC and Differential PrivacyPoster51 citations
109. Hierarchical Clustering for Euclidean DataPoster50 citations
110. Know Your Boundaries: Constraining Gaussian Processes by Variational Harmonic FeaturesPoster50 citations
111. Connecting Weighted Automata and Recurrent Neural Networks through Spectral LearningPoster49 citations
112. Fisher Information and Natural Gradient Learning in Random Deep NetworksPoster49 citations
113. Accelerated Coordinate Descent with Arbitrary Sampling and Best Rates for MinibatchesPoster48 citations
114. Deep Neural Networks with Multi-Branch Architectures Are Intrinsically Less Non-ConvexPoster48 citations
115. Scalable High-Order Gaussian Process RegressionPoster48 citations
116. Sobolev DescentPoster48 citations
117. Towards Gradient Free and Projection Free Stochastic OptimizationPoster48 citations
118. Theoretical Analysis of Efficiency and Robustness of Softmax and Gap-Increasing Operators in Reinforcement LearningPoster45 citations
119. Restarting Frank-WolfePoster44 citations
120. Distributionally Robust Submodular MaximizationPoster43 citations
121. Kernel Exponential Family Estimation via Doubly Dual EmbeddingPoster43 citations
122. Bayesian Learning of Neural Network ArchitecturesPoster42 citations
123. Projection-Free Bandit Convex OptimizationPoster42 citations
124. Structured Robust Submodular Maximization: Offline and Online AlgorithmsPoster42 citations
125. A Thompson Sampling Algorithm for Cascading BanditsPoster41 citations
126. Are we there yet? Manifold identification of gradient-related proximal methodsPoster41 citations
127. An Optimal Control Approach to Sequential Machine TeachingPoster40 citations
128. Banded Matrix Operators for Gaussian Markov Models in the Automatic Differentiation EraPoster40 citations
129. Efficient Bayesian Optimization for Target Vector EstimationPoster40 citations
130. Low-Precision Random Fourier Features for Memory-constrained Kernel ApproximationPoster40 citations
131. On Target Shift in Adversarial Domain AdaptationPoster40 citations
132. Optimal Noise-Adding Mechanism in Additive Differential PrivacyPoster40 citations
133. Database Alignment with Gaussian FeaturesPoster39 citations
134. Data-Driven Approach to Multiple-Source Domain AdaptationPoster38 citations
135. On the Dynamics of Gradient Descent for AutoencodersPoster38 citations
136. Risk-Averse Stochastic Convex BanditPoster38 citations
137. Active Ranking with Subset-wise PreferencesPoster37 citations
138. Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation FunctionPoster37 citations
139. Region-Based Active LearningPoster37 citations
140. Risk-Sensitive Generative Adversarial Imitation LearningPoster37 citations
141. Testing Conditional Independence on Discrete Data using Stochastic ComplexityPoster37 citations
142. Temporal Quilting for Survival AnalysisPoster36 citations
143. $β^3$-IRT: A New Item Response Model and its ApplicationsPoster35 citations
144. Complexities in Projection-Free Stochastic Non-convex MinimizationPoster35 citations
145. Learning One-hidden-layer Neural Networks under General Input DistributionsPoster35 citations
146. Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions 2: Numerical integratorsPoster35 citations
147. Projection Free Online Learning over Smooth SetsPoster35 citations
148. Low-Dimensional Density Ratio Estimation for Covariate Shift CorrectionPoster34 citations
149. Revisiting Adversarial RiskPoster34 citations
150. Efficient Greedy Coordinate Descent for Composite ProblemsPoster33 citations
151. LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable ModelsPoster33 citations
152. Autoencoding any Data through Kernel AutoencodersPoster32 citations
153. Globally-convergent Iteratively Reweighted Least Squares for Robust Regression ProblemsPoster32 citations
154. Improving Quadrature for Constrained IntegrandsPoster32 citations
155. Inferring Multidimensional Rates of Aging from Cross-Sectional DataPoster32 citations
156. Inverting Supervised Representations with Autoregressive Neural Density ModelsPoster32 citations
157. A Fast Sampling Algorithm for Maximum Inner Product SearchPoster31 citations
158. Non-linear process convolutions for multi-output Gaussian processesPoster31 citations
159. Distributional reinforcement learning with linear function approximationPoster30 citations
160. High-dimensional Mixed Graphical Model with Ordinal Data: Parameter Estimation and Statistical InferencePoster30 citations
161. Learning Mixtures of Smooth Product Distributions: Identifiability and AlgorithmPoster30 citations
162. Analysis of Thompson Sampling for Combinatorial Multi-armed Bandit with Probabilistically Triggered ArmsPoster29 citations
163. Imitation-Regularized Offline LearningPoster29 citations
164. No-regret algorithms for online $k$-submodular maximizationPoster29 citations
165. Robust descent using smoothed multiplicative noisePoster29 citations
166. Two-temperature logistic regression based on the Tsallis divergencePoster29 citations
167. Interpretable Almost-Exact Matching for Causal InferencePoster28 citations
168. Overcomplete Independent Component Analysis via SDPPoster28 citations
169. Unbiased Smoothing using Particle Independent Metropolis-HastingsPoster28 citations
170. A new evaluation framework for topic modeling algorithms based on synthetic corporaPoster27 citations
171. Bridging the gap between regret minimization and best arm identification, with application to A/B testsPoster27 citations
172. Identifiability of Generalized Hypergeometric Distribution (GHD) Directed Acyclic Graphical ModelsPoster27 citations
173. On Structure Priors for Learning Bayesian NetworksPoster27 citations
174. Support Localization and the Fisher Metric for off-the-grid Sparse RegularizationPoster27 citations
175. Accelerating Imitation Learning with Predictive ModelsPoster26 citations
176. Data-dependent compression of random features for large-scale kernel approximationPoster26 citations
177. Gaussian Process Latent Variable Alignment LearningPoster26 citations
178. Online learning with feedback graphs and switching costsPoster26 citations
179. Probabilistic Multilevel Clustering via Composite Transportation DistancePoster26 citations
180. Scalable Thompson Sampling via Optimal TransportPoster26 citations
181. Sequential Patient Recruitment and Allocation for Adaptive Clinical TrialsPoster26 citations
182. Top Feasible Arm IdentificationPoster26 citations
183. $HS^2$: Active learning over hypergraphs with pointwise and pairwise queriesPoster25 citations
184. Adaptive Ensemble Prediction for Deep Neural Networks based on Confidence LevelPoster25 citations
185. Batched Stochastic Bayesian Optimization via Combinatorial Constraints DesignPoster25 citations
186. Exploring Fast and Communication-Efficient Algorithms in Large-Scale Distributed NetworksPoster25 citations
187. Forward Amortized Inference for Likelihood-Free Variational MarginalizationPoster25 citations
188. Learning the Structure of a Nonstationary Vector AutoregressionPoster25 citations
189. Online Decentralized Leverage Score Sampling for Streaming Multidimensional Time SeriesPoster25 citations
190. A Geometric Perspective on the Transferability of Adversarial DirectionsPoster24 citations
191. Multitask Metric Learning: Theory and AlgorithmPoster24 citations
192. A Unified Weight Learning Paradigm for Multi-view LearningPoster23 citations
193. Noisy Blackbox Optimization using Multi-fidelity Queries: A Tree Search ApproachPoster23 citations
194. Sampling from Non-Log-Concave Distributions via Variance-Reduced Gradient Langevin DynamicsPoster23 citations
195. A Robust Zero-Sum Game Framework for Pool-based Active LearningPoster22 citations
196. A Stein–Papangelou Goodness-of-Fit Test for Point ProcessesPoster22 citations
197. Efficient Linear Bandits through Matrix SketchingPoster22 citations
198. Graph to Graph: a Topology Aware Approach for Graph Structures Learning and GenerationPoster22 citations
199. Probabilistic Semantic Inpainting with Pixel Constrained CNNsPoster22 citations
200. Binary Space Partitioning ForestPoster21 citations
201. Clustering Time Series with Nonlinear Dynamics: A Bayesian Non-Parametric and Particle-Based ApproachPoster21 citations
202. Interaction Detection with Bayesian Decision Tree EnsemblesPoster21 citations
203. Representation Learning on Graphs: A Reinforcement Learning ApplicationPoster21 citations
204. Sharp Analysis of Learning with Discrete LossesPoster21 citations
205. Gaussian Process Modulated Cox Processes under Linear Inequality ConstraintsPoster20 citations
206. Statistical Learning under Nonstationary Mixing ProcessesPoster20 citations
207. Adaptive Estimation for Approximate $k$-Nearest-Neighbor ComputationsPoster19 citations
208. Adaptive Gaussian Copula ABCPoster19 citations
209. Domain-Size Aware Markov Logic NetworksPoster19 citations
210. Harmonizable mixture kernels with variational Fourier featuresPoster19 citations
211. Multiscale Gaussian Process Level Set EstimationPoster19 citations
212. Renyi Differentially Private ERM for Smooth ObjectivesPoster19 citations
213. Scalable Gaussian Process Inference with Finite-data Mean and Variance GuaranteesPoster19 citations
214. Semi-Generative Modelling: Covariate-Shift Adaptation with Cause and Effect FeaturesPoster19 citations
215. A Higher-Order Kolmogorov-Smirnov TestPoster18 citations
216. A maximum-mean-discrepancy goodness-of-fit test for censored dataPoster18 citations
217. Adversarial Discrete Sequence Generation without Explicit NeuralNetworks as DiscriminatorsPoster18 citations
218. Adversarial Learning of a Sampler Based on an Unnormalized DistributionPoster18 citations
219. Boosting Transfer Learning with Survival Data from Heterogeneous DomainsPoster18 citations
220. Consistent Online Optimization: Convex and SubmodularPoster18 citations
221. Correcting the bias in least squares regression with volume-rescaled samplingPoster18 citations
222. High Dimensional Inference in Partially Linear ModelsPoster18 citations
223. Learning Tree Structures from Noisy DataPoster18 citations
224. Performance Metric Elicitation from Pairwise Classifier ComparisonsPoster18 citations
225. A Memoization Framework for Scaling Submodular Optimization to Large Scale ProblemsPoster17 citations
226. Decentralized Gradient Tracking for Continuous DR-Submodular MaximizationPoster17 citations
227. Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational InferencePoster17 citations
228. Lovasz Convolutional NetworksPoster17 citations
229. Probabilistic Riemannian submanifold learning with wrapped Gaussian process latent variable modelsPoster17 citations
230. Variational Noise-Contrastive EstimationPoster17 citations
231. Computation Efficient Coded Linear TransformPoster16 citations
232. Designing Optimal Binary Rating SystemsPoster16 citations
233. Exploring $k$ out of Top $ρ$ Fraction of Arms in Stochastic BanditsPoster16 citations
234. From Cost-Sensitive to Tight F-measure BoundsPoster16 citations
235. Generalizing the theory of cooperative inferencePoster16 citations
236. On Constrained Nonconvex Stochastic Optimization: A Case Study for Generalized Eigenvalue DecompositionPoster16 citations
237. On Kernel Derivative Approximation with Random Fourier FeaturesPoster16 citations
238. Pathwise Derivatives for Multivariate DistributionsPoster16 citations
239. Vine copula structure learning via Monte Carlo tree searchPoster16 citations
240. Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process ModelsPoster15 citations
241. Cost aware Inference for IoT DevicesPoster15 citations
242. Infinite Task Learning in RKHSsPoster15 citations
243. Proximal Splitting Meets Variance ReductionPoster15 citations
244. Reducing training time by efficient localized kernel regressionPoster15 citations
245. Semi-supervised clustering for de-duplicationPoster15 citations
246. The LORACs Prior for VAEs: Letting the Trees Speak for the DataPoster15 citations
247. Bayesian Learning of Conditional Kernel Mean Embeddings for Automatic Likelihood-Free InferencePoster14 citations
248. Bounding Inefficiency of Equilibria in Continuous Actions Games using Submodularity and CurvaturePoster14 citations
249. Correspondence Analysis Using Neural NetworksPoster14 citations
250. Learning Invariant Representations with Kernel WarpingPoster14 citations
251. Online Algorithm for Unsupervised Sensor SelectionPoster14 citations
252. Regularized Contextual BanditsPoster14 citations
253. Best of many worlds: Robust model selection for online supervised learningPoster13 citations
254. Conservative Exploration using InterleavingPoster13 citations
255. Differentially Private Online Submodular MinimizationPoster13 citations
256. Efficient Inference in Multi-task Cox Process ModelsPoster13 citations
257. Lifting high-dimensional non-linear models with Gaussian regressorsPoster13 citations
258. Model Consistency for Learning with Mirror-Stratifiable RegularizersPoster13 citations
259. Modularity-based Sparse Soft Graph ClusteringPoster13 citations
260. Reversible Jump Probabilistic ProgrammingPoster13 citations
261. Size of Interventional Markov Equivalence Classes in random DAG modelsPoster13 citations
262. Structured Neural Topic Models for ReviewsPoster13 citations
263. The non-parametric bootstrap and spectral analysis in moderate and high-dimensionPoster13 citations
264. Amortized Variational Inference with Graph Convolutional Networks for Gaussian ProcessesPoster12 citations
265. An Optimal Algorithm for Stochastic Three-Composite OptimizationPoster12 citations
266. Classifying Signals on Irregular Domains via Convolutional Cluster PoolingPoster12 citations
267. Empirical Risk Minimization and Stochastic Gradient Descent for Relational DataPoster12 citations
268. Fast Stochastic Algorithms for Low-rank and Nonsmooth Matrix ProblemsPoster12 citations
269. Fixing Mini-batch Sequences with Hierarchical Robust PartitioningPoster12 citations
270. Graph Embedding with Shifted Inner Product Similarity and Its Improved Approximation CapabilityPoster12 citations
271. Scalable Bayesian Learning for State Space Models using Variational Inference with SMC SamplersPoster12 citations
272. Stochastic Gradient Descent with Exponential Convergence Rates of Expected Classification ErrorsPoster12 citations
273. Variational Information Planning for Sequential Decision MakingPoster12 citations
274. Distributed Inexact Newton-type Pursuit for Non-convex Sparse LearningPoster11 citations
275. Efficient Nonconvex Empirical Risk Minimization via Adaptive Sample Size MethodsPoster11 citations
276. Estimating Network Structure from Incomplete Event DataPoster11 citations
277. Feature subset selection for the multinomial logit model via mixed-integer optimizationPoster11 citations
278. Learning Natural Programs from a Few Examples in Real-TimePoster11 citations
279. Near Optimal Algorithms for Hard Submodular Programs with Discounted Cooperative CostsPoster11 citations
280. Precision Matrix Estimation with Noisy and Missing DataPoster11 citations
281. Stochastic algorithms with descent guarantees for ICAPoster11 citations
282. A Family of Exact Goodness-of-Fit Tests for High-Dimensional Discrete DistributionsPoster10 citations
283. Black Box Quantiles for Kernel LearningPoster10 citations
284. Interpretable Cascade Classifiers with AbstentionPoster10 citations
285. Learning Determinantal Point Processes by Corrective Negative SamplingPoster10 citations
286. Learning Influence-Receptivity Network Structure with GuaranteePoster10 citations
287. Finding the bandit in a graph: Sequential search-and-stopPoster9 citations
288. Iterative Bayesian Learning for Crowdsourced RegressionPoster9 citations
289. Online Multiclass Boosting with Bandit FeedbackPoster9 citations
290. Optimizing over a Restricted Policy Class in MDPsPoster9 citations
291. Sparse Feature Selection in Kernel Discriminant Analysis via Optimal ScoringPoster9 citations
292. Towards Understanding the Generalization Bias of Two Layer Convolutional Linear Classifiers with Gradient DescentPoster9 citations
293. Detection of Planted Solutions for Flat Satisfiability ProblemsPoster8 citations
294. Estimation of Non-Normalized Mixture ModelsPoster8 citations
295. Improved Semi-Supervised Learning with Multiple GraphsPoster8 citations
296. Lifted Weight Learning of Markov Logic Networks RevisitedPoster8 citations
297. Minimum Volume Topic ModelingPoster8 citations
298. Pseudo-Bayesian Learning with Kernel Fourier Transform as PriorPoster8 citations
299. Robust Graph Embedding with Noisy Link WeightsPoster8 citations
300. Robust Matrix Completion from Quantized ObservationsPoster8 citations
301. Robustness Guarantees for Density ClusteringPoster8 citations
302. Adaptive Minimax Regret against Smooth Logarithmic Losses over High-Dimensional l1-Balls via Envelope ComplexityPoster7 citations
303. Analysis of Network Lasso for Semi-Supervised RegressionPoster7 citations
304. Deep Topic Models for Multi-label LearningPoster7 citations
305. Error bounds for sparse classifiers in high-dimensionsPoster7 citations
306. Fast Algorithms for Sparse Reduced-Rank RegressionPoster7 citations
307. Greedy and IHT Algorithms for Non-convex Optimization with Monotone Costs of Non-zerosPoster7 citations
308. KAMA-NNs: Low-dimensional Rotation Based Neural NetworksPoster7 citations
309. Lifelong Optimization with Low RegretPoster7 citations
310. Logarithmic Regret for Online Gradient Descent Beyond Strong ConvexityPoster7 citations
311. Markov Properties of Discrete Determinantal Point ProcessesPoster7 citations
312. Modeling simple structures and geometry for better stochastic optimization algorithmsPoster7 citations
313. Nonlinear Acceleration of Primal-Dual AlgorithmsPoster7 citations
314. Optimal Minimization of the Sum of Three Convex Functions with a Linear OperatorPoster7 citations
315. Optimal Testing in the Experiment-rich RegimePoster7 citations
316. Optimization of Inf-Convolution Regularized Nonconvex Composite ProblemsPoster7 citations
317. Partial Optimality of Dual Decomposition for MAP Inference in Pairwise MRFsPoster7 citations
318. Universal Hypothesis Testing with Kernels: Asymptotically Optimal Tests for Goodness of FitPoster7 citations
319. AutoML from Service Provider’s Perspective: Multi-device, Multi-tenant Model Selection with GP-EIPoster6 citations
320. Block Stability for MAP InferencePoster6 citations
321. Conditional Sparse $L_p$-norm Regression With Optimal ProbabilityPoster6 citations
322. Gain estimation of linear dynamical systems using Thompson SamplingPoster6 citations
323. On Euclidean k-Means Clustering with alpha-Center ProximityPoster6 citations
324. Sparse Multivariate Bernoulli Processes in High DimensionsPoster6 citations
325. Bernoulli Race Particle FiltersPoster5 citations
326. Blind Demixing via Wirtinger Flow with Random InitializationPoster5 citations
327. Efficient Bayes Risk Estimation for Cost-Sensitive ClassificationPoster5 citations
328. Extreme Stochastic Variational Inference: Distributed Inference for Large Scale Mixture ModelsPoster5 citations
329. Generalized Boltzmann Machine with Deep Neural StructurePoster5 citations
330. MaxHedge: Maximizing a Maximum OnlinePoster5 citations
331. Multi-Task Time Series Analysis applied to Drug Response ModellingPoster5 citations
332. Statistical Windows in Testing for the Initial Distribution of a Reversible Markov ChainPoster5 citations
333. Towards a Theoretical Understanding of Hashing-Based Neural NetsPoster5 citations
334. Training Variational Autoencoders with Buffered Stochastic Variational InferencePoster5 citations
335. Augmented Ensemble MCMC sampling in Factorial Hidden Markov ModelsPoster4 citations
336. Classification using margin pursuitPoster4 citations
337. Towards Clustering High-dimensional Gaussian Mixture Clouds in Linear Running TimePoster4 citations
338. A Bayesian model for sparse graphs with flexible degree distribution and overlapping community structurePoster3 citations
339. Active Probabilistic Inference on Matrices for Pre-Conditioning in Stochastic OptimizationPoster3 citations
340. Adaptive Rao-Blackwellisation in Gibbs Sampling for Probabilistic Graphical ModelsPoster3 citations
341. Least Squares Estimation of Weakly Convex FunctionsPoster3 citations
342. Multi-Observation RegressionPoster3 citations
343. Multi-Order Information for Working Set Selection of Sequential Minimal OptimizationPoster3 citations
344. Parallel Asynchronous Stochastic Coordinate Descent with Auxiliary VariablesPoster3 citations
345. Recovery Guarantees For Quadratic Tensors With Sparse ObservationsPoster3 citations
346. SMOGS: Social Network Metrics of Game SuccessPoster3 citations
347. A recurrent Markov state-space generative model for sequencesPoster2 citations
348. SpikeCaKe: Semi-Analytic Nonparametric Bayesian Inference for Spike-Spike Neuronal ConnectivityPoster2 citations
349. Active multiple matrix completion with adaptive confidence setsPoster1 citations
350. Adaptive MCMC via Combining Local SamplersPoster1 citations
351. Conditionally Independent Multiresolution Gaussian ProcessesPoster1 citations
352. On the Interaction Effects Between Prediction and ClusteringPoster1 citations
353. Sample Efficient Graph-Based Optimization with Noisy ObservationsPoster1 citations
354. Sketching for Latent Dirichlet-Categorical ModelsPoster1 citations
355. Tossing Coins Under MonotonicityPoster1 citations
356. Deep Switch Networks for Generating Discrete Data and LanguagePoster
357. Distributed Maximization of "Submodular plus Diversity" Functions for Multi-label Feature Selection on Huge DatasetsPoster
358. Exponential Weights on the Hypercube in Polynomial TimePoster
359. Gaussian Regression with Convex ConstraintsPoster
360. Learning Rules-First ClassifiersPoster

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