UAI 2022 Accepted Papers

The full list of 230 papers accepted at UAI 2022 (Conference on Uncertainty in Artificial Intelligence). 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. Bayesian structure learning with generative flow networksPoster169 citations
2. Multi-objective Bayesian optimization over high-dimensional search spacesPoster141 citations
3. On the effectiveness of adversarial training against common corruptionsPoster124 citations
4. Faster non-convex federated learning via global and local momentumPoster106 citations
5. Fedvarp: Tackling the variance due to partial client participation in federated learningPoster72 citations
6. Greedy relaxations of the sparsest permutation algorithmPoster66 citations
7. Conditional simulation using diffusion Schrödinger bridgesPoster61 citations
8. Multi-source domain adaptation via weighted joint distributions optimal transportPoster47 citations
9. Offline reinforcement learning under value and density-ratio realizability: The power of gapsPoster45 citations
10. Data dependent randomized smoothingPoster43 citations
11. Fast predictive uncertainty for classification with Bayesian deep networksPoster43 citations
12. Stability of SGD: Tightness analysis and improved boundsPoster41 citations
13. Quantification of Credal Uncertainty in Machine Learning: A Critical Analysis and Empirical ComparisonPoster40 citations
14. Neuro-symbolic entropy regularizationPoster39 citations
15. How unfair is private learning?Poster38 citations
16. CounteRGAN: Generating counterfactuals for real-time recourse and interpretability using residual GANsPoster37 citations
17. Calibrated ensembles can mitigate accuracy tradeoffs under distribution shiftPoster36 citations
18. Data augmentation in Bayesian neural networks and the cold posterior effectPoster36 citations
19. Discovery of extended summary graphs in time seriesPoster34 citations
20. Bayesian quantile and expectile optimisationPoster33 citations
21. Generalizing off-policy learning under sample selection biasPoster32 citations
22. A free lunch from the noise: Provable and practical exploration for representation learningPoster29 citations
23. Meta-learning without data via Wasserstein distributionally-robust model fusionPoster29 citations
24. Physics guided neural networks for spatio-temporal super-resolution of turbulent flowsPoster29 citations
25. SENTINEL: taming uncertainty with ensemble based distributional reinforcement learningPoster29 citations
26. Differentially private SGDA for minimax problemsPoster28 citations
27. Inductive synthesis of finite-state controllers for POMDPsPoster28 citations
28. Learning invariant weights in neural networksPoster28 citations
29. ResIST: Layer-wise decomposition of ResNets for distributed trainingPoster28 citations
30. Robust textual embedding against word-level adversarial attacksPoster26 citations
31. Variational multiple shooting for Bayesian ODEs with Gaussian processesPoster26 citations
32. Deterministic policy gradient: Convergence analysisPoster25 citations
33. Privacy-aware compression for federated data analysisPoster25 citations
34. Understanding and mitigating the limitations of prioritized experience replayPoster25 citations
35. An explore-then-commit algorithm for submodular maximization under full-bandit feedbackPoster24 citations
36. Federated online clustering of banditsPoster24 citations
37. Robust Bayesian recoursePoster24 citations
38. Shoring up the foundations: fusing model embeddings and weak supervisionPoster24 citations
39. Bayesian federated estimation of causal effects from observational dataPoster23 citations
40. Greedy equivalence search in the presence of latent confoundersPoster23 citations
41. Local calibration: metrics and recalibrationPoster23 citations
42. Cross-domain adaptive transfer reinforcement learning based on state-action correspondencePoster22 citations
43. Towards unsupervised open world semantic segmentationPoster22 citations
44. Near-optimal Thompson sampling-based algorithms for differentially private stochastic banditsPoster20 citations
45. Regret guarantees for model-based reinforcement learning with long-term average constraintsPoster20 citations
46. SASH: Efficient secure aggregation based on SHPRG for federated learningPoster20 citations
47. A causal bandit approach to learning good atomic interventions in presence of unobserved confoundersPoster19 citations
48. Causal discovery with heterogeneous observational dataPoster19 citations
49. Distributed adversarial training to robustify deep neural networks at scalePoster19 citations
50. Mutation-driven follow the regularized leader for last-iterate convergence in zero-sum gamesPoster19 citations
51. The optimal noise in noise-contrastive learning is not what you thinkPoster19 citations
52. Counterfactual inference of second OpinionsPoster18 citations
53. Revisiting the general identifiability problemPoster18 citations
54. Toward learning human-aligned cross-domain robust models by countering misaligned featuresPoster18 citations
55. Balancing utility and scalability in metric differential privacyPoster17 citations
56. ReVar: Strengthening policy evaluation via reduced variance samplingPoster17 citations
57. Causal inference with treatment measurement error: a nonparametric instrumental variable approachPoster16 citations
58. Decision-theoretic planning with communication in open multiagent systemsPoster16 citations
59. Efficient resource allocation with fairness constraints in restless multi-armed banditsPoster16 citations
60. Principle of relevant information for graph sparsificationPoster16 citations
61. Resolving label uncertainty with implicit posterior modelsPoster16 citations
62. Detecting textual adversarial examples through randomized substitution and votePoster15 citations
63. Robust expected information gain for optimal Bayesian experimental design using ambiguity setsPoster15 citations
64. Semi-supervised novelty detection using ensembles with regularized disagreementPoster15 citations
65. A mutually exciting latent space Hawkes process model for continuous-time networksPoster14 citations
66. Addressing token uniformity in transformers via singular value transformationPoster14 citations
67. Cycle class consistency with distributional optimal transport and knowledge distillation for unsupervised domain adaptationPoster14 citations
68. If you’ve trained one you’ve trained them all: inter-architecture similarity increases with robustnessPoster14 citations
69. Improved feature importance computation for tree models based on the Banzhaf valuePoster14 citations
70. Laplace approximated Gaussian process state-space modelsPoster14 citations
71. Low-precision arithmetic for fast Gaussian processesPoster14 citations
72. Asymmetric DQN for partially observable reinforcement learningPoster13 citations
73. Attribution of predictive uncertainties in classification modelsPoster13 citations
74. Cyclic test time augmentation with entropy weight methodPoster13 citations
75. GNN2GNN: Graph neural networks to generate neural networksPoster13 citations
76. Mitigating statistical bias within differentially private synthetic dataPoster13 citations
77. On provably robust meta-Bayesian optimizationPoster13 citations
78. On the definition and computation of causal treewidthPoster13 citations
79. Recursive Monte Carlo and variational inference with auxiliary variablesPoster13 citations
80. Revisiting DP-Means: fast scalable algorithms via parallelism and delayed cluster creationPoster13 citations
81. SMT-based weighted model integration with structure awarenessPoster13 citations
82. Self-distribution distillation: efficient uncertainty estimationPoster13 citations
83. $\ell_∞$-Bounds of the MLE in the BTL Model under General Comparison GraphsPoster12 citations
84. Pareto navigation gradient descent: a first-order algorithm for optimization in pareto setPoster12 citations
85. Probabilistic spatial transformer networksPoster12 citations
86. Stackmix: a complementary mix algorithmPoster12 citations
87. Efficient and transferable adversarial examples from bayesian neural networksPoster11 citations
88. Neural ensemble search via Bayesian samplingPoster11 citations
89. On testability of the front-door model via Verma constraintsPoster11 citations
90. Solving structured hierarchical games using differential backward inductionPoster11 citations
91. Variational- and metric-based deep latent space for out-of-distribution detectionPoster11 citations
92. AUTM flow: atomic unrestricted time machine for monotonic normalizing flowsPoster10 citations
93. Finite-horizon equilibria for neuro-symbolic concurrent stochastic gamesPoster10 citations
94. Identifiability of sparse causal effects using instrumental variablesPoster10 citations
95. Learning large Bayesian networks with expert constraintsPoster10 citations
96. Modeling extremes with $d$-max-decreasing neural networksPoster10 citations
97. Quantum perceptron revisited: Computational-statistical tradeoffsPoster10 citations
98. Residual bootstrap exploration for stochastic linear banditPoster10 citations
99. ST-MAML : A stochastic-task based method for task-heterogeneous meta-learningPoster10 citations
100. Voronoi density estimator for high-dimensional data: Computation, compactification and convergencePoster10 citations
101. Causal forecasting: generalization bounds for autoregressive modelsPoster9 citations
102. CoSPA: An improved masked language model with copy mechanism for Chinese spelling correctionPoster9 citations
103. Enhanced adaptive optics control with image to image translationPoster9 citations
104. Equilibrium aggregation: encoding sets via optimizationPoster9 citations
105. Evaluating high-order predictive distributions in deep learningPoster9 citations
106. Forget-me-not! Contrastive critics for mitigating posterior collapsePoster9 citations
107. Learning sparse representations of preferences within Choquet expected utility theoryPoster9 citations
108. PAC-Bayesian domain adaptation bounds for multiclass learnersPoster9 citations
109. PathFlow: A normalizing flow generator that finds transition pathsPoster9 citations
110. Superposing many tickets into one: A performance booster for sparse neural network trainingPoster9 citations
111. Towards painless policy optimization for constrained MDPsPoster9 citations
112. VQ-Flows: Vector quantized local normalizing flowsPoster9 citations
113. Active learning with label comparisonsPoster8 citations
114. Can mean field control (mfc) approximate cooperative multi agent reinforcement learning (marl) with non-uniform interaction?Poster8 citations
115. Combinatorial Bayesian optimization with random mapping functions to convex polytopesPoster8 citations
116. Do Bayesian variational autoencoders know what they don’t know?Poster8 citations
117. Future gradient descent for adapting the temporal shifting data distribution in online recommendation systemsPoster8 citations
118. Information theoretic approach to detect collusion in multi-agent gamesPoster8 citations
119. Intervention target estimation in the presence of latent variablesPoster8 citations
120. Learning linear non-Gaussian polytree modelsPoster8 citations
121. Optimal control of partially observable Markov decision processes with finite linear temporal logic constraintsPoster8 citations
122. Partial likelihood Thompson samplingPoster8 citations
123. Restless and uncertain: Robust policies for restless bandits via deep multi-agent reinforcement learningPoster8 citations
124. Shifted compression framework: generalizations and improvementsPoster8 citations
125. Temporal abstractions-augmented temporally contrastive learning: An alternative to the Laplacian in RLPoster8 citations
126. X-MEN: guaranteed XOR-maximum entropy constrained inverse reinforcement learningPoster8 citations
127. Interpolating between sampling and variational inference with infinite stochastic mixturesPoster7 citations
128. Linearizing contextual bandits with latent state dynamicsPoster7 citations
129. Marginal MAP estimation for inverse RL under occlusion with observer noisePoster7 citations
130. Offline change detection under contaminationPoster7 citations
131. Offline stochastic shortest path: Learning, evaluation and towards optimalityPoster7 citations
132. Perturbation type categorization for multiple adversarial perturbation robustnessPoster7 citations
133. Probabilistic surrogate networks for simulators with unbounded randomnessPoster7 citations
134. Robust learning of tractable probabilistic modelsPoster7 citations
135. Self-supervised representations for multi-view reinforcement learningPoster7 citations
136. A new constructive criterion for Markov equivalence of MAGsPoster6 citations
137. Asymptotic optimality for active learning processesPoster6 citations
138. Binary independent component analysis: a non-stationarity-based approachPoster6 citations
139. Deep Dirichlet process mixture modelsPoster6 citations
140. Implicit kernel meta-learning using kernel integral formsPoster6 citations
141. Individual fairness in feature-based pricing for monopoly marketsPoster6 citations
142. Learning in Markov games: Can we exploit a general-sum opponent?Poster6 citations
143. Lifting in multi-agent systems under uncertaintyPoster6 citations
144. Monotonicity regularization: Improved penalties and novel applications to disentangled representation learning and robust classificationPoster6 citations
145. Mutual information based Bayesian graph neural network for few-shot learningPoster6 citations
146. Ordinal causal discoveryPoster6 citations
147. Semiparametric causal sufficient dimension reduction of multidimensional treatmentsPoster6 citations
148. AND/OR branch-and-bound for computational protein design optimizing K*Poster5 citations
149. Combating the instability of mutual information-based losses via regularizationPoster5 citations
150. Efficient learning of sparse and decomposable PDEs using random projectionPoster5 citations
151. Feature selection for discovering distributional treatment effect modifiersPoster5 citations
152. Fixing the Bethe approximation: How structural modifications in a graph improve belief propagationPoster5 citations
153. Improving sign-random-projection via count sketchPoster5 citations
154. Multi-winner approval voting goes epistemicPoster5 citations
155. Quadratic metric elicitation for fairness and beyondPoster5 citations
156. Reinforcement learning in many-agent settings under partial observabilityPoster5 citations
157. Sequential algorithmic modification with test data reusePoster5 citations
158. Bayesian spillover graphs for dynamic networksPoster4 citations
159. Causal discovery under a confounder blanketPoster4 citations
160. Contrastive latent variable models for neural text generationPoster4 citations
161. Data sampling affects the complexity of online SGD over dependent dataPoster4 citations
162. Differentially private multi-party data release for linear regressionPoster4 citations
163. Feature learning and random features in standard finite-width convolutional neural networks: An empirical studyPoster4 citations
164. Greedy modality selection via approximate submodular maximizationPoster4 citations
165. Learning soft interventions in complex equilibrium systemsPoster4 citations
166. Offline policy optimization with eligible actionsPoster4 citations
167. On the inductive bias of neural networks for learning read-once DNFsPoster4 citations
168. On-the-fly adaptation of patrolling strategies in changing environmentsPoster4 citations
169. Orthogonal Gromov-Wasserstein discrepancy with efficient lower boundPoster4 citations
170. Predictive Whittle networks for time seriesPoster4 citations
171. Reframed GES with a neural conditional dependence measurePoster4 citations
172. Set-valued prediction in hierarchical classification with constrained representation complexityPoster4 citations
173. SymNet 2.0: Effectively handling Non-Fluents and Actions in Generalized Neural Policies for RDDL Relational MDPsPoster4 citations
174. Variational message passing neural network for Maximum-A-Posteriori (MAP) inferencePoster4 citations
175. A label efficient two-sample testPoster3 citations
176. Accelerating training of batch normalization: A manifold perspectivePoster3 citations
177. Active approximately metric-fair learningPoster3 citations
178. Byzantine-tolerant distributed multiclass sparse linear discriminant analysisPoster3 citations
179. Case-based off-policy evaluation using prototype learningPoster3 citations
180. Efficient inference for dynamic topic modeling with large vocabulariesPoster3 citations
181. Expectation programming: Adapting probabilistic programming systems to estimate expectations efficientlyPoster3 citations
182. Generalized Bayesian quadrature with spectral kernelsPoster3 citations
183. High-probability bounds for robust stochastic Frank-Wolfe algorithmPoster3 citations
184. Multiclass classification for Hawkes processesPoster3 citations
185. Neural-progressive hedging: Enforcing constraints in reinforcement learning with stochastic programmingPoster3 citations
186. Noisy L0-sparse subspace clustering on dimensionality reduced dataPoster3 citations
187. Proportional allocation of indivisible resources under ordinal and uncertain preferences.Poster3 citations
188. Robustness of model predictions under extensionPoster3 citations
189. Uncertainty-aware pseudo-labeling for quantum calculationsPoster3 citations
190. A geometric method for improved uncertainty estimation in real-timePoster2 citations
191. A robustness test for estimating total effects with covariate adjustmentPoster2 citations
192. AdaCat: Adaptive categorical discretization for autoregressive modelsPoster2 citations
193. Convergence Analysis of Linear Coupling with Inexact Proximal OperatorPoster2 citations
194. Data poisoning attacks on off-policy policy evaluation methodsPoster2 citations
195. Dynamic relocation in ridesharing via fixpoint constructionPoster2 citations
196. Learning a neural Pareto manifold extractor with constraintsPoster2 citations
197. NeuroBE: Escalating neural network approximations of Bucket EliminationPoster2 citations
198. On early extinction and the effect of travelling in the SIR modelPoster2 citations
199. Research on video adversarial attack with long living cyclePoster2 citations
200. Robust identifiability in linear structural equation models of causal inferencePoster2 citations
201. Test for non-negligible adverse shiftsPoster2 citations
202. Using hierarchies to efficiently combine evidence with Dempster’s rule of combinationPoster2 citations
203. A competitive analysis of online failure-aware assignmentPoster1 citations
204. Balancing adaptability and non-exploitability in repeated gamesPoster1 citations
205. Bias aware probabilistic Boolean matrix factorizationPoster1 citations
206. Dimension reduction for high-dimensional small counts with KL divergencePoster1 citations
207. Empirical bayes approach to truth discovery problemsPoster1 citations
208. Estimating transfer entropy under long ranged dependenciesPoster1 citations
209. Fine-Grained matching with multi-perspective similarity modeling for cross-modal retrievalPoster1 citations
210. Hitting times for continuous-time imprecise-Markov chainsPoster1 citations
211. Identifying near-optimal decisions in linear-in-parameter bandit models with continuous decision setsPoster1 citations
212. Knowledge representation combining quaternion path integration and depth-wise atrous circular convolutionPoster1 citations
213. Learning binary multi-scale games on networksPoster1 citations
214. Learning functions on multiple sets using multi-set transformersPoster1 citations
215. Nonparametric exponential family graph embeddings for multiple representation learningPoster1 citations
216. Partially adaptive regularized multiple regression analysis for estimating linear causal effectsPoster1 citations
217. Safety aware changepoint detection for piecewise i.i.d. banditsPoster1 citations
218. Simplified and unified analysis of various learning problems by reduction to Multiple-Instance LearningPoster1 citations
219. CIGMO: Categorical invariant representations in a deep generative frameworkPoster
220. Capturing actionable dynamics with structured latent ordinary differential equationsPoster
221. Clustering a union of linear subspaces via matrix factorization and innovation searchPoster
222. Efficient and accurate top-k recovery from choice dataPoster
223. Fast inference and transfer of compositional task structures for few-shot task generalizationPoster
224. Information design for multiple independent and self-interested defenders: Work less, pay off morePoster
225. Learning explainable templated graphical modelsPoster
226. Multistate analysis with infinite mixtures of Markov chainsPoster
227. Non-parametric inference of relational dependencePoster
228. PDQ-Net: Deep probabilistic dual quaternion network for absolute pose regression on $SE(3)$Poster
229. Sublinear time algorithms for greedy selection in high dimensionsPoster
230. Systematized event-aware learning for multi-object trackingPoster

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