Bayesian & Probabilistic

On PAC-Bayesian reconstruction guarantees for VAEs AISTATS 2022 On perfectness in Gaussian graphical models AISTATS 2022 On the detrimental effect of invariances in the likelihood for variational inference NeurIPS 2022 On the expressivity of bi-Lipschitz normalizing flows ACML 2022 On the inability of Gaussian process regression to optimally learn compositional functions NeurIPS 2022 On the probability–quality paradox in language generation ACL 2022 On the relationship between variational inference and auto-associative memory NeurIPS 2022 On the Robustness to Misspecification of α-posteriors and Their Variational Approximations JMLR 2022 On the Role of Channel Capacity in Learning Gaussian Mixture Models COLT 2022 On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels NeurIPS 2022 On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification NeurIPS 2022 Open Problem: Regret Bounds for Noise-Free Kernel-Based Bandits COLT 2022 Optimal SQ Lower Bounds for Robustly Learning Discrete Product Distributions and Ising Models COLT 2022 Optimistic Tree Searches for Combinatorial Black-Box Optimization NeurIPS 2022 Out-of-Distribution Detection via Conditional Kernel Independence Model NeurIPS 2022 Parallel MCMC Without Embarrassing Failures AISTATS 2022 Parameterized Completeness Results for Bayesian Inference PGM 2022 Pareto Set Learning for Expensive Multi-Objective Optimization NeurIPS 2022 Path Auxiliary Proposal for MCMC in Discrete Space ICLR 2022 Pathfinder: Parallel quasi-Newton variational inference JMLR 2022 Personalized Federated Learning via Variational Bayesian Inference ICML 2022 Personalized Public Policy Analysis in Social Sciences Using Causal-Graphical Normalizing Flows AAAI 2022 Phase transitions in when feedback is useful NeurIPS 2022 Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisation NeurIPS 2022 PLAD: Learning To Infer Shape Programs With Pseudo-Labels and Approximate Distributions CVPR 2022