X Zhang, Y Li, W Li, K Guo… - … Conference on Machine …, 2022 - proceedings.mlr.press
Federated learning faces huge challenges from model overfitting due to the lack of data and statistical diversity among clients. To address these challenges, this paper proposes a novel …
Abstract Along with Markov chain Monte Carlo (MCMC) methods, variational inference (VI) has emerged as a central computational approach to large-scale Bayesian inference …
Variational inference (VI) seeks to approximate a target distribution $\pi $ by an element of a tractable family of distributions. Of key interest in statistics and machine learning is Gaussian …
Y Wang, DM Blei - Journal of the American Statistical Association, 2019 - Taylor & Francis
ABSTRACT A key challenge for modern Bayesian statistics is how to perform scalable inference of posterior distributions. To address this challenge, variational Bayes (VB) …
K Kim, J Oh, K Wu, Y Ma… - Advances in Neural …, 2024 - proceedings.neurips.cc
We provide the first convergence guarantee for black-box variational inference (BBVI) with the reparameterization gradient. While preliminary investigations worked on simplified …
F Chen, S Mei, Y Bai - arXiv preprint arXiv:2209.11745, 2022 - arxiv.org
Finding unified complexity measures and algorithms for sample-efficient learning is a central topic of research in reinforcement learning (RL). The Decision-Estimation Coefficient (DEC) …
K Ray, B Szabó - Journal of the American Statistical Association, 2022 - Taylor & Francis
We study a mean-field spike and slab variational Bayes (VB) approximation to Bayesian model selection priors in sparse high-dimensional linear regression. Under compatibility …
F Zhang, C Gao - The Annals of Statistics, 2020 - JSTOR
We study convergence rates of variational posterior distributions for nonparametric and high- dimensional inference. We formulate general conditions on prior, likelihood and variational …
J Domke, R Gower, G Garrigos - Advances in neural …, 2024 - proceedings.neurips.cc
Black-box variational inference is widely used in situations where there is no proof that its stochastic optimization succeeds. We suggest this is due to a theoretical gap in existing …