Convergence rates of variational posterior distributions

From MaRDI portal
Publication:2215731

DOI10.1214/19-AOS1883zbMATH Open1471.62243arXiv1712.02519OpenAlexW3049347563MaRDI QIDQ2215731FDOQ2215731


Authors: Fengshuo Zhang, Chao Gao Edit this on Wikidata


Publication date: 14 December 2020

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: We study convergence rates of variational posterior distributions for nonparametric and high-dimensional inference. We formulate general conditions on prior, likelihood, and variational class that characterize the convergence rates. Under similar "prior mass and testing" conditions considered in the literature, the rate is found to be the sum of two terms. The first term stands for the convergence rate of the true posterior distribution, and the second term is contributed by the variational approximation error. For a class of priors that admit the structure of a mixture of product measures, we propose a novel prior mass condition, under which the variational approximation error of the mean-field class is dominated by convergence rate of the true posterior. We demonstrate the applicability of our general results for various models, prior distributions and variational classes by deriving convergence rates of the corresponding variational posteriors.


Full work available at URL: https://arxiv.org/abs/1712.02519




Recommendations




Cites Work


Cited In (34)

Uses Software





This page was built for publication: Convergence rates of variational posterior distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2215731)