Theoretical guarantees for neural control variates in MCMC

DOI10.1016/J.MATCOM.2024.01.019MaRDI QIDQ6129489zbMATH OpenWikidataFDO

Authors D. Belomestny, A. Goldman, Alexey Naumov, S. P. Samsonov

Publication date 17 April 2024

Published in Mathematics and Computers in Simulation (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2304.01111

zbMATH Keywords

MCMC control variates Stein operator deep neural networks variance reductions

Mathematics Subject Classification ID

Statistics (62-XX) Systems theory; control (93-XX)

Abstract: In this paper, we propose a variance reduction approach for Markov chains based on additive control variates and the minimization of an appropriate estimate for the asymptotic variance. We focus on the particular case when control variates are represented as deep neural networks. We derive the optimal convergence rate of the asymptotic variance under various ergodicity assumptions on the underlying Markov chain. The proposed approach relies upon recent results on the stochastic errors of variance reduction algorithms and function approximation theory.

This page was built for publication: Theoretical guarantees for neural control variates in MCMC

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6129489)