A note on concentration inequalities for the overlapped batch mean variance estimators for Markov chains

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Moulines, Eric, Naumov, Alexey, Samsonov, Sergey
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916735127388160
author Moulines, Eric
Naumov, Alexey
Samsonov, Sergey
author_facet Moulines, Eric
Naumov, Alexey
Samsonov, Sergey
contents In this paper, we study the concentration properties of quadratic forms associated with Markov chains using the martingale decomposition method introduced by Atchadé and Cattaneo (2014). In particular, we derive concentration inequalities for the overlapped batch mean (OBM) estimators of the asymptotic variance for uniformly geometrically ergodic Markov chains. Our main result provides an explicit control of the $p$-th moment of the difference between the OBM estimator and the asymptotic variance of the Markov chain with explicit dependence upon $p$ and mixing time of the underlying Markov chain.
format Preprint
id arxiv_https___arxiv_org_abs_2505_08456
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A note on concentration inequalities for the overlapped batch mean variance estimators for Markov chains
Moulines, Eric
Naumov, Alexey
Samsonov, Sergey
Probability
Statistics Theory
Machine Learning
60J10, 60J22, 62M10
In this paper, we study the concentration properties of quadratic forms associated with Markov chains using the martingale decomposition method introduced by Atchadé and Cattaneo (2014). In particular, we derive concentration inequalities for the overlapped batch mean (OBM) estimators of the asymptotic variance for uniformly geometrically ergodic Markov chains. Our main result provides an explicit control of the $p$-th moment of the difference between the OBM estimator and the asymptotic variance of the Markov chain with explicit dependence upon $p$ and mixing time of the underlying Markov chain.
title A note on concentration inequalities for the overlapped batch mean variance estimators for Markov chains
topic Probability
Statistics Theory
Machine Learning
60J10, 60J22, 62M10
url https://arxiv.org/abs/2505.08456