Annals of Applied Probability
- Ann. Appl. Probab.
- Volume 29, Number 3 (2019), 1778-1807.
Effective Berry–Esseen and concentration bounds for Markov chains with a spectral gap
Abstract
Applying quantitative perturbation theory for linear operators, we prove nonasymptotic bounds for Markov chains whose transition kernel has a spectral gap in an arbitrary Banach algebra of functions $\mathscr{X}$. The main results are concentration inequalities and Berry–Esseen bounds, obtained assuming neither reversibility nor “warm start” hypothesis: the law of the first term of the chain can be arbitrary. The spectral gap hypothesis is basically a uniform $\mathscr{X}$-ergodicity hypothesis, and when $\mathscr{X}$ consist in regular functions this is weaker than uniform ergodicity. We show on a few examples how the flexibility in the choice of function space can be used. The constants are completely explicit and reasonable enough to make the results usable in practice, notably in MCMC methods.
Article information
Source
Ann. Appl. Probab., Volume 29, Number 3 (2019), 1778-1807.
Dates
Received: November 2017
Revised: July 2018
First available in Project Euclid: 19 February 2019
Permanent link to this document
https://projecteuclid.org/euclid.aoap/1550566842
Digital Object Identifier
doi:10.1214/18-AAP1438
Mathematical Reviews number (MathSciNet)
MR3914556
Zentralblatt MATH identifier
07057466
Subjects
Primary: 65C05: Monte Carlo methods
Secondary: 60J22: Computational methods in Markov chains [See also 65C40] 62E17: Approximations to distributions (nonasymptotic)
Keywords
Concentration inequalities Berry–Esseen bounds Markov chains spectral gap property Markov chain Monte-Carlo method
Citation
Kloeckner, Benoît. Effective Berry–Esseen and concentration bounds for Markov chains with a spectral gap. Ann. Appl. Probab. 29 (2019), no. 3, 1778--1807. doi:10.1214/18-AAP1438. https://projecteuclid.org/euclid.aoap/1550566842