Guardado en:
Detalles Bibliográficos
Autores principales: Cui, Tiangang, Dong, Jing, Jasra, Ajay, Tong, Xin T.
Formato: Preprint
Publicado: 2022
Materias:
Acceso en línea:https://arxiv.org/abs/2203.03104
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911372628983808
author Cui, Tiangang
Dong, Jing
Jasra, Ajay
Tong, Xin T.
author_facet Cui, Tiangang
Dong, Jing
Jasra, Ajay
Tong, Xin T.
contents When implementing Markov Chain Monte Carlo (MCMC) algorithms, perturbation caused by numerical errors is sometimes inevitable. This paper studies how perturbation of MCMC affects the convergence speed and Monte Carlo estimation accuracy. Our results show that when the original Markov chain converges to stationarity fast enough and the perturbed transition kernel is a good approximation to the original transition kernel, the corresponding perturbed sampler has similar convergence speed and high approximation accuracy as well. We discuss two different analysis frameworks: ergodicity and spectral gap, both are widely used in the literature. Our results can be easily extended to obtain non-asymptotic error bounds for MCMC estimators. We also demonstrate how to apply our convergence and approximation results to the analysis of specific sampling algorithms, including Random walk Metropolis and Metropolis adjusted Langevin algorithm with perturbed target densities, and parallel tempering Monte Carlo with perturbed densities. Finally we present some simple numerical examples to verify our theoretical claims.
format Preprint
id arxiv_https___arxiv_org_abs_2203_03104
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Convergence Speed and Approximation Accuracy of Numerical MCMC
Cui, Tiangang
Dong, Jing
Jasra, Ajay
Tong, Xin T.
Computation
Probability
When implementing Markov Chain Monte Carlo (MCMC) algorithms, perturbation caused by numerical errors is sometimes inevitable. This paper studies how perturbation of MCMC affects the convergence speed and Monte Carlo estimation accuracy. Our results show that when the original Markov chain converges to stationarity fast enough and the perturbed transition kernel is a good approximation to the original transition kernel, the corresponding perturbed sampler has similar convergence speed and high approximation accuracy as well. We discuss two different analysis frameworks: ergodicity and spectral gap, both are widely used in the literature. Our results can be easily extended to obtain non-asymptotic error bounds for MCMC estimators. We also demonstrate how to apply our convergence and approximation results to the analysis of specific sampling algorithms, including Random walk Metropolis and Metropolis adjusted Langevin algorithm with perturbed target densities, and parallel tempering Monte Carlo with perturbed densities. Finally we present some simple numerical examples to verify our theoretical claims.
title Convergence Speed and Approximation Accuracy of Numerical MCMC
topic Computation
Probability
url https://arxiv.org/abs/2203.03104