arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.14656math.STmath.PRstat.TH
收藏

蒙特卡洛马尔可夫链的收敛界

Convergence Bounds for Monte Carlo Markov Chains

Qian Qin

AI总结:

本文为新手介绍马尔可夫链蒙特卡洛的收敛分析,重点通过耦合方法和基于电导与等周不等式的L2理论构建链分布与平稳分布间距离的界,并讨论识别缓慢收敛的策略。

摘要:

这篇为《Markov Chain Monte Carlo手册》第二版撰写的综述论文,旨在为该领域的新手研究人员介绍马尔可夫链蒙特卡洛(MCMC)的收敛分析研究。我们重点关注构建给定时刻马尔可夫链分布与其平稳分布间距离的界的方法。文章探讨了两种广泛使用的方法:耦合方法和马尔可夫链的L2理论。对于后者,我们强调了基于电导和等周不等式的技术。此外,我们还简要讨论了识别马尔可夫链中缓慢收敛的策略。

英文摘要:

This review paper, written for the second edition of the Handbook of Markov Chain Monte Carlo, provides an introduction to the study of convergence analysis for Markov chain Monte Carlo (MCMC), aimed at researchers new to the field. We focus on methods for constructing bounds on the distance between the distribution of a Markov chain at a given time and its stationary distribution. Two widely-used approaches are explored: the coupling method and the L2 theory of Markov chains. For the latter, we emphasize techniques based on conductance and isoperimetric inequalities. Additionally, we briefly discuss strategies for identifying slow convergence in Markov chains.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑