Deep Learning for Computing Convergence Rates of Markov Chains

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qu, Yanlin, Blanchet, Jose, Glynn, Peter
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909697675624448
author Qu, Yanlin
Blanchet, Jose
Glynn, Peter
author_facet Qu, Yanlin
Blanchet, Jose
Glynn, Peter
contents Convergence rate analysis for general state-space Markov chains is fundamentally important in areas such as Markov chain Monte Carlo and algorithmic analysis (for computing explicit convergence bounds). This problem, however, is notoriously difficult because traditional analytical methods often do not generate practically useful convergence bounds for realistic Markov chains. We propose the Deep Contractive Drift Calculator (DCDC), the first general-purpose sample-based algorithm for bounding the convergence of Markov chains to stationarity in Wasserstein distance. The DCDC has two components. First, inspired by the new convergence analysis framework in Qu, Blanchet and Glynn (2023), we introduce the Contractive Drift Equation (CDE), the solution of which leads to an explicit convergence bound. Second, we develop an efficient neural-network-based CDE solver. Equipped with these two components, DCDC solves the CDE and converts the solution into a convergence bound. We analyze the sample complexity of the algorithm and further demonstrate the effectiveness of the DCDC by generating convergence bounds for realistic Markov chains arising from stochastic processing networks as well as constant step-size stochastic optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2405_20435
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Learning for Computing Convergence Rates of Markov Chains
Qu, Yanlin
Blanchet, Jose
Glynn, Peter
Machine Learning
Probability
Convergence rate analysis for general state-space Markov chains is fundamentally important in areas such as Markov chain Monte Carlo and algorithmic analysis (for computing explicit convergence bounds). This problem, however, is notoriously difficult because traditional analytical methods often do not generate practically useful convergence bounds for realistic Markov chains. We propose the Deep Contractive Drift Calculator (DCDC), the first general-purpose sample-based algorithm for bounding the convergence of Markov chains to stationarity in Wasserstein distance. The DCDC has two components. First, inspired by the new convergence analysis framework in Qu, Blanchet and Glynn (2023), we introduce the Contractive Drift Equation (CDE), the solution of which leads to an explicit convergence bound. Second, we develop an efficient neural-network-based CDE solver. Equipped with these two components, DCDC solves the CDE and converts the solution into a convergence bound. We analyze the sample complexity of the algorithm and further demonstrate the effectiveness of the DCDC by generating convergence bounds for realistic Markov chains arising from stochastic processing networks as well as constant step-size stochastic optimization.
title Deep Learning for Computing Convergence Rates of Markov Chains
topic Machine Learning
Probability
url https://arxiv.org/abs/2405.20435