Improved estimation of relaxation time in nonreversible Markov chains

DOI10.1214/23-aap1963arXiv2209.00175MaRDI QIDQ6126104

Geoffrey Wolfer, Leonid (Aryeh) Kontorovich

Publication date: 9 April 2024

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2209.00175

zbMATH Keywords

mixing timeergodic Markov chainempirical confidence intervalpseudo-spectral gap

Mathematics Subject Classification ID

Markov processes: estimation; hidden Markov models (62M05) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Inference from stochastic processes (62M99)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Non-reversible Metropolis-Hastings
• Irreversible Monte Carlo algorithms for efficient sampling
• User-friendly tail bounds for sums of random matrices
• Eigenvalue bounds on convergence to stationarity for nonreversible Markov chains, with an application to the exclusion process
• Learning from dependent observations
• Basic properties of strong mixing conditions. A survey and some open questions
• Rates of convergence for empirical processes of stationary mixing sequences
• Analysis of a nonreversible Markov chain sampler.
• Information geometry of reversible Markov chains
• Statistical estimation of ergodic Markov chain kernel over discrete state space
• Metropolis-Hastings reversiblizations of non-reversible Markov chains
• Mixing time estimation in reversible Markov chains from a single sample path
• Concentration inequalities for Markov chains by Marton couplings and spectral methods
• Accelerating reversible Markov chains
• Lifting Markov chains to speed up mixing
• Statistical Methods in Markov Chains
• Mathematical Aspects of Mixing Times in Markov Chains
• On the Rates of Convergence of the Lanczos and the Block-Lanczos Methods
• Estimating the Largest Eigenvalue by the Power and Lanczos Algorithms with a Random Start
• Regret Bounds for Reinforcement Learning via Markov Chain Concentration
• An Introduction to Matrix Concentration Inequalities
• Estimates for Some Computational Techniques in Linear Algebra
• Non-Reversible Parallel Tempering: A Scalable Highly Parallel MCMC Scheme
• Accelerated and Instance-Optimal Policy Evaluation with Linear Function Approximation
• Hold-out estimates of prediction models for Markov processes

This page was built for publication: Improved estimation of relaxation time in nonreversible Markov chains