• Corpus ID: 251979301

# Improved Estimation of Relaxation Time in Non-reversible Markov Chains

@inproceedings{Wolfer2022ImprovedEO,
title={Improved Estimation of Relaxation Time in Non-reversible Markov Chains},
author={Geoffrey Wolfer and Aryeh Kontorovich},
year={2022}
}
• Published 1 September 2022
• Mathematics
We show that the minimax sample complexity for estimating the pseudo-spectral gap γ ps of an ergodic Markov chain in constant multiplicative error is of the order of

## References

SHOWING 1-10 OF 52 REFERENCES

• Mathematics, Computer Science
Proc. ACM Meas. Anal. Comput. Syst.
• 2019
The UCPI (Upper Confidence Power Iteration) algorithm is proposed, a low-complexity algorithm which estimates the spectral gap in time O(n) and memory space O ((łn n)^2) given n samples, in stark contrast with most known methods which require at least memoryspace O(|Ω|), so that they cannot be applied to large state spaces.
• Mathematics
• 2018
We investigate the statistical complexity of estimating the parameters of a discrete-state Markov chain kernel from a single long sequence of state observations. In the finite case, we characterize
• Mathematics
NIPS
• 2010
It is confirmed that non-reversible chains are fundamentally better than reversible ones in terms of asymptotic performance, and suggests interesting directions for further improving MCMC.
• Mathematics
Electronic Journal of Statistics
• 2019
The utility of a Markov chain Monte Carlo algorithm is, in large part, determined by the size of the spectral gap of the corresponding Markov operator. However, calculating (and even approximating)
• Mathematics
• 2016
The spectral gap $\gamma$ of an ergodic and reversible Markov chain is an important parameter measuring the asymptotic rate of convergence. In applications, the transition matrix $P$ may be unknown,
• Mathematics
NIPS
• 2015
This article provides the first procedure for computing a fully data-dependent interval that traps the mixing time of a finite reversible ergodic Markov chain at a prescribed confidence level, and does not require the knowledge of any parameters of the chain.
• Computer Science, Mathematics
• 2019
A class of efficient continuous-time, non-reversible algorithms which make active use of the structure of the underlying space and place particular emphasis on how symmetries and other group-theoretic notions can be used to improve exploration of the space.
I show how any reversible Markov chain on a finite state space that is irreducible, and hence suitable for estimating expectations with respect to its invariant distribution, can be used to construct
We tackle the fundamental problem of estimating the mixing time of a Markov chain from a single trajectory of observations. In contrast with previous works which considered Hilbert space methods to