• Corpus ID: 251979301

Improved Estimation of Relaxation Time in Non-reversible Markov Chains

  title={Improved Estimation of Relaxation Time in Non-reversible Markov Chains},
  author={Geoffrey Wolfer and Aryeh Kontorovich},
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 

Figures and Tables from this paper



Computationally Efficient Estimation of the Spectral Gap of a Markov Chain

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.

Statistical estimation of ergodic Markov chain kernel over discrete state space

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

Improving the Asymptotic Performance of Markov Chain Monte-Carlo by Inserting Vortices

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.

Estimating the spectral gap of a trace-class Markov operator

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)

Estimating the Spectral Gap of a Reversible Markov Chain from a Short Trajectory

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,

Mixing Time Estimation in Reversible Markov Chains from a Single Sample Path

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.

Accelerated Sampling on Discrete Spaces with Non-Reversible Markov Processes

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.

Improving Asymptotic Variance of MCMC Estimators: Non-reversible Chains are Better

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

Empirical and Instance-Dependent Estimation of Markov Chain and Mixing Time

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