English

Improved Estimation of Relaxation Time in Non-reversible Markov Chains

Statistics Theory 2023-08-07 v3 Probability Statistics Theory

Abstract

We show that the minimax sample complexity for estimating the pseudo-spectral gap γps\gamma_{\mathsf{ps}} of an ergodic Markov chain in constant multiplicative error is of the order of Θ~(1γpsπ),\tilde{\Theta}\left( \frac{1}{\gamma_{\mathsf{ps}} \pi_{\star}} \right), where π\pi_\star is the minimum stationary probability, recovering the known bound in the reversible setting for estimating the absolute spectral gap [Hsu et al., 2019], and resolving an open problem of Wolfer and Kontorovich [2019]. Furthermore, we strengthen the known empirical procedure by making it fully-adaptive to the data, thinning the confidence intervals and reducing the computational complexity. Along the way, we derive new properties of the pseudo-spectral gap and introduce the notion of a reversible dilation of a stochastic matrix.

Keywords

Cite

@article{arxiv.2209.00175,
  title  = {Improved Estimation of Relaxation Time in Non-reversible Markov Chains},
  author = {Geoffrey Wolfer and Aryeh Kontorovich},
  journal= {arXiv preprint arXiv:2209.00175},
  year   = {2023}
}