## Abstract

We address the problem of estimating the mixing time t_{mix} of an arbitrary ergodic finite Markov chain from a single trajectory of length m. The reversible case was addressed by Hsu et al. (2018+), who left the general case as an open problem. In the reversible case, the analysis is greatly facilitated by the fact that the Markov operator is self-adjoint, and Weyl’s inequality allows for a dimension-free perturbation analysis of the empirical eigenvalues. As Hsu et al. point out, in the absence of reversibility (and hence, the non-symmetry of the pair probabilities matrix), the existing perturbation analysis has a worst-case exponential dependence on the number of states d. Furthermore, even if an eigenvalue perturbation analysis with better dependence on d were available, in the non-reversible case the connection between the spectral gap and the mixing time is not nearly as straightforward as in the reversible case. Our key insight is to estimate the pseudo-spectral gap instead, which allows us to overcome the loss of self-adjointness and to achieve a polynomial dependence on d and the minimal stationary probability π_{*}. Additionally, in the reversible case, we obtain simultaneous nearly (up to logarithmic factors) minimax rates in t_{mix} and precision ε, closing a gap in Hsu et al., who treated ε as constant in the lower bounds. Finally, we construct fully empirical confidence intervals for the pseudo-spectral gap, which shrink to zero at a rate of roughly 1/√m, and improve the state of the art in even the reversible case.

Original language | English |
---|---|

Pages (from-to) | 3120-3159 |

Number of pages | 40 |

Journal | Proceedings of Machine Learning Research |

Volume | 99 |

State | Published - 1 Jan 2019 |

Event | 32nd Conference on Learning Theory, COLT 2019 - Phoenix, United States Duration: 25 Jun 2019 → 28 Jun 2019 |

## Keywords

- ergodic Markov chain
- mixing time
- non-reversible Markov chain

## ASJC Scopus subject areas

- Artificial Intelligence
- Software
- Control and Systems Engineering
- Statistics and Probability