DeLTA seminar by Pierre Alquier: Optimistic Estimation of Convergence in Markov Chains with the Average Mixing Time

Press here to join the Zoom call. 

Speaker

Pierre Alquier, Professor of Statistics at ESSEC Business School.

Title

Optimistic Estimation of Convergence in Markov Chains with the Average Mixing Time

Abstract

The convergence rate of a Markov chain to its stationary distribution is typically assessed using the concept of total variation mixing time. However, this worst-case measure often yields pessimistic estimates and is challenging to infer from observations. In this talk, we advocate for the use of the average-mixing time as a more optimistic and demonstrably easier-to-estimate alternative. We further illustrate its applicability across a range of settings, from two-point to countable spaces, and discuss some practical implications. We will also highlight the consequences of these results in terms of machine learning on Markov chains.

_____________________________

You can subscribe to the DeLTA Seminar mailing list by sending an empty email to delta-seminar-join@list.ku.dk.
Online calendar
DeLTA Lab page