Chernoff-Hoeffding Bounds for Markov Chains: Generalized and Simplified

TL;DR

This paper establishes new Chernoff-Hoeffding bounds for finite-state Markov chains, providing generalized and simplified concentration inequalities based on mixing time and spectral properties, applicable to both discrete and continuous-time chains.

Contribution

It introduces the first Chernoff-Hoeffding bounds for nonreversible Markov chains using L_1 mixing time and offers a simplified spectral-based proof, extending to continuous-time and arbitrary initial distributions.

Findings

Bounds depend on mixing time T and spectral gap (1-lambda).

Results extend to continuous-time Markov chains.

Bounds hold for nonreversible chains and arbitrary starting distributions.

Abstract

We prove the first Chernoff-Hoeffding bounds for general nonreversible finite-state Markov chains based on the standard L_1 (variation distance) mixing-time of the chain. Specifically, consider an ergodic Markov chain M and a weight function f: [n] -> [0,1] on the state space [n] of M with mean mu = E_{v <- pi}[f(v)], where pi is the stationary distribution of M. A t-step random walk (v_1,...,v_t) on M starting from the stationary distribution pi has expected total weight E[X] = mu t, where X = sum_{i=1}^t f(v_i). Let T be the L_1 mixing-time of M. We show that the probability of X deviating from its mean by a multiplicative factor of delta, i.e., Pr [ |X - mu t| >= delta mu t ], is at most exp(-Omega(delta^2 mu t / T)) for 0 <= delta <= 1, and exp(-Omega(delta mu t / T)) for delta > 1. In fact, the bounds hold even if the weight functions f_i's for i in [t] are distinct, provided that all of them have the same mean mu. We also obtain a simplified proof for the Chernoff-Hoeffding bounds based on the spectral expansion lambda of M, which is the square root of the second largest eigenvalue (in absolute value) of M tilde{M}, where tilde{M} is the time-reversal Markov chain of M. We show that the probability Pr [ |X - mu t| >= delta mu t ] is at most exp(-Omega(delta^2 (1-lambda) mu t)) for 0 <= delta <= 1, and exp(-Omega(delta (1-lambda) mu t)) for delta > 1. Both of our results extend to continuous-time Markov chains, and to the case where the walk starts from an arbitrary distribution x, at a price of a multiplicative factor depending on the distribution x in the concentration bounds.