Concentration of Markov chains with bounded moments
Probability
2019-06-19 v1 Functional Analysis
Abstract
Let be a finite state stationary Markov chain, and suppose that is a real-valued function on the state space. If is bounded, then Gillman's expander Chernoff bound (1993) provides concentration estimates for the random variable that depend on the spectral gap of the Markov chain and the assumed bound on . Here we obtain analogous inequalities assuming only that the 'th moment of is bounded for some . Our proof relies on reasoning that differs substantially from the proofs of Gillman's theorem that are available in the literature, and it generalizes to yield dimension-independent bounds for mappings that take values in an for some , thus answering (even in the Hilbertian special case ) a question of Kargin (2007).
Keywords
Cite
@article{arxiv.1906.07260,
title = {Concentration of Markov chains with bounded moments},
author = {Assaf Naor and Shravas Rao and Oded Regev},
journal= {arXiv preprint arXiv:1906.07260},
year = {2019}
}