Chernoff-type bound for finite Markov chains

Abstract : This paper develops bounds on the distribution function of the empirical mean for irreducible finite-state Markov chains. One approach, explored by D. Gillman, reduces this problem to bounding the largest eigenvalue of a perturbation of the transition matrix for the Markov chain. By using estimates on eigenvalues given in Kato's book ''Perturbation Theory for Linear Operators'', we simplify the proof of D. Gillman and extend it to non-reversible finite-state Markov chains and continuous time. We also set out another method, directly applicable to some general ergodic Markov kernels having a spectral gap.
Document type :
Journal articles
Liste complète des métadonnées

Cited literature [20 references]  Display  Hide  Download

https://hal-enac.archives-ouvertes.fr/hal-00940907
Contributor : Laurence Porte <>
Submitted on : Tuesday, April 1, 2014 - 1:04:22 PM
Last modification on : Monday, February 18, 2019 - 7:52:04 PM
Document(s) archivé(s) le : Tuesday, July 1, 2014 - 10:42:43 AM

File

437.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-00940907, version 1

Collections

Citation

Pascal Lezaud. Chernoff-type bound for finite Markov chains. Annals of Applied Probability, Institute of Mathematical Statistics (IMS), 1998, 8 (3), pp 849-867. ⟨hal-00940907⟩

Share

Metrics

Record views

208

Files downloads

463