Skip to Main content Skip to Navigation
Journal articles

Concentration of measure inequalities for Markov chains and Φ-mixing processes

Abstract : We prove concentration inequalities for some classes of Markov chains and Φ-mixing processes, with constants independent of the size of the sample, that extend the inequalities for product measures of Talagrand. The method is based on information inequalities put forwardby Marton in case of contracting Markov chains. Using a simple duality argument on entropy, our results also include the family of logarithmic Sobolev inequalities for convex functions. Applications to bounds on supremum of dependent empirical processes complete this work.
Document type :
Journal articles
Complete list of metadata

https://hal-upec-upem.archives-ouvertes.fr/hal-01586214
Contributor : Paul-Marie Samson Connect in order to contact the contributor
Submitted on : Tuesday, September 12, 2017 - 3:51:48 PM
Last modification on : Tuesday, October 19, 2021 - 4:07:26 PM

Links full text

Identifiers

`

Citation

Paul-Marie Samson. Concentration of measure inequalities for Markov chains and Φ-mixing processes. Annals of Probability, Institute of Mathematical Statistics, 2000, Ann. Probab., 28 (1), pp.416--461. ⟨10.1214/aop/1019160125⟩. ⟨hal-01586214⟩

Share

Metrics

Record views

458