Deviation inequalities for separately Lipschitz functionals of composition of random functions

JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS

卷:479

Article

Dedecker, Jerome^1,2  Doukhan, Paul^3,4  Fan, Xiequan⁵ 

[1] Univ Paris 05, Sorbonne Paris Cite, Lab MAPS, F-75016 Paris, France

[2] CNRS, UMR 8145, F-75016 Paris, France

[3] Univ Paris Seine, AGM, UMR 8088, UCP Site St Martin,2 Bd Adolphe Chauvin, F-95000 Cergy Pontoise, France

[4] Univ Valparaiso, CIMFAV, Valparaiso, Chile

[5] Tianjin Univ, Ctr Appl Math, Tianjin, Peoples R China

关键词: Non-homogeneous Markov chains;    Martingales;    Exponential inequalities;    Moment inequalities;   

DOI  :  10.1016/j.jmaa.2019.07.011

来源: Elsevier

【 摘 要 】

We consider a class of non-homogeneous Markov chains, that contains many natural examples. Next, using martingale methods, we establish some deviation and moment inequalities for separately Lipschitz functions of such a chain, under moment conditions on some dominating random variables. (C) 2019 Elsevier Inc. All rights reserved.

【 授权许可】

Free