Deviation inequalities for contractive infinite memory processes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Doukhan, Paul, Fan, Xiequan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917940694089728
author Doukhan, Paul
Fan, Xiequan
author_facet Doukhan, Paul
Fan, Xiequan
contents In this paper, we introduce a class of processes that contains many natural examples. The interesting feature of such type processes lays on its infinite memory that allows it to record a quite ancient history. Then, using the martingale decomposition method, we establish some deviation and moment inequalities for separately Lipschitz functions of such a process, under various moment conditions on some dominating random variables. Our results generalize the Markov models of Dedecker and Fan [Stochastic Process. Appl., 2015] and a recent paper by Chazottes et al. [Ann. Appl. Probab., 2023] for the special case of a specific class of infinite memory models with discrete values. An application to stochastic gradient Langevin dynamic algorithm is also discussed.
format Preprint
id arxiv_https___arxiv_org_abs_2408_11719
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deviation inequalities for contractive infinite memory processes
Doukhan, Paul
Fan, Xiequan
Probability
60G42, 60J05, 60E15
In this paper, we introduce a class of processes that contains many natural examples. The interesting feature of such type processes lays on its infinite memory that allows it to record a quite ancient history. Then, using the martingale decomposition method, we establish some deviation and moment inequalities for separately Lipschitz functions of such a process, under various moment conditions on some dominating random variables. Our results generalize the Markov models of Dedecker and Fan [Stochastic Process. Appl., 2015] and a recent paper by Chazottes et al. [Ann. Appl. Probab., 2023] for the special case of a specific class of infinite memory models with discrete values. An application to stochastic gradient Langevin dynamic algorithm is also discussed.
title Deviation inequalities for contractive infinite memory processes
topic Probability
60G42, 60J05, 60E15
url https://arxiv.org/abs/2408.11719