Exponential inequalities for unbounded functions of geometrically ergodic Markov chains. Applications to quantitative error bounds for regenerative Metropolis algorithms

Abstract : The aim of this note is to investigate the concentration properties of unbounded functions of geometrically ergodic Markov chains. We derive concentration properties of centered functions with respect to the square of the Lyapunov's function in the drift condition satisfied by the Markov chain. We apply the new exponential inequalities to derive confidence intervals for MCMC algorithms. Quantitative error bounds are providing for the regenerative Metropolis algorithm of [5].
Type de document :
Pré-publication, Document de travail
2016
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01222870
Contributeur : Olivier Wintenberger <>
Soumis le : vendredi 9 septembre 2016 - 15:34:23
Dernière modification le : vendredi 7 décembre 2018 - 01:23:56

Fichiers

MCrev.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01222870, version 2
  • ARXIV : 1511.01752

Collections

Citation

Olivier Wintenberger. Exponential inequalities for unbounded functions of geometrically ergodic Markov chains. Applications to quantitative error bounds for regenerative Metropolis algorithms. 2016. 〈hal-01222870v2〉

Partager

Métriques

Consultations de la notice

281

Téléchargements de fichiers

261