Non-Asymptotic Gaussian Estimates for the Recursive Approximation of the Invariant Measure of a Diffusion

Abstract : We obtain non-asymptotic Gaussian concentration bounds for the difference between the invariant measure ν of an ergodic Brownian diffusion process and the empirical distribution of an approximating scheme with decreasing time step along a suitable class of (smooth enough) test functions f such that f − ν(f) is a coboundary of the infinitesimal generator. We show that these bounds can still be improved when the (squared) Fröbenius norm of the diffusion coefficient lies in this class. We apply these bounds to design computable non-asymptotic confidence intervals for the approximating scheme. As a theoretical application, we finally derive non-asymptotic deviation bounds for the almost sure Central Limit Theorem.
Type de document :
Pré-publication, Document de travail
2016
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01321645
Contributeur : Stephane Menozzi <>
Soumis le : mercredi 29 juin 2016 - 09:07:14
Dernière modification le : samedi 18 février 2017 - 01:20:26
Document(s) archivé(s) le : vendredi 30 septembre 2016 - 11:16:41

Fichiers

article_20_06_16_MODIF_PREPRIN...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01321645, version 2
  • ARXIV : 1605.08525

Collections

Citation

Igor Honoré, Stephane Menozzi, Gilles Pagès. Non-Asymptotic Gaussian Estimates for the Recursive Approximation of the Invariant Measure of a Diffusion. 2016. <hal-01321645v2>

Partager

Métriques

Consultations de
la notice

340

Téléchargements du document

47