Fano's inequality for random variables

Abstract : We extend Fano's inequality, which controls the average probability of (disjoint) events in terms of the average of some Kullback-Leibler divergences, to work with arbitrary [0,1]-valued random variables. Our simple two-step methodology is general enough to cover the case of an arbitrary (possibly continuously infinite) family of distributions as well as [0,1]-valued random variables not necessarily summing up to 1. Several novel applications are provided, in which the consideration of random variables is particularly handy. The most important applications deal with the problem of Bayesian posterior concentration (minimax or distribution-dependent) rates and with a lower bound on the regret in non-stochastic sequential learning. We also improve in passing some earlier fundamental results: in particular, we provide a simple and enlightening proof of the refined Pinsker's inequality of Ordentlich and Weinberger and derive a sharper Bretagnolle-Huber inequality.
Type de document :
Pré-publication, Document de travail
Liste complète des métadonnées
Contributeur : Gilles Stoltz <>
Soumis le : vendredi 17 février 2017 - 19:27:05
Dernière modification le : vendredi 14 septembre 2018 - 09:16:06
Document(s) archivé(s) le : jeudi 18 mai 2017 - 15:26:52


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


  • HAL Id : hal-01470862, version 1
  • ARXIV : 1702.05985


Sebastien Gerchinovitz, Pierre Ménard, Gilles Stoltz. Fano's inequality for random variables. 2017. 〈hal-01470862v1〉



Consultations de la notice


Téléchargements de fichiers