Fano's inequality for random variables

DOI10.1214/19-STS716arXiv1702.05985MaRDI QIDQ6283393FDOQ6283393

Authors: Sébastien Gerchinovitz, Pierre Ménard, Gilles Stoltz 

Publication date: 20 February 2017

Abstract: We extend Fano's inequality, which controls the average probability of events in terms of the average of some $f$--divergences, to work with arbitrary events (not necessarily forming a partition) and even with arbitrary $[0,1]$--valued random variables, possibly in continuously infinite number. We provide two applications of these extensions, in which the consideration of random variables is particularly handy: we offer new and elegant proofs for existing lower bounds, on Bayesian posterior concentration (minimax or distribution-dependent) rates and on the regret in non-stochastic sequential learning.

Mathematics Subject Classification ID

Statistics (62-XX)

This page was built for publication: Fano's inequality for random variables

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6283393)