Exponential inequality for chaos based on sampling without replacement

Creators: Hodara, Pierre; Reynaud-Bouret, Patricia

Others:: Mathématiques et Informatique Appliquées du Génome à l'Environnement [Jouy-En-Josas] (MaIAGE) ; Institut National de la Recherche Agronomique (INRA); COMUE Université Côte d'Azur (2015-2019) (COMUE UCA); FAPESP project Research, Innovation and Dissemination Center for Neuromathematics [2013/07699-0, 2016/17655-8]; French government [ANR-15-IDEX-01]; structuring program C@UCA of University Cote d'Azur; University of Nice Sophia-Antipolis

Description

We are interested in the behavior of particular functionals, in a framework where the only source of randomness is a sampling without replacement. More precisely the aim of this short note is to prove an exponential concentration inequality for special U-statistics of order 2, that can be seen as chaos. (C) 2018 Published by Elsevier B.V.

Abstract

International audience

Exponential inequality for chaos based on sampling without replacement

Description

Abstract

Additional details