Concentration inequalities for separately convex functions

Abstract : We provide new comparison inequalities for separately convex functions of independent random variables. Our method is based on the decomposition in Doob martingale. However we only impose that the martingale increments are stochastically bounded. For this purpose, building on the results of Bentkus ([4], [5], [6]), we establish comparison inequalities for random variables stochastically dominated from below and from above. We illustrate our main results by showing how they can be used to derive deviation or moment inequalities for functions which are both separately convex and separately Lipschitz, weighted empirical distribution functions, suprema of randomized empirical processes and chaos of order two.
Type de document :
Article dans une revue
Bernoulli, Bernoulli Society for Mathematical Statistics and Probability, 2018, 24 (4A), pp.2906-2933. 〈http://www.bernoulli-society.org/index.php/publications/bernoulli-journal/bernoulli-journal〉. 〈10.3150/17-BEJ949〉
Liste complète des métadonnées

Littérature citée [20 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01344861
Contributeur : Antoine Marchina <>
Soumis le : lundi 26 mars 2018 - 15:32:57
Dernière modification le : mercredi 28 mars 2018 - 01:16:42

Fichier

BEJ949_final.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Citation

Antoine Marchina. Concentration inequalities for separately convex functions. Bernoulli, Bernoulli Society for Mathematical Statistics and Probability, 2018, 24 (4A), pp.2906-2933. 〈http://www.bernoulli-society.org/index.php/publications/bernoulli-journal/bernoulli-journal〉. 〈10.3150/17-BEJ949〉. 〈hal-01344861v2〉

Partager

Métriques

Consultations de la notice

94

Téléchargements de fichiers

152