Proximity Operators of Discrete Information Divergences

Abstract : While ϕ-divergences have been extensively studied in convex analysis, their use in optimization problems often remains challenging. In this regard, one of the main shortcomings of existing methods is that the minimization of ϕ-divergences is usually performed with respect to one of their arguments, possibly within alternating optimization techniques. In this paper, we overcome this limitation by deriving new closed-form expressions for the proximity operator of such two-variable functions. This makes it possible to employ standard proximal methods for efficiently solving a wide range of convex optimization problems involving ϕ-divergences. In addition, we show that these proximity operators are useful to compute the epigraphical projection of several functions. The proposed proximal tools are numerically validated in the context of optimal query execution within database management systems, where the problem of selectivity estimation plays a central role. Experiments are carried out on small to large scale scenarios.
Type de document :
Article dans une revue
IEEE Transactions on Information Theory, Institute of Electrical and Electronics Engineers, 2018, 64 (2), pp.1092-1104
Liste complète des métadonnées

Littérature citée [93 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01672646
Contributeur : Giovanni Chierchia <>
Soumis le : mardi 26 décembre 2017 - 15:27:18
Dernière modification le : mercredi 4 juillet 2018 - 16:33:28

Fichier

ArticleIT.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01672646, version 1

Citation

Mireille Gheche, Giovanni Chierchia, Jean-Christophe Pesquet. Proximity Operators of Discrete Information Divergences. IEEE Transactions on Information Theory, Institute of Electrical and Electronics Engineers, 2018, 64 (2), pp.1092-1104. 〈hal-01672646〉

Partager

Métriques

Consultations de la notice

203

Téléchargements de fichiers

106