Regular self-proximal distances are Bregman

Author	dc.contributor.author	Álvarez, Felipe
Author	dc.contributor.author	Correa Fontecilla, Rafael
Author	dc.contributor.author	Marechal, Matthieu
Admission date	dc.date.accessioned	2019-05-29T13:38:45Z
Available date	dc.date.available	2019-05-29T13:38:45Z
Publication date	dc.date.issued	2017
Cita de ítem	dc.identifier.citation	Journal of Convex Analysis Volume 24 (2017), No. 1, 135–148
Identifier	dc.identifier.issn	09446532
Identifier	dc.identifier.uri	https://repositorio.uchile.cl/handle/2250/168971
Abstract	dc.description.abstract	Bregman distances play a key role in generalized versions of the proximal algorithm. This paper proposes a new characterization of Bregman distances in terms of their gradient and Hessian matrix. Thanks to this characterization, we obtain two results: all the so called self-proximal distances are Bregman, and all the induced proximal distances, under some regularity assumptions, are Bregman functions.
Lenguage	dc.language.iso	en
Publisher	dc.publisher	Heldermann Verlag
Type of license	dc.rights	Attribution-NonCommercial-NoDerivs 3.0 Chile
Link to License	dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/cl/
Source	dc.source	Journal of Convex Analysis
Keywords	dc.subject	Analysis
Keywords	dc.subject	Mathematics (all)
Título	dc.title	Regular self-proximal distances are Bregman
Document type	dc.type	Artículo de revista
Cataloguer	uchile.catalogador	laj
Indexation	uchile.index	Artículo de publicación SCOPUS
uchile.cosecha	uchile.cosecha	SI

Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivs 3.0 Chile