Salvato in:
Dettagli Bibliografici
Autori principali: Greenstein, Dan, Hallak, Nadav
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2305.01055
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929607864745984
author Greenstein, Dan
Hallak, Nadav
author_facet Greenstein, Dan
Hallak, Nadav
contents We consider the minimization of a sum of a smooth function with a nonsmooth composite function, where the composition is applied on a random linear mapping. This random composite model encompasses many problems, and can especially capture realistic scenarios in which the data is sampled during the optimization process. We propose and analyze a method that combines the classical Augmented Lagrangian framework with a sampling mechanism and adaptive update of the penalty parameter. We show that every accumulation point of the sequence produced by our algorithm is almost surely a critical point.
format Preprint
id arxiv_https___arxiv_org_abs_2305_01055
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle An Augmented Lagrangian Approach to Composite Problems with a Random Linear Operator
Greenstein, Dan
Hallak, Nadav
Optimization and Control
We consider the minimization of a sum of a smooth function with a nonsmooth composite function, where the composition is applied on a random linear mapping. This random composite model encompasses many problems, and can especially capture realistic scenarios in which the data is sampled during the optimization process. We propose and analyze a method that combines the classical Augmented Lagrangian framework with a sampling mechanism and adaptive update of the penalty parameter. We show that every accumulation point of the sequence produced by our algorithm is almost surely a critical point.
title An Augmented Lagrangian Approach to Composite Problems with a Random Linear Operator
topic Optimization and Control
url https://arxiv.org/abs/2305.01055