Forward-Backward algorithms for weakly convex problems

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bednarczuk, Ewa, Bruccola, Giovanni, Scrivanti, Gabriele, Tran, The Hung
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916295999488000
author Bednarczuk, Ewa
Bruccola, Giovanni
Scrivanti, Gabriele
Tran, The Hung
author_facet Bednarczuk, Ewa
Bruccola, Giovanni
Scrivanti, Gabriele
Tran, The Hung
contents We investigate the convergence properties of exact and inexact forward-backward algorithms to minimise the sum of two weakly convex functions defined on a Hilbert space, where one has a Lipschitz-continuous gradient. We show that the exact forward-backward algorithm converges strongly to a global solution, provided that the objective function satisfies a sharpness condition. For the inexact forward-backward algorithm, the same condition ensures that the distance from the iterates to the solution set approaches a positive threshold depending on the accuracy level of the proximal computations. As an application of the considered setting, we provide numerical experiments related to discrete tomography.
format Preprint
id arxiv_https___arxiv_org_abs_2303_14021
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Forward-Backward algorithms for weakly convex problems
Bednarczuk, Ewa
Bruccola, Giovanni
Scrivanti, Gabriele
Tran, The Hung
Optimization and Control
90C30 90C26 90C51 65K10 52A01
We investigate the convergence properties of exact and inexact forward-backward algorithms to minimise the sum of two weakly convex functions defined on a Hilbert space, where one has a Lipschitz-continuous gradient. We show that the exact forward-backward algorithm converges strongly to a global solution, provided that the objective function satisfies a sharpness condition. For the inexact forward-backward algorithm, the same condition ensures that the distance from the iterates to the solution set approaches a positive threshold depending on the accuracy level of the proximal computations. As an application of the considered setting, we provide numerical experiments related to discrete tomography.
title Forward-Backward algorithms for weakly convex problems
topic Optimization and Control
90C30 90C26 90C51 65K10 52A01
url https://arxiv.org/abs/2303.14021