Randomized block proximal method with locally Lipschitz continuous gradient

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pérez-Aros, Pedro, Torregrosa-Belén, David
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916691809665024
author Pérez-Aros, Pedro
Torregrosa-Belén, David
author_facet Pérez-Aros, Pedro
Torregrosa-Belén, David
contents Block-coordinate algorithms are recognized to furnish efficient iterative schemes for addressing large-scale problems, especially when the computation of full derivatives entails substantial memory requirements and computational efforts. In this paper, we investigate a randomized block proximal gradient algorithm for minimizing the sum of a differentiable function and a separable proper lower-semicontinuous function, both possibly nonconvex. In contrast to previous works, we only assume that the partial gradients of the differentiable function are locally Lipschitz continuous. At each iteration, the method adaptively selects a proximal stepsize to satisfy a sufficient decrease condition without prior knowledge of the local Lipschitz moduli of the partial gradients of the differentiable function. In addition, we incorporate the possibility of conducting an additional linesearch to enhance the performance of the algorithm. Our main result establishes subsequential convergence to a stationary point of the problem almost surely. Finally, we provide numerical validation of the method in an experiment in image compression using a nonnegative matrix factorization model.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11410
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Randomized block proximal method with locally Lipschitz continuous gradient
Pérez-Aros, Pedro
Torregrosa-Belén, David
Optimization and Control
90C26, 90C30, 65K05, 90C06
Block-coordinate algorithms are recognized to furnish efficient iterative schemes for addressing large-scale problems, especially when the computation of full derivatives entails substantial memory requirements and computational efforts. In this paper, we investigate a randomized block proximal gradient algorithm for minimizing the sum of a differentiable function and a separable proper lower-semicontinuous function, both possibly nonconvex. In contrast to previous works, we only assume that the partial gradients of the differentiable function are locally Lipschitz continuous. At each iteration, the method adaptively selects a proximal stepsize to satisfy a sufficient decrease condition without prior knowledge of the local Lipschitz moduli of the partial gradients of the differentiable function. In addition, we incorporate the possibility of conducting an additional linesearch to enhance the performance of the algorithm. Our main result establishes subsequential convergence to a stationary point of the problem almost surely. Finally, we provide numerical validation of the method in an experiment in image compression using a nonnegative matrix factorization model.
title Randomized block proximal method with locally Lipschitz continuous gradient
topic Optimization and Control
90C26, 90C30, 65K05, 90C06
url https://arxiv.org/abs/2504.11410