Salvato in:
Dettagli Bibliografici
Autori principali: Long, Xian-Jun, Zeng, Kang, Li, Gao-Xi, Dao, Minh N., Peng, Zai-Yun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.27156
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908622501445632
author Long, Xian-Jun
Zeng, Kang
Li, Gao-Xi
Dao, Minh N.
Peng, Zai-Yun
author_facet Long, Xian-Jun
Zeng, Kang
Li, Gao-Xi
Dao, Minh N.
Peng, Zai-Yun
contents In this paper, we consider a broad class of nonconvex and nonsmooth optimization problems, where one objective component is a nonsmooth weakly convex function composed with a linear operator. By integrating variable smoothing techniques with first-order methods, we propose a variable smoothing alternating proximal gradient algorithm that features flexible parameter choices for step sizes and smoothing levels. Under mild assumptions, we establish that the iteration complexity to reach an $\varepsilon$-approximate stationary point is $\mathcal{O}(\varepsilon^{-3})$. The proposed algorithm is evaluated on sparse signal recovery and image denoising problems. Numerical experiments demonstrate its effectiveness and superiority over existing algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2510_27156
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Variable Smoothing Alternating Proximal Gradient Algorithm for Coupled Composite Optimization
Long, Xian-Jun
Zeng, Kang
Li, Gao-Xi
Dao, Minh N.
Peng, Zai-Yun
Optimization and Control
In this paper, we consider a broad class of nonconvex and nonsmooth optimization problems, where one objective component is a nonsmooth weakly convex function composed with a linear operator. By integrating variable smoothing techniques with first-order methods, we propose a variable smoothing alternating proximal gradient algorithm that features flexible parameter choices for step sizes and smoothing levels. Under mild assumptions, we establish that the iteration complexity to reach an $\varepsilon$-approximate stationary point is $\mathcal{O}(\varepsilon^{-3})$. The proposed algorithm is evaluated on sparse signal recovery and image denoising problems. Numerical experiments demonstrate its effectiveness and superiority over existing algorithms.
title Variable Smoothing Alternating Proximal Gradient Algorithm for Coupled Composite Optimization
topic Optimization and Control
url https://arxiv.org/abs/2510.27156