A four-operator splitting algorithm for nonconvex and nonsmooth optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Alcantara, Jan Harold, Lee, Ching-pei, Takeda, Akiko
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916661259403264
author Alcantara, Jan Harold
Lee, Ching-pei
Takeda, Akiko
author_facet Alcantara, Jan Harold
Lee, Ching-pei
Takeda, Akiko
contents In this work, we address a class of nonconvex nonsmooth optimization problems where the objective function is the sum of two smooth functions (one of which is proximable) and two nonsmooth functions (one proper, closed and proximable, and the other continuous and weakly concave). We introduce a new splitting algorithm that extends the Davis-Yin splitting (DYS) algorithm to handle such four-term nonconvex nonsmooth problems. We prove that with appropriately chosen stepsizes, our algorithm exhibits global subsequential convergence to stationary points with a stationarity measure converging at a global rate of $1/T$, where $T$ is the number of iterations. When specialized to the setting of the DYS algorithm, our results allow for larger stepsizes compared to existing bounds in the literature. Experimental results demonstrate the practical applicability and effectiveness of our proposed algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2406_16025
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A four-operator splitting algorithm for nonconvex and nonsmooth optimization
Alcantara, Jan Harold
Lee, Ching-pei
Takeda, Akiko
Optimization and Control
90C26, 90C30
In this work, we address a class of nonconvex nonsmooth optimization problems where the objective function is the sum of two smooth functions (one of which is proximable) and two nonsmooth functions (one proper, closed and proximable, and the other continuous and weakly concave). We introduce a new splitting algorithm that extends the Davis-Yin splitting (DYS) algorithm to handle such four-term nonconvex nonsmooth problems. We prove that with appropriately chosen stepsizes, our algorithm exhibits global subsequential convergence to stationary points with a stationarity measure converging at a global rate of $1/T$, where $T$ is the number of iterations. When specialized to the setting of the DYS algorithm, our results allow for larger stepsizes compared to existing bounds in the literature. Experimental results demonstrate the practical applicability and effectiveness of our proposed algorithm.
title A four-operator splitting algorithm for nonconvex and nonsmooth optimization
topic Optimization and Control
90C26, 90C30
url https://arxiv.org/abs/2406.16025