An Inexact Preconditioned Zeroth-order Proximal Method for Composite Optimization

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Shanglin, Wang, Lei, Xiao, Nachuan, Liu, Xin
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929202185371648
author Liu, Shanglin
Wang, Lei
Xiao, Nachuan
Liu, Xin
author_facet Liu, Shanglin
Wang, Lei
Xiao, Nachuan
Liu, Xin
contents In this paper, we consider the composite optimization problem, where the objective function integrates a continuously differentiable loss function with a nonsmooth regularization term. Moreover, only the function values for the differentiable part of the objective function are available. To efficiently solve this composite optimization problem, we propose a preconditioned zeroth-order proximal gradient method in which the gradients and preconditioners are estimated by finite-difference schemes based on the function values at the same trial points. We establish the global convergence and worst-case complexity for our proposed method. Numerical experiments exhibit the superiority of our developed method.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03565
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Inexact Preconditioned Zeroth-order Proximal Method for Composite Optimization
Liu, Shanglin
Wang, Lei
Xiao, Nachuan
Liu, Xin
Optimization and Control
In this paper, we consider the composite optimization problem, where the objective function integrates a continuously differentiable loss function with a nonsmooth regularization term. Moreover, only the function values for the differentiable part of the objective function are available. To efficiently solve this composite optimization problem, we propose a preconditioned zeroth-order proximal gradient method in which the gradients and preconditioners are estimated by finite-difference schemes based on the function values at the same trial points. We establish the global convergence and worst-case complexity for our proposed method. Numerical experiments exhibit the superiority of our developed method.
title An Inexact Preconditioned Zeroth-order Proximal Method for Composite Optimization
topic Optimization and Control
url https://arxiv.org/abs/2401.03565