An Inexact Preconditioned Zeroth-order Proximal Method for Composite Optimization
Optimization and Control
2024-01-09 v1
Abstract
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.
Cite
@article{arxiv.2401.03565,
title = {An Inexact Preconditioned Zeroth-order Proximal Method for Composite Optimization},
author = {Shanglin Liu and Lei Wang and Nachuan Xiao and Xin Liu},
journal= {arXiv preprint arXiv:2401.03565},
year = {2024}
}