Zeroth-Order Methods for Stochastic Nonconvex Nonsmooth Composite Optimization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Ziyi, Yu, Peiran, Huang, Heng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908577340325888
author Chen, Ziyi
Yu, Peiran
Huang, Heng
author_facet Chen, Ziyi
Yu, Peiran
Huang, Heng
contents This work aims to solve a stochastic nonconvex nonsmooth composite optimization problem. Previous works on composite optimization problem requires the major part to satisfy Lipschitz smoothness or some relaxed smoothness conditions, which excludes some machine learning examples such as regularized ReLU network and sparse support matrix machine. In this work, we focus on stochastic nonconvex composite optimization problem without any smoothness assumptions. In particular, we propose two new notions of approximate stationary points for such optimization problem and obtain finite-time convergence results of two zeroth-order algorithms to these two approximate stationary points respectively. Finally, we demonstrate that these algorithms are effective using numerical experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2510_04446
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Zeroth-Order Methods for Stochastic Nonconvex Nonsmooth Composite Optimization
Chen, Ziyi
Yu, Peiran
Huang, Heng
Optimization and Control
Machine Learning
This work aims to solve a stochastic nonconvex nonsmooth composite optimization problem. Previous works on composite optimization problem requires the major part to satisfy Lipschitz smoothness or some relaxed smoothness conditions, which excludes some machine learning examples such as regularized ReLU network and sparse support matrix machine. In this work, we focus on stochastic nonconvex composite optimization problem without any smoothness assumptions. In particular, we propose two new notions of approximate stationary points for such optimization problem and obtain finite-time convergence results of two zeroth-order algorithms to these two approximate stationary points respectively. Finally, we demonstrate that these algorithms are effective using numerical experiments.
title Zeroth-Order Methods for Stochastic Nonconvex Nonsmooth Composite Optimization
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2510.04446