Compressed Momentum-based Single-Point Zeroth-Order Algorithm for Stochastic Distributed Nonconvex Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Linjing, Xie, Antai, Yi, Xinlei, Ren, Xiaoqiang, Wang, Xiaofan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918491641085952
author Chen, Linjing
Xie, Antai
Yi, Xinlei
Ren, Xiaoqiang
Wang, Xiaofan
author_facet Chen, Linjing
Xie, Antai
Yi, Xinlei
Ren, Xiaoqiang
Wang, Xiaofan
contents This paper studies a compressed momentum-based single-point zeroth-order algorithm for stochastic distributed nonconvex optimization, aiming to alleviate communication overhead and address the unavailability of explicit gradient information. In the developed framework, each agent has access only to stochastic zeroth-order information of its local objective function, performs local stochastic updates with momentum, and exchanges compressed updates with its neighbors. We theoretically prove that the proposed algorithm can achieve the exact solution with diminishing step sizes and can achieve a sublinear convergence rate towards a neighborhood of the stationary point with fixed step sizes. Numerical experiments validate the effectiveness and communication efficiency of the proposed algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2512_06366
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Compressed Momentum-based Single-Point Zeroth-Order Algorithm for Stochastic Distributed Nonconvex Optimization
Chen, Linjing
Xie, Antai
Yi, Xinlei
Ren, Xiaoqiang
Wang, Xiaofan
Optimization and Control
This paper studies a compressed momentum-based single-point zeroth-order algorithm for stochastic distributed nonconvex optimization, aiming to alleviate communication overhead and address the unavailability of explicit gradient information. In the developed framework, each agent has access only to stochastic zeroth-order information of its local objective function, performs local stochastic updates with momentum, and exchanges compressed updates with its neighbors. We theoretically prove that the proposed algorithm can achieve the exact solution with diminishing step sizes and can achieve a sublinear convergence rate towards a neighborhood of the stationary point with fixed step sizes. Numerical experiments validate the effectiveness and communication efficiency of the proposed algorithm.
title Compressed Momentum-based Single-Point Zeroth-Order Algorithm for Stochastic Distributed Nonconvex Optimization
topic Optimization and Control
url https://arxiv.org/abs/2512.06366