The reviewed record of science sign in
Pith

arxiv: 2410.05942 · v1 · pith:O3ZLKGY7 · submitted 2024-10-08 · cs.LG · math.OC

Single Point-Based Distributed Zeroth-Order Optimization with a Non-Convex Stochastic Objective Function

Reviewed by Pithpith:O3ZLKGY7open to challenge →

classification cs.LG math.OC
keywords optimizationdistributedmethodtechniquefracfunctiongradientnon-convex
0
0 comments X
read the original abstract

Zero-order (ZO) optimization is a powerful tool for dealing with realistic constraints. On the other hand, the gradient-tracking (GT) technique proved to be an efficient method for distributed optimization aiming to achieve consensus. However, it is a first-order (FO) method that requires knowledge of the gradient, which is not always possible in practice. In this work, we introduce a zero-order distributed optimization method based on a one-point estimate of the gradient tracking technique. We prove that this new technique converges with a single noisy function query at a time in the non-convex setting. We then establish a convergence rate of $O(\frac{1}{\sqrt[3]{K}})$ after a number of iterations K, which competes with that of $O(\frac{1}{\sqrt[4]{K}})$ of its centralized counterparts. Finally, a numerical example validates our theoretical results.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.