In this letter, we first propose a \underline{Z}eroth-\underline{O}rder c\underline{O}ordinate \underline{M}ethod~(ZOOM) to solve the stochastic optimization problem over a decentralized network with only zeroth-order~(ZO) oracle feedback available. Moreover, we equip a simple mechanism "powerball" to ZOOM and propose ZOOM-PB to accelerate the convergence of ZOOM. Compared with the existing methods, we verify the proposed algorithms through two benchmark examples in the literature, namely the black-box binary classification and the generating adversarial examples from black-box DNNs in order to compare with the existing state-of-the-art centralized and distributed ZO algorithms. The numerical results demonstrate a faster convergence rate of the proposed algorithms.
@article{arxiv.2204.04743,
title = {Zeroth-Order Stochastic Coordinate Methods for Decentralized Non-convex Optimization},
author = {Shengjun Zhang and Tan Shen and Hongwei Sun and Yunlong Dong and Dong Xie and Heng Zhang},
journal= {arXiv preprint arXiv:2204.04743},
year = {2022}
}
Comments
arXiv admin note: substantial text overlap with arXiv:2109.03224