Accelerated Zeroth-order Algorithm for Stochastic Distributed Nonconvex Optimization

MaRDI QIDQ6377062zbMATH OpenFDO

Authors Shengjun Zhang, Colleen P. Bailey

Publication date 7 September 2021

Abstract: This paper investigates how to accelerate the convergence of distributed optimization algorithms on nonconvex problems with zeroth-order information available only. We propose a zeroth-order (ZO) distributed primal-dual stochastic coordinates algorithm equipped with "powerball" method to accelerate. We prove that the proposed algorithm has a convergence rate of $mathcalO(sqrtp/sqrtnT)$ for general nonconvex cost functions. We consider solving the generation of adversarial examples from black-box DNNs problem to compare with the existing state-of-the-art centralized and distributed ZO algorithms. The numerical results demonstrate the faster convergence rate of the proposed algorithm and match the theoretical analysis.

This page was built for publication: Accelerated Zeroth-order Algorithm for Stochastic Distributed Nonconvex Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6377062)