Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/162832
Title: Adaptive evolution strategies for stochastic zeroth-order optimization
Authors: He, Xiaoyu
Zheng, Zibin
Chen, Zefeng
Zhou, Yuren
Keywords: Engineering::Computer science and engineering
Issue Date: 2022
Source: He, X., Zheng, Z., Chen, Z. & Zhou, Y. (2022). Adaptive evolution strategies for stochastic zeroth-order optimization. IEEE Transactions On Emerging Topics in Computational Intelligence, 6(5), 1271-1285. https://dx.doi.org/10.1109/TETCI.2022.3146330
Project: A19C1a0018 
Journal: IEEE Transactions on Emerging Topics in Computational Intelligence
Abstract: We consider solving a class of unconstrained optimization problems in which only stochastic estimates of the objective functions are available. Existing stochastic optimization methods are mainly extended from gradient-based methods, faced with the challenges of noisy function evaluations, hardness in choosing step-sizes, and probably ill-conditioned landscapes. This paper presents a stochastic evolution strategy (SES) framework and several adaptation schemes to avoid these challenges. The SES framework combines the ideas of population sampling and minibatch sampling in exploiting the zeroth-order gradient information, efficiently reducing the noise in both data selection and gradient approximation. In addition, it admits approximating the gradients using a non-isotropic Gaussian distribution to better capture the curvature information of the landscapes. Based on this framework, we implement a step-size adaptation rule and two covariance matrix adaptation rules, where the former can automatically tune the step-sizes and the latter are intended to cope with ill-conditioning. For SES with certain fixed step-sizes, we establish a nearly optimal convergence rate over smooth landscapes. We also show that using the adaptive step-sizes allows convergence at a slightly slower rate but without the need to know the smoothness constant. Several numerical experiments on machine learning problems verify the above theoretical results and suggest that the adaptive SES methods show much promise.
URI: https://hdl.handle.net/10356/162832
ISSN: 2471-285X
DOI: 10.1109/TETCI.2022.3146330
Rights: © 2022 IEEE. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

Page view(s)

17
Updated on Nov 30, 2022

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.