Simultaneous perturbation stochastic approximation: towards one-measurement per iteration
Optimization and Control
2022-03-08 v1
Abstract
When measuring the value of a function to be minimized is not only expensive but also with noise, the popular simultaneous perturbation stochastic approximation (SPSA) algorithm requires only two function values in each iteration. In this paper, we propose a method requiring only one function measurement value per iteration in the average sense. We prove the strong convergence and asymptotic normality of the new algorithm. Experimental results show the effectiveness and potential of our algorithm.
Cite
@article{arxiv.2203.03075,
title = {Simultaneous perturbation stochastic approximation: towards one-measurement per iteration},
author = {Shiru Li and Yong Xia and Zi Xu},
journal= {arXiv preprint arXiv:2203.03075},
year = {2022}
}
Comments
17 pages, 3 figures