Global Convergence and Acceleration for Single Observation Gradient Free Optimization
Optimization and Control
2025-09-05 v1
Abstract
Simultaneous perturbation stochastic approximation (SPSA) is an approach to gradient-free optimization introduced by Spall as a simplification of the approach of Kiefer and Wolfowitz. In many cases the most attractive option is the single-sample version known as 1SPSA, which is the focus of the present paper, containing two major contributions: a modification of the algorithm designed to ensure convergence from arbitrary initial condition, and a new approach to exploration to dramatically accelerate the rate of convergence. Examples are provided to illustrate the theory, and to demonstrate that estimates from unmodified 1SPSA may diverge even for a quadratic objective function.
Cite
@article{arxiv.2509.04424,
title = {Global Convergence and Acceleration for Single Observation Gradient Free Optimization},
author = {Caio Kalil Lauand and Sean Meyn},
journal= {arXiv preprint arXiv:2509.04424},
year = {2025}
}
Comments
12 pages, 2 figures