Extremely Fast Convergence Rates for Extremum Seeking Control with Polyak-Ruppert Averaging
Abstract
Stochastic approximation is a foundation for many algorithms found in machine learning and optimization. It is in general slow to converge: the mean square error vanishes as . A deterministic counterpart known as quasi-stochastic approximation is a viable alternative in many applications, including gradient-free optimization and reinforcement learning. It was assumed in prior research that the optimal achievable convergence rate is . It is shown in this paper that through design it is possible to obtain far faster convergence, of order , with arbitrary. Two techniques are introduced for the first time to achieve this rate of convergence. The theory is also specialized within the context of gradient-free optimization, and tested on standard benchmarks. The main results are based on a combination of novel application of results from number theory and techniques adapted from stochastic approximation theory.
Cite
@article{arxiv.2206.00814,
title = {Extremely Fast Convergence Rates for Extremum Seeking Control with Polyak-Ruppert Averaging},
author = {Caio Kalil Lauand and Sean Meyn},
journal= {arXiv preprint arXiv:2206.00814},
year = {2024}
}
Comments
36 pages, 14 figures