English

Extremely Fast Convergence Rates for Extremum Seeking Control with Polyak-Ruppert Averaging

Optimization and Control 2024-03-26 v2

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 O(n1)O(n^{-1}). 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 O(n2)O(n^{-2}). It is shown in this paper that through design it is possible to obtain far faster convergence, of order O(n4+δ)O(n^{-4+\delta}), with δ>0\delta>0 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.

Keywords

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

R2 v1 2026-06-24T11:36:40.046Z