English

Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning

Optimization and Control 2023-07-18 v2 Machine Learning

Abstract

Stochastic Approximation (SA) is a classical algorithm that has had since the early days a huge impact on signal processing, and nowadays on machine learning, due to the necessity to deal with a large amount of data observed with uncertainties. An exemplar special case of SA pertains to the popular stochastic (sub)gradient algorithm which is the working horse behind many important applications. A lesser-known fact is that the SA scheme also extends to non-stochastic-gradient algorithms such as compressed stochastic gradient, stochastic expectation-maximization, and a number of reinforcement learning algorithms. The aim of this article is to overview and introduce the non-stochastic-gradient perspectives of SA to the signal processing and machine learning audiences through presenting a design guideline of SA algorithms backed by theories. Our central theme is to propose a general framework that unifies existing theories of SA, including its non-asymptotic and asymptotic convergence results, and demonstrate their applications on popular non-stochastic-gradient algorithms. We build our analysis framework based on classes of Lyapunov functions that satisfy a variety of mild conditions. We draw connections between non-stochastic-gradient algorithms and scenarios when the Lyapunov function is smooth, convex, or strongly convex. Using the said framework, we illustrate the convergence properties of the non-stochastic-gradient algorithms using concrete examples. Extensions to the emerging variance reduction techniques for improved sample complexity will also be discussed.

Keywords

Cite

@article{arxiv.2302.11147,
  title  = {Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning},
  author = {Aymeric Dieuleveut and Gersende Fort and Eric Moulines and Hoi-To Wai},
  journal= {arXiv preprint arXiv:2302.11147},
  year   = {2023}
}

Comments

Accepted for publication at IEEE Transactions on Signal Processing; 31 pages, 7 pages of supplementary materials

R2 v1 2026-06-28T08:46:24.688Z