The continuous stochastic gradient method: part I–convergence theory

Max Grieshammer (), Lukas Pflug (), Michael Stingl () and Andrian Uihlein ()
Additional contact information
Max Grieshammer: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)
Lukas Pflug: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)
Michael Stingl: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)
Andrian Uihlein: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)

Computational Optimization and Applications, 2024, vol. 87, issue 3, No 9, 935-976

Abstract: Abstract In this contribution, we present a full overview of the continuous stochastic gradient (CSG) method, including convergence results, step size rules and algorithmic insights. We consider optimization problems in which the objective function requires some form of integration, e.g., expected values. Since approximating the integration by a fixed quadrature rule can introduce artificial local solutions into the problem while simultaneously raising the computational effort, stochastic optimization schemes have become increasingly popular in such contexts. However, known stochastic gradient type methods are typically limited to expected risk functions and inherently require many iterations. The latter is particularly problematic, if the evaluation of the cost function involves solving multiple state equations, given, e.g., in form of partial differential equations. To overcome these drawbacks, a recent article introduced the CSG method, which reuses old gradient sample information via the calculation of design dependent integration weights to obtain a better approximation to the full gradient. While in the original CSG paper convergence of a subsequence was established for a diminishing step size, here, we provide a complete convergence analysis of CSG for constant step sizes and an Armijo-type line search. Moreover, new methods to obtain the integration weights are presented, extending the application range of CSG to problems involving higher dimensional integrals and distributed data.

Keywords: Stochastic gradient scheme; Convergence analysis; Step size rule; Backtracking line search; Constant step size; 65K05; 90C06; 90C15; 90C30 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10589-023-00542-8 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:coopap:v:87:y:2024:i:3:d:10.1007_s10589-023-00542-8

Ordering information: This journal article can be ordered from
http://www.springer.com/math/journal/10589

DOI: 10.1007/s10589-023-00542-8

Access Statistics for this article

Computational Optimization and Applications is currently edited by William W. Hager

More articles in Computational Optimization and Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().