Convergence Analysis of the ProbAbilistic Gradient Estimator Algorithm for Weakly Convex Finite-Sum Optimization
Journal of Optimization Theory and Applications · 2026-08 · 210 (2)
DOI: 10.1007/s10957-026-03065-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Optimization Theory and Applications, online erschienen am 28.07.2026. Verfasst von Laurent Condat und 1 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: King Abdullah University of Science and Technology.
Abstract (Originalsprache)
The ProbAbilistic Gradient Estimator algorithm (PAGE), a stochastic algorithm introduced by Li et al. in 2021, was designed to find stationary points for the average of smooth nonconvex functions. In this work, we study PAGE within the broad framework of τ\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\tau $$\end{document}-weakly convex functions, providing a continuous interpolation between the general nonconvex L-smooth regime (τ=L\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\tau =L$$\end{document}) and the convex regime (τ=0\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\tau =0$$\end{document}). We establish new convergence rates for PAGE, showing that its complexity improves as τ\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\tau $$\end{document} decreases.
Förderung
- King Abdullah University of Science and Technology
Zitieren
APA
Condat, L., & Richtárik, P. (2026). Convergence Analysis of the ProbAbilistic Gradient Estimator Algorithm for Weakly Convex Finite-Sum Optimization. Journal of Optimization Theory and Applications, 210(2). https://doi.org/10.1007/s10957-026-03065-4
Vancouver
Condat L, Richtárik P. Convergence Analysis of the ProbAbilistic Gradient Estimator Algorithm for Weakly Convex Finite-Sum Optimization. Journal of Optimization Theory and Applications. 2026;210(2). doi:10.1007/s10957-026-03065-4
BibTeX
@article{Condat2026,
author = {Condat, Laurent and Richtárik, Peter},
title = {Convergence Analysis of the ProbAbilistic Gradient Estimator Algorithm for Weakly Convex Finite-Sum Optimization},
journal = {Journal of Optimization Theory and Applications},
year = {2026},
volume = {210},
number = {2},
doi = {10.1007/s10957-026-03065-4}
}
EUVIMED