A Semismooth Newton Stochastic Proximal Point Algorithm with Variance Reduction
SIAM Journal on Optimization · 31.03.2024 · 34 (1) · 1157-1185
DOI: 10.1137/22m1488181 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Optimization, online erschienen am 26.03.2024. Verfasst von Andre Milzarek und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: Fundamental Research Fund–Shenzhen Research Institute of Big Data, Shenzhen Science and Technology Program.
Abstract (Originalsprache)
We develop an implementable stochastic proximal point (SPP) method for a class of weakly convex, composite optimization problems. The proposed stochastic proximal point algorithm incorporates a variance reduction mechanism and the resulting SPP updates are solved using an inexact semismooth Newton framework. We establish detailed convergence results that take the inexactness of the SPP steps into account and that are in accordance with existing convergence guarantees of (proximal) stochastic variance-reduced gradient methods. Numerical experiments show that the proposed algorithm competes favorably with other state-of-the-art methods and achieves higher robustness with respect to the step size selection.
Förderung
- Fundamental Research Fund–Shenzhen Research Institute of Big Data
- Shenzhen Science and Technology Program
Zitieren
APA
Milzarek, A., Schaipp, F., & Ulbrich, M. (2024). A Semismooth Newton Stochastic Proximal Point Algorithm with Variance Reduction. SIAM Journal on Optimization, 34(1), 1157-1185. https://doi.org/10.1137/22m1488181
Vancouver
Milzarek A, Schaipp F, Ulbrich M. A Semismooth Newton Stochastic Proximal Point Algorithm with Variance Reduction. SIAM Journal on Optimization. 2024;34(1):1157-1185. doi:10.1137/22m1488181
BibTeX
@article{Milzarek2024,
author = {Milzarek, Andre and Schaipp, Fabian and Ulbrich, Michael},
title = {A Semismooth Newton Stochastic Proximal Point Algorithm with Variance Reduction},
journal = {SIAM Journal on Optimization},
year = {2024},
volume = {34},
number = {1},
pages = {1157--1185},
doi = {10.1137/22m1488181}
}
EUVIMED