Stochastic Optimization Over Proximally Smooth Sets
SIAM Journal on Optimization · 31.03.2025 · 35 (1) · 157-179
DOI: 10.1137/20m1320225 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Optimization, online erschienen am 10.01.2025. Verfasst von Damek Davis und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Science Foundation, AFOSR.
Abstract (Originalsprache)
We introduce a class of stochastic algorithms for minimizing weakly convex functions over proximally smooth sets. As their main building blocks, the algorithms use simplified models of the objective function and the constraint set, along with a retraction operation to restore feasibility. All the proposed methods come equipped with a finite time efficiency guarantee in terms of a natural stationarity measure. We discuss consequences for nonsmooth optimization over smooth manifolds and over sets cut out by weakly convex inequalities.
Förderung
- National Science Foundation
- AFOSR
Zitieren
APA
Davis, D., Drusvyatskiy, D., & Shi, Z. (2025). Stochastic Optimization Over Proximally Smooth Sets. SIAM Journal on Optimization, 35(1), 157-179. https://doi.org/10.1137/20m1320225
Vancouver
Davis D, Drusvyatskiy D, Shi Z. Stochastic Optimization Over Proximally Smooth Sets. SIAM Journal on Optimization. 2025;35(1):157-179. doi:10.1137/20m1320225
BibTeX
@article{Davis2025,
author = {Davis, Damek and Drusvyatskiy, Dmitriy and Shi, Zhan},
title = {Stochastic Optimization Over Proximally Smooth Sets},
journal = {SIAM Journal on Optimization},
year = {2025},
volume = {35},
number = {1},
pages = {157--179},
doi = {10.1137/20m1320225}
}
EUVIMED