A Simple Adaptive Proximal Gradient Method for Nonconvex Optimization
SIAM Journal on Optimization · 31.12.2026 · 36 (4) · 2530-2554
DOI: 10.1137/25m1809434 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Optimization, online erschienen am 11.11.2026. Verfasst von Zilong Ye und 3 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Ministry of Education of China, National Science Foundation.
Abstract (Originalsprache)
We consider composite nonconvex optimization problems where the objective function consists of a smooth nonconvex term (with Lipschitz-continuous gradient) and a convex (possibly nonsmooth) term. In this paper, we introduce a novel adaptive proximal gradient method (referred to as AdaPGNC) that is both parameter-free and line-search-free for solving this class of problems. It features a simple single-loop structure and achieves the theoretically optimal iteration/gradient evaluation complexity of [Formula: see text] for finding an [Formula: see text]-stationary point. The core innovation lies in designing an adaptive step size strategy that leverages upper and lower curvature estimates. A key technical contribution is the development of a novel Lyapunov function that effectively balances the function value gap and the squared norm of consecutive iterate differences, serving as a central component in our convergence analysis. Preliminary experimental results on several benchmark problems demonstrate that AdaPGNC is competitive against related existing methods.
Förderung
- National Natural Science Foundation of China
- Ministry of Education of China
- National Science Foundation
Zitieren
APA
Ye, Z., Ma, S., Yang, J., & Zhou, D. (2026). A Simple Adaptive Proximal Gradient Method for Nonconvex Optimization. SIAM Journal on Optimization, 36(4), 2530-2554. https://doi.org/10.1137/25m1809434
Vancouver
Ye Z, Ma S, Yang J, Zhou D. A Simple Adaptive Proximal Gradient Method for Nonconvex Optimization. SIAM Journal on Optimization. 2026;36(4):2530-2554. doi:10.1137/25m1809434
BibTeX
@article{Ye2026,
author = {Ye, Zilong and Ma, Shiqian and Yang, Junfeng and Zhou, Danqing},
title = {A Simple Adaptive Proximal Gradient Method for Nonconvex Optimization},
journal = {SIAM Journal on Optimization},
year = {2026},
volume = {36},
number = {4},
pages = {2530--2554},
doi = {10.1137/25m1809434}
}
EUVIMED