A Mirror Inertial Forward–Reflected–Backward Splitting: Convergence Analysis Beyond Convexity and Lipschitz Smoothness
Journal of Optimization Theory and Applications · 2024-11 · 203 (2) · 1127-1159
DOI: 10.1007/s10957-024-02383-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Optimization Theory and Applications, online erschienen am 20.02.2024. Verfasst von Ziyuan Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
This work investigates a Bregman and inertial extension of the forward–reflected–backward algorithm (Malitsky and Tam in SIAM J Optim 30:1451–1472, 2020) applied to structured nonconvex minimization problems under relative smoothness. To this end, the proposed algorithm hinges on two key features: taking inertial steps in the dual space, and allowing for possibly negative inertial values. The interpretation of relative smoothness as a two-sided weak convexity condition proves beneficial in providing tighter stepsize ranges. Our analysis begins with studying an envelope function associated with the algorithm that takes inertial terms into account through a novel product space formulation. Such construction substantially differs from similar objects in the literature and could offer new insights for extensions of splitting algorithms. Global convergence and rates are obtained by appealing to the Kurdyka–Łojasiewicz property.
Förderung
- Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
Wang, Z., Themelis, A., Ou, H., & Wang, X. (2024). A Mirror Inertial Forward–Reflected–Backward Splitting: Convergence Analysis Beyond Convexity and Lipschitz Smoothness. Journal of Optimization Theory and Applications, 203(2), 1127-1159. https://doi.org/10.1007/s10957-024-02383-9
Vancouver
Wang Z, Themelis A, Ou H, Wang X. A Mirror Inertial Forward–Reflected–Backward Splitting: Convergence Analysis Beyond Convexity and Lipschitz Smoothness. Journal of Optimization Theory and Applications. 2024;203(2):1127-1159. doi:10.1007/s10957-024-02383-9
BibTeX
@article{Wang2024,
author = {Wang, Ziyuan and Themelis, Andreas and Ou, Hongjia and Wang, Xianfu},
title = {A Mirror Inertial Forward–Reflected–Backward Splitting: Convergence Analysis Beyond Convexity and Lipschitz Smoothness},
journal = {Journal of Optimization Theory and Applications},
year = {2024},
volume = {203},
number = {2},
pages = {1127--1159},
doi = {10.1007/s10957-024-02383-9}
}
EUVIMED