A Riemannian Proximal Newton Method
SIAM Journal on Optimization · 31.03.2024 · 34 (1) · 654-681
DOI: 10.1137/23m1565097 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Optimization, online erschienen am 09.02.2024. Verfasst von Wutao Si und 4 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
In recent years, the proximal gradient method and its variants have been generalized to Riemannian manifolds for solving optimization problems with an additively separable structure, i.e., [Formula: see text], where [Formula: see text] is continuously differentiable, and [Formula: see text] may be nonsmooth but convex with computationally reasonable proximal mapping. In this paper, we generalize the proximal Newton method to embedded submanifolds for solving the type of problem with [Formula: see text]. The generalization relies on the Weingarten and semismooth analysis. It is shown that the Riemannian proximal Newton method has a local superlinear convergence rate under certain reasonable assumptions. Moreover, a hybrid version is given by concatenating a Riemannian proximal gradient method and the Riemannian proximal Newton method. It is shown that if the switch parameter is chosen appropriately, then the hybrid method converges globally and also has a local superlinear convergence rate. Numerical experiments on random and synthetic data are used to demonstrate the performance of the proposed methods.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Si, W., Absil, P., Huang, W., Jiang, R., & Vary, S. (2024). A Riemannian Proximal Newton Method. SIAM Journal on Optimization, 34(1), 654-681. https://doi.org/10.1137/23m1565097
Vancouver
Si W, Absil P, Huang W, Jiang R, Vary S. A Riemannian Proximal Newton Method. SIAM Journal on Optimization. 2024;34(1):654-681. doi:10.1137/23m1565097
BibTeX
@article{Si2024,
author = {Si, Wutao and Absil, P.-A. and Huang, Wen and Jiang, Rujun and Vary, Simon},
title = {A Riemannian Proximal Newton Method},
journal = {SIAM Journal on Optimization},
year = {2024},
volume = {34},
number = {1},
pages = {654--681},
doi = {10.1137/23m1565097}
}
EUVIMED