Proximal Quasi-Newton Method for Composite Optimization over the Stiefel Manifold

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Qinsi, Yang, Wei Hong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913653431730176
author Wang, Qinsi
Yang, Wei Hong
author_facet Wang, Qinsi
Yang, Wei Hong
contents In this paper, we consider the composite optimization problems over the Stiefel manifold. A successful method to solve this class of problems is the proximal gradient method proposed by Chen et al. Motivated by the proximal Newton-type techniques in the Euclidean space, we present a Riemannian proximal quasi-Newton method, named ManPQN, to solve the composite optimization problems. The global convergence of the ManPQN method is proved and iteration complexity for obtaining an $ε$-stationary point is analyzed. Under some mild conditions, we also establish the local linear convergence result of the ManPQN method. Numerical results are encouraging, which shows that the proximal quasi-Newton technique can be used to accelerate the proximal gradient method.
format Preprint
id arxiv_https___arxiv_org_abs_2501_09516
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Proximal Quasi-Newton Method for Composite Optimization over the Stiefel Manifold
Wang, Qinsi
Yang, Wei Hong
Optimization and Control
90C53
In this paper, we consider the composite optimization problems over the Stiefel manifold. A successful method to solve this class of problems is the proximal gradient method proposed by Chen et al. Motivated by the proximal Newton-type techniques in the Euclidean space, we present a Riemannian proximal quasi-Newton method, named ManPQN, to solve the composite optimization problems. The global convergence of the ManPQN method is proved and iteration complexity for obtaining an $ε$-stationary point is analyzed. Under some mild conditions, we also establish the local linear convergence result of the ManPQN method. Numerical results are encouraging, which shows that the proximal quasi-Newton technique can be used to accelerate the proximal gradient method.
title Proximal Quasi-Newton Method for Composite Optimization over the Stiefel Manifold
topic Optimization and Control
90C53
url https://arxiv.org/abs/2501.09516