A New Inexact Manifold Proximal Linear Algorithm with Adaptive Stopping Criteria

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zheng, Zhong, Yu, Xin, Ma, Shiqian, Xue, Lingzhou
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909893749899264
author Zheng, Zhong
Yu, Xin
Ma, Shiqian
Xue, Lingzhou
author_facet Zheng, Zhong
Yu, Xin
Ma, Shiqian
Xue, Lingzhou
contents This paper proposes a new inexact manifold proximal linear (IManPL) algorithm for solving nonsmooth, nonconvex composite optimization problems over an embedded submanifold. At each iteration, IManPL solves a convex subproblem inexactly, guided by two adaptive stopping criteria. We establish convergence guarantees and show that IManPL achieves the best first-order oracle complexity for solving this class of problems. Numerical experiments on sparse spectral clustering and sparse principal component analysis demonstrate that our methods outperform existing approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19234
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A New Inexact Manifold Proximal Linear Algorithm with Adaptive Stopping Criteria
Zheng, Zhong
Yu, Xin
Ma, Shiqian
Xue, Lingzhou
Optimization and Control
This paper proposes a new inexact manifold proximal linear (IManPL) algorithm for solving nonsmooth, nonconvex composite optimization problems over an embedded submanifold. At each iteration, IManPL solves a convex subproblem inexactly, guided by two adaptive stopping criteria. We establish convergence guarantees and show that IManPL achieves the best first-order oracle complexity for solving this class of problems. Numerical experiments on sparse spectral clustering and sparse principal component analysis demonstrate that our methods outperform existing approaches.
title A New Inexact Manifold Proximal Linear Algorithm with Adaptive Stopping Criteria
topic Optimization and Control
url https://arxiv.org/abs/2508.19234