The Proximal Gradient Method for Composite Optimization Problems on Riemannian Manifolds-Reference-Cited by-同舟云学术

The Proximal Gradient Method for Composite Optimization Problems on Riemannian Manifolds

Published:2024-08-25 Issue:17 Volume:12 Page:2638
ISSN:2227-7390
Container-title:Mathematics
language:en
Short-container-title:Mathematics

Author:

Li Xiaobo¹

Affiliation:

1. School of Sciences, Civil Aviation Flight University of China, Guanghan 618300, China

Abstract

In this paper, the composite optimization problem is studied on Riemannian manifolds. To tackle this problem, the proximal gradient method to solve composite optimization problems is proposed on Riemannian manifolds. Under some reasonable conditions, the convergence of the proximal gradient method with the backtracking procedure in the nonconvex case is presented. Furthermore, a sublinear convergence rate and the complexity result of the proximal gradient method for convex case are also established on Riemannian manifolds.

Funder

Young Scientists Fund of the National Natural Science Foundation of China

Natural Science Foundation of Sichuan

Fundamental Research Funds for the Central Universities

Publisher

MDPI AG

Link

https://www.mdpi.com/2227-7390/12/17/2638/pdf

Reference25 articles.

1. Gradient methods for minimizing composite functions;Nesterov;Neural Comput.,2012

2. A fast iterative shrinkage-thresholding algorithm for linear inverse problems;Beck;Siam J. Imaging Sci.,2009

3. Block successive upper-bound minimization for solving a class of composite optimization problems;Liu;Math. Program.,2015

4. Smoothing methods for nonsmooth, nonconvex minimization;Chen;J. Comput. Appl. Math.,2012

5. A Iteratively Reweighted Least Squares Algorithm for Sparse Regularization;Becker;J. Comput. Graph. Stat.,2011