Title of article
Perturbation resilience of proximal gradient algorithm for composite objectives
Author/Authors
Guo ، Yanni - Civil Aviation University of China , Cui ، Wei - Civil Aviation University of China , Guo ، Yansha - Tianjin University of Technology and Education
Pages
10
From page
5566
To page
5575
Abstract
In this paper, we study the perturbation resilience of a proximal gradient algorithm under the general Hilbert space setting. With the assumption that the error sequence is summable, we prove that the iterative sequence converges weakly to a solution of the composite optimization problem. We also show the bounded perturbation resilience of this iterative method and apply it to the lasso problem.
Keywords
Perturbation resilience , proximal gradient algorithm , composite optimization , lasso problem
Journal title
Journal of Nonlinear Science and Applications
Serial Year
2017
Journal title
Journal of Nonlinear Science and Applications
Record number
2476750
Link To Document