Global convergence and asymptotic optimality of the heavy ball method for a class of non-convex optimization problems
Optimization and Control
2022-03-28 v2 Systems and Control
Systems and Control
Abstract
In this letter we revisit the famous heavy ball method and study its global convergence for a class of non-convex problems with sector-bounded gradient. We characterize the parameters that render the method globally convergent and yield the best -convergence factor. We show that for this family of functions, this convergence factor is superior to the factor obtained from the triple momentum method.
Keywords
Cite
@article{arxiv.2202.02914,
title = {Global convergence and asymptotic optimality of the heavy ball method for a class of non-convex optimization problems},
author = {Valery Ugrinovskii and Ian R. Petersen and Iman Shames},
journal= {arXiv preprint arXiv:2202.02914},
year = {2022}
}
Comments
6 pages, 4 figures, to appear in CSS Letters