We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Convergence properties of stochastic proximal subgradient method in solving a class of composite optimization problems with cardinality regularizer.
- Authors
Hu, Xiaoyin; Liu, Xin; Xiao, Nachuan
- Abstract
In this paper, we study a class of composite optimization problems, whose objective function is the summation of a bunch of nonsmooth nonconvex loss functions and a cardinality regularizer. Firstly we investigate the optimality condition of these problems and then suggest a stochastic proximal subgradient method (SPSG) to solve them. Then we establish the almost surely subsequence convergence of SPSG under mild assumptions. We emphasize that these assumptions are satisfied by a wide range of problems arising from training neural networks. Furthermore, we conduct preliminary numerical experiments to demonstrate the effectiveness and efficiency of SPSG in solving this class of problems.
- Subjects
SUBGRADIENT methods; STOCHASTIC convergence; NONSMOOTH optimization; PROBLEM solving
- Publication
Journal of Industrial & Management Optimization, 2024, Vol 20, Issue 5, p1
- ISSN
1547-5816
- Publication type
Article
- DOI
10.3934/jimo.2023149