A generalized conditional gradient method for multiobjective composite optimization problems
Optimization and Control
2023-02-28 v1
Abstract
This article deals with multiobjective composite optimization problems that consist of simultaneously minimizing several objective functions, each of which is composed of a combination of smooth and non-smooth functions. To tackle these problems, we propose a generalized version of the conditional gradient method, also known as Frank-Wolfe method. The method is analyzed with three step size strategies, including Armijo-type, adaptive, and diminishing step sizes. We establish asymptotic convergence properties and iteration-complexity bounds, with and without convexity assumptions on the objective functions. Numerical experiments illustrating the practical behavior of the methods are presented.
Cite
@article{arxiv.2302.12912,
title = {A generalized conditional gradient method for multiobjective composite optimization problems},
author = {P. B. Assunção and O. P. Ferreira and L. F. Prudente},
journal= {arXiv preprint arXiv:2302.12912},
year = {2023}
}