Linearization Algorithms for Fully Composite Optimization

02/24/2023

∙

by   Maria-Luiza Vladarean, et al.

∙

0

∙

share

In this paper, we study first-order algorithms for solving fully composite optimization problems over bounded sets. We treat the differentiable and non-differentiable parts of the objective separately, linearizing only the smooth components. This provides us with new generalizations of the classical and accelerated Frank-Wolfe methods, that are applicable to non-differentiable problems whenever we can access the structure of the objective. We prove global complexity bounds for our algorithms that are optimal in several settings.