English

A nonsmooth Frank-Wolfe algorithm through a dual cutting-plane approach

Optimization and Control 2024-03-28 v1

Abstract

An extension of the Frank-Wolfe Algorithm (FWA), also known as Conditional Gradient algorithm, is proposed. In its standard form, the FWA allows to solve constrained optimization problems involving β\beta-smooth cost functions, calling at each iteration a Linear Minimization Oracle. More specifically, the oracle solves a problem obtained by linearization of the original cost function. The algorithm designed and investigated in this article, named Dualized Level-Set (DLS) algorithm, extends the FWA and allows to address a class of nonsmooth costs, involving in particular support functions. The key idea behind the construction of the DLS method is a general interpretation of the FWA as a cutting-plane algorithm, from the dual point of view. The DLS algorithm essentially results from a dualization of a specific cutting-plane algorithm, based on projections on some level sets. The DLS algorithm generates a sequence of primal-dual candidates, and we prove that the corresponding primal-dual gap converges with a rate of O(1/t)O(1/\sqrt{t}).

Keywords

Cite

@article{arxiv.2403.18744,
  title  = {A nonsmooth Frank-Wolfe algorithm through a dual cutting-plane approach},
  author = {Guilherme Mazanti and Thibault Moquet and Laurent Pfeiffer},
  journal= {arXiv preprint arXiv:2403.18744},
  year   = {2024}
}
R2 v1 2026-06-28T15:35:49.320Z