2023/12/13 by Sebastian Pokutta · 1 citation
paper · doi:10.1365/s13291-023-00275-x
crossref issued 2023/12/13 · crossref published 2023/12/13 · crossref published-online 2023/12/13 · crossref created 2023/12/13 · crossref deposited 2024/02/23 · crossref published-print 2024/03/01 · crossref indexed 2026/07/31
Abstract In this paper we provide an introduction to the Frank-Wolfe algorithm, a method for smooth convex optimization in the presence of (relatively) complicated constraints. We will present the algorithm, introduce key concepts, and establish important baseline results, such as e.g., primal and dual convergence. We will also discuss some of its properties, present a new adaptive step-size strategy as well as applications.