The Frank-Wolfe Algorithm: A Short Introduction-Reference-Cited by-同舟云学术

The Frank-Wolfe Algorithm: A Short Introduction

Published:2023-12-13 Issue: Volume: Page:
ISSN:0012-0456
Container-title:Jahresbericht der Deutschen Mathematiker-Vereinigung
language:en
Short-container-title:Jahresber. Dtsch. Math. Ver.

Author:

Pokutta Sebastian

Abstract

AbstractIn 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.

Funder

Zuse-Institut Berlin

Publisher

Springer Fachmedien Wiesbaden GmbH

Subject

General Earth and Planetary Sciences,General Environmental Science

Link

https://link.springer.com/content/pdf/10.1365/s13291-023-00275-x.pdf

Reference87 articles.

1. Anari, N., Haghtalab, N., Naor, S., Pokutta, S., Singh, M., Torrico, A.: Structured robust submodular maximization: offline and online algorithms. In: Proceedings of AISTATS (2019)

2. Anari, N., Haghtalab, N., Naor, S., Pokutta, S., Singh, M., Torrico, A.: Structured robust submodular maximization: offline and online algorithms. INFORMS J. Comput. 33, 1259–1684 (2021)

3. Bach, F.: Duality between subgradient and conditional gradient methods. SIAM J. Optim. 25(1), 115–129 (2015)

4. Bach, F.: Submodular functions: from discrete to continuous domains. Math. Program. 175, 419–459 (2019)

5. Badanidiyuru, A., Vondrák, J.: Fast algorithms for maximizing submodular functions. In: Proceedings of the 25th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), pp. 1497–1514 (2014)