Frank–Wolfe and friends: a journey into projection-free first-order optimization methods
- Author(s)
- Immanuel Bomze, Francesco Rinaldi, Damiano Zeffiro
- Abstract
Invented some 65 years ago in a seminal paper by Marguerite Straus-Frank and Philip Wolfe, the Frank-Wolfe method recently enjoys a remarkable revival, fuelled by the need of fast and reliable first-order optimization methods in Data Science and other relevant application areas. This review tries to explain the success of this approach by illustrating versatility and applicability in a wide range of contexts, combined with an account on recent progress in variants, improving on both the speed and efficiency of this surprisingly simple principle of first-order optimization.
- Organisation(s)
- Department of Statistics and Operations Research, Research Network Data Science, Research Platform Governance of digital practices
- External organisation(s)
- University of Padova
- Journal
- 4 OR
- Volume
- 19
- Pages
- 313-345
- No. of pages
- 33
- ISSN
- 1619-4500
- DOI
- https://doi.org/10.1007/s10288-021-00493-y
- Publication date
- 09-2021
- Peer reviewed
- Yes
- Austrian Fields of Science 2012
- 101015 Operations research
- Keywords
- ASJC Scopus subject areas
- Theoretical Computer Science, Management Information Systems, Computational Theory and Mathematics, Management Science and Operations Research
- Portal url
- https://ucris.univie.ac.at/portal/en/publications/frankwolfe-and-friends-a-journey-into-projectionfree-firstorder-optimization-methods(d8e5ac9d-80b8-4112-9c2d-1ff124cda213).html