Frank–Wolfe and friends: a journey into projection-free first-order optimization methods-Reference-Cited by-同舟云学术

Frank–Wolfe and friends: a journey into projection-free first-order optimization methods

Published:2021-09 Issue:3 Volume:19 Page:313-345
ISSN:1619-4500
Container-title:4OR
language:en
Short-container-title:4OR-Q J Oper Res

Author:

Bomze Immanuel M.^ORCID,Rinaldi Francesco,Zeffiro Damiano

Abstract

AbstractInvented 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.

Funder

University of Vienna

Publisher

Springer Science and Business Media LLC

Subject

Computational Theory and Mathematics,Theoretical Computer Science,Management Information Systems,Management Science and Operations Research

Link

https://link.springer.com/content/pdf/10.1007/s10288-021-00493-y.pdf

Reference96 articles.

1. Ahipaşaoğlu SD, Sun P, Todd MJ (2008) Linear convergence of a modified Frank–Wolfe algorithm for computing minimum-volume enclosing ellipsoids. Optim Methods Soft 23(1):5–19

2. Ahipaşaoğlu SD, Todd MJ (2013) A modified Frank–Wolfe algorithm for computing minimum-area enclosing ellipsoidal cylinders: Theory and algorithms. Comput Geom 46(5):494–519

3. Allen-Zhu Z, Hazan E, Hu W, Li Y (2017) Linear convergence of a Frank–Wolfe type algorithm over trace-norm balls. Adv Neural Inf Process Syst 2017:6192–6201

4. Bach F et al (2013) Learning with submodular functions: A convex optimization perspective. Foundations and Trends$$\textregistered $$. Mach Learn 6(2–3):145–373

5. Bashiri MA, Zhang X (2017) Decomposition-invariant conditional gradient for general polytopes with line search. In: Advances in neural information processing systems, pp 2690–2700

Cited by 15 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Projection free methods on product domains;Computational Optimization and Applications;2024-06-04

2. On Some Works of Boris Teodorovich Polyak on the Convergence of Gradient Methods and Their Development;Computational Mathematics and Mathematical Physics;2024-04

3. Catching-Up Algorithm with Approximate Projections for Moreau’s Sweeping Processes;Journal of Optimization Theory and Applications;2024-03-18

4. 21 volumes for the 21st century;4OR;2024-03

5. Frank–Wolfe-type methods for a class of nonconvex inequality-constrained problems;Mathematical Programming;2024-02-03