Complexity of Linear Minimization and Projection on Some Sets

DOI10.1016/J.ORL.2021.06.005arXiv2101.10040MaRDI QIDQ6358963FDOQ6358963

Authors: Cyrille W. Combettes, Sebastian Pokutta 

Publication date: 25 January 2021

Abstract: The Frank-Wolfe algorithm is a method for constrained optimization that relies on linear minimizations, as opposed to projections. Therefore, a motivation put forward in a large body of work on the Frank-Wolfe algorithm is the computational advantage of solving linear minimizations instead of projections. However, the discussions supporting this advantage are often too succinct or incomplete. In this paper, we review the complexity bounds for both tasks on several sets commonly used in optimization. Projection methods onto the $el{l}_p$-ball, $pinleft]1,2ight[cupleft]2,+inftyight[$, and the Birkhoff polytope are also proposed.

Mathematics Subject Classification ID

Convex programming (90C25) Nonlinear programming (90C30)

This page was built for publication: Complexity of Linear Minimization and Projection on Some Sets

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6358963)