pith. sign in

arxiv: 1307.0873 · v2 · pith:LIWGTJ2Ynew · submitted 2013-07-02 · 🧮 math.OC

New Analysis and Results for the Frank-Wolfe Method

classification 🧮 math.OC
keywords computationalguaranteesmethodresultsstep-sizefrank-wolfegapsrules
0
0 comments X
read the original abstract

We present new results for the Frank-Wolfe method (also known as the conditional gradient method). We derive computational guarantees for arbitrary step-size sequences, which are then applied to various step-size rules, including simple averaging and constant step-sizes. We also develop step-size rules and computational guarantees that depend naturally on the warm-start quality of the initial (and subsequent) iterates. Our results include computational guarantees for both duality/bound gaps and the so-called FW gaps. Lastly, we present complexity bounds in the presence of approximate computation of gradients and/or linear optimization subproblem solutions.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.