New Analysis and Results for the Frank-Wolfe Method
Optimization and Control
2014-06-03 v2
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.
Cite
@article{arxiv.1307.0873,
title = {New Analysis and Results for the Frank-Wolfe Method},
author = {Robert M. Freund and Paul Grigas},
journal= {arXiv preprint arXiv:1307.0873},
year = {2014}
}
Comments
Changed the name of the method from "conditional gradient" to "Frank-Wolfe"