Active set complexity of the Away-step Frank-Wolfe Algorithm
Optimization and Control
2019-12-30 v1
Abstract
In this paper, we study active set identification results for the away-step Frank-Wolfe algorithm in different settings. We first prove a local identification property that we apply, in combination with a convergence hypothesis, to get an active set identification result. We then prove, in the nonconvex case, a novel convergence rate result and active set identification for different stepsizes (under suitable assumptions on the set of stationary points). By exploiting those results, we also give explicit active set complexity bounds for both strongly convex and nonconvex objectives. While we initially consider the probability simplex as feasible set, in the appendix we show how to adapt some of our results to generic polytopes.
Keywords
Cite
@article{arxiv.1912.11492,
title = {Active set complexity of the Away-step Frank-Wolfe Algorithm},
author = {Immanuel M. Bomze and Francesco Rinaldi and Damiano Zeffiro},
journal= {arXiv preprint arXiv:1912.11492},
year = {2019}
}
Comments
23 pages