Optimization Online


Active Set Complexity of the Away-step Frank-Wolfe Algorithm

I. M. Bomze (immanuel.bomze***at***univie.ac.at)
F. Rinaldi (rinaldi***at***math.unipd.it)
D. Zeffiro (damiano.zeffiro***at***math.unipd.it)

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 O(1/ √k) 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: Surface Identification, Manifold Identification, Active Set Complexity

Category 1: Nonlinear Optimization

Category 2: Nonlinear Optimization (Constrained Nonlinear Optimization )


Download: [PDF]

Entry Submitted: 12/24/2019
Entry Accepted: 12/24/2019
Entry Last Modified: 05/06/2020

Modify/Update this entry

  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository


Coordinator's Board
Classification Scheme
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society