Title
First-order Methods for the Impatient: Support Identification in Finite Time with Convergent Frank-Wolfe Variants.
Abstract
In this paper, we focus on the problem of minimizing a nonconvex function over the unit simplex. We analyze two well-known and widely used variants of the Frank-Wolfe algorithm and first prove global convergence of the iterates to stationary points, both when using exact and Armijo line search. Then we show that the algorithms identify the support in a finite number of iterations (the identification result does not hold for the classic Frank-Wolfe algorithm). This, to the best of our knowledge, is the first time a manifold identification property has been shown for such a class of methods.
Year
DOI
Venue
2019
10.1137/18M1206953
SIAM JOURNAL ON OPTIMIZATION
Keywords
Field
DocType
surface identification,manifold identification,active set,finite convergence
Applied mathematics,Mathematical optimization,First order,Finite convergence,Simplex,Mathematics,Finite time
Journal
Volume
Issue
ISSN
29
3
1052-6234
Citations 
PageRank 
References 
1
0.36
0
Authors
3
Name
Order
Citations
PageRank
Immanuel M. Bomze192287.13
Francesco Rinaldi210.70
Samuel Rota Bulò356433.69