Journal ArticleDOI
Some comments of Wolfe's `away step'
J Guélat,Patrice Marcotte +1 more
TLDR
It is given a detailed proof, under slightly weaker conditions on the objective function, that a modified Frank-Wolfe algorithm based on Wolfe's ‘away step’ strategy can achieve geometric convergence, provided a strict complementarity assumption holds.Abstract:
We give a detailed proof, under slightly weaker conditions on the objective function, that a modified Frank-Wolfe algorithm based on Wolfe's ‘away step’ strategy can achieve geometric convergence, provided a strict complementarity assumption holds.read more
Citations
More filters
The Iterates of the Frank-Wolfe Algorithm May Not Converge
TL;DR: The Frank-Wolfe algorithm is a popular method for minimizing a smooth convex function f over a compact convex set C as mentioned in this paper , and the convergence behavior of the sequence of iterates (xt)t∈N is known.
Journal ArticleDOI
The smoothed complexity of Frank–Wolfe methods via conditioning of random matrices and polytopes
TL;DR: The smoothed complexity of the condition number of small random perturbations of the input polytope was studied in this article , and it was shown that it is polynomial for any simplex and exponential for general polytopes.
Posted Content
Screening for a Reweighted Penalized Conditional Gradient Method.
Yifan Sun,Francis Bach +1 more
TL;DR: In this article, the authors explore the sparsity acquiring properties of a general penalized conditional gradient method for convex regularizers and a reweighted penalized CGM (RP-CGM) for nonconvex regularisers, replacing the usual convex constraints with gauge-inspired penalties.
Proceedings Article
Acceleration of Frank-Wolfe Algorithms with Open-Loop Step-Sizes
TL;DR: A general setting for which Frank-Wolfe algorithms with open loop step-size rules converges non-asymptotically faster than with line search or short-step is characterized, several accelerated convergence results for FW are derived, and potential gaps are highlighted in current understanding of the FW method in general.
Posted Content
First-order methods for the convex hull membership problem
TL;DR: Kalantari et al. as mentioned in this paper considered the convex hull membership problem (CHMP) as a quadratic programming problem, which could then be tackled with standard first-order methods.
References
More filters