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
Proceedings Article
Linearly Convergent Frank-Wolfe with Backtracking Line-Search
TL;DR: In this paper, the authors proposed variants of Away-steps and Pairwise Frank-Wolfe (FW) algorithms that do not require prior knowledge of the objective and inherit all the favorable convergence properties of the exact line-search version, including linear convergence for strongly convex functions over polytopes.
Posted Content
A Novel Frank-Wolfe Algorithm. Analysis and Applications to Large-Scale SVM Training
TL;DR: In this paper, a variant of the Frank-Wolfe (FW) method was proposed to accelerate the convergence of the basic FW procedure on quadratic forms, where the convergence rate was shown to be linear with the number of iterations.
Journal ArticleDOI
An efficient multi-label support vector machine with a zero label
TL;DR: This paper proposes a novel support vector machine for multi-label classification through both simplifying Rank-SVM and adding a zero label, resulting into a quadratic programming problem in which each class has an independent equality constraint.
Journal ArticleDOI
Conditional gradient type methods for composite nonlinear and stochastic optimization
TL;DR: In this article, a conditional gradient type (CGT) method for composite optimization problems is presented, where the objective function consists of a (weakly) smooth term and a (strongly) convex regularization term.
Journal ArticleDOI
Determining origin-destination matrices and optimal multiproduct flows for freight transportation over multimodal networks
TL;DR: A normative transshipment problem for freight flows over a multimodal network, in which an origin/destination matrix which corresponds to the minimal cost flows must be computed as well is considered.
References
More filters