Frank–Wolfe algorithm: Difference between revisions

Revision as of 18:19, 16 December 2014

Revision as of 20:24, 3 February 2015

Line 3:

==Problem statement==

Suppose <math>\mathcal{D}</math> is a [[compact space|compact]] [[convex set]] in a [[vector space]] and <math>f \colon \mathcal{D} \to \mathbb{R}</math> is a [[convex function|convex]] [[differentiable function|differentiable]] [[real-valued function]]. The Frank–Wolfe algorithm solves the [[optimization problem]]

:Minimize <math> f(\mathbf{x})</math>

:subject to <math> \mathbf{x} \in \mathcal{D}</math>.

Where the function <math> f</math> is [[Convex function|convex]] and [[differentiable function|differentiable]], and the ___domain / feasible set <math>\mathcal{D}</math> is a [[Convex set|convex]] and bounded set in some [[vector space]].

==Algorithm==