Revision as of 01:21, 8 March 2014 edit Saung Tadashi (talk \| contribs) Extended confirmed users 2,083 edits m added a external link ← Previous edit		Revision as of 10:34, 24 March 2014 edit undo Mathmon (talk \| contribs) 21 edits m →Lower bounds on the solution value, and primal-dual analysis Next edit →
Line 49: :<math> l_k := \max (l_{k - 1}, f(\mathbf{x}_k) + (\mathbf{s}_k - \mathbf{x}_k)^T \nabla f(\mathbf{x}_k)) </math> Such lower bounds on the unknown optimal value are important in practice because they can be used as a stopping criterion, and give an efficient certificate of the approximation quality in every iteration, since always <math>l_k \leq f(\mathbf{x}^*) \leq f(\mathbf{x}_k)</math>.

Frank–Wolfe algorithm: Difference between revisions