Area-convexity, l ∞ regularization, and undirected multicommodity flow
Jonah Sherman · 2017
We show the strong-convexity assumption of regularization-based methods for solving bilinear saddle point problems may be relaxed to a weaker notion of area-convexity with respect to an alternating bilinear form. This allows bypassing the infamous '' barrier for strongly convex regularizers that has stalled progress on a number of algorithmic problems.