— In this paper we develop a new dual decomposition method for optimizing a sum of convex objective functions corresponding to multiple agents but with coupled constraints. In ou...
A popular approach in combinatorial optimization is to model problems as integer linear programs. Ideally, the relaxed linear program would have only integer solutions, which happ...
We introduce an alternative to the smoothing technique approach for constrained optimization. As it turns out for any given smoothing function there exists a modification with part...
We present a novel boosting algorithm, called SoftBoost, designed for sets of binary labeled examples that are not necessarily separable by convex combinations of base hypotheses....
Manfred K. Warmuth, Karen A. Glocer, Gunnar Rä...
We show how (now familiar) hierarchical representations of (convex) polyhedra can be used to answer various separation queries efficiently (in a number of cases, optimally). Our e...