Many structured prediction tasks involve complex models where inference is computationally intractable, but where it can be well approximated using a linear programming relaxation...
Ofer Meshi, David Sontag, Tommi Jaakkola, Amir Glo...
We consider the question: What is the maximum flow achievable in a network if the flow must be decomposable into a collection of edgedisjoint paths? Equivalently, we wish to find a...
Abstract. We give a (ln n + 1)-approximation for the decision tree (DT) problem. An instance of DT is a set of m binary tests T = (T1, . . . , Tm) and a set of n items X = (X1, . ....
The paper focuses on developing effective importance sampling algorithms for mixed probabilistic and deterministic graphical models. The use of importance sampling in such graphi...
Achieving weighted throughput maximization (WTM) through power control has been a long standing open problem in interference-limited wireless networks. The complicated coupling bet...