We introduce a combinatorial dimension that characterizes the number of queries needed to exactly (or approximately) learn concept classes in various models. Our general dimension...
For two-class datasets, we provide a method for estimating the generalization error of a bag using out-of-bag estimates. In bagging, each predictor (single hypothesis) is learned ...
The goal of a threshold query is to detect all objects whose score exceeds a given threshold. This type of query is used in many settings, such as data mining, event triggering, a...
Guy Sagy, Daniel Keren, Izchak Sharfman, Assaf Sch...
A D-polyhedron is a polyhedron P such that if x, y are in P then so are their componentwise max and min. In other words, the point set of a D-polyhedron forms a distributive latti...
Loopy belief propagation has been employed in a wide variety of applications with great empirical success, but it comes with few theoretical guarantees. In this paper we analyze t...
Sujay Sanghavi, Dmitry M. Malioutov, Alan S. Wills...