We propose a novel algorithm for extracting the structure of a Bayesian network from a dataset. Our approach is based on generalized conditional entropies, a parametric family of e...
We propose a generalization of expected utility that we call generalized EU (GEU), where a deci sion maker's beliefs are represented by plausibil ity measures and the dec...
We provide a description of generalized default logic as a unified formalism for nonmonotonic reasoning. Special attention will be paid to the role of the monotonic logic underlyi...
We derive generalization bounds for learning algorithms based on their robustness: the property that if a testing sample is "similar" to a training sample, then the test...
Let S be a set of r red points and b = r +2 blue points in general position in the plane. A line determined by them is said to be balanced if in each open half-plane bounded by th...