The problem of learning linear discriminant concepts can be solved by various mistake-driven update procedures, including the Winnow family of algorithms and the well-known Percep...
Abstract. We propose a convex optimization approach to solving the nonparametric regression estimation problem when the underlying regression function is Lipschitz continuous. This...
Dimitris Bertsimas, David Gamarnik, John N. Tsitsi...
We describe a new boosting algorithm which generates only smooth distributions which do not assign too much weight to any single example. We show that this new boosting algorithm ...
We relate two problems that have been explored in two distinct communities. The first is the problem of combining expert advice, studied extensively in the computational learning...
: In this paper we prove sanity-check bounds for the error of the leave-one-out cross-validation estimate of the generalization error: that is, bounds showing that the worst-case e...