: 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...
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...
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...
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...
Efficient learning of DFA is a challenging research problem in grammatical inference. It is known that both exact and approximate (in the PAC sense) identifiability of DFA is har...
An index for an r.e. class of languages (by definition) generates a sequence of grammars defining the class. An index for an indexed family of languages (by definition) generat...
This paper is a comparative study of feature selection methods in statistical learning of text categorization. The focus is on aggressive dimensionality reduction. Five methods we...
Genetic programming evolves Lisp-like programs rather than fixed size linear strings. This representational power combined with generality makes genetic programming an interesting ...