We present a polynomial update time algorithm for the inductive inference of a large class of context-free languages using the paradigm of positive data and a membership oracle. W...
We describe a new approach for understanding the difficulty of designing efficient learning algorithms. We prove that the existence of an efficient learning algorithm for a circui...
: We study the weight distribution and list-decoding size of Reed-Muller codes. Given a weight parameter, we are interested in bounding the number of Reed-Muller codewords with a w...
Abstract. Recent works have shown the advantage of using Active Learning methods, such as the Query by Committee (QBC) algorithm, to various learning problems. This class of Algori...
We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised...