We suggest a new approach to optimize the learning of sparse features under the constraints of explicit transformation symmetries imposed on the set of feature vectors. Given a set...
Bandit convex optimization is a special case of online convex optimization with partial information. In this setting, a player attempts to minimize a sequence of adversarially gen...
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...
Geometric methods are very intuitive and provide a theoretically solid viewpoint to many optimization problems. SVM is a typical optimization task that has attracted a lot of atte...
Michael E. Mavroforakis, Margaritis Sdralis, Sergi...
We consider parameterized convex optimization problems over the unit simplex, that depend on one parameter. We provide a simple and efficient scheme for maintaining an -approximat...