Some theoretical results concerning the convergence of compositions of regularized linear functions

Abstract

Recently, sample complexity bounds have been derived for problems involving linear functions such as neural networks and support vector machines. Ini this paper, we extend some theoretical results in this area by deriving dimensional independent covering number bounds for regularized linear functions under certain regularization conditions. We show that such bounds lead to a class of new methods for training linear classifiers with similar theoretical advantages of the support vector machine. Furthermore, we also present a theoretical analysis for these new methods from the asymptotic statistical point of view. This technique provides better description for large sample behaviors of these algorithms.