A new analytical approach to consistency and overfitting in regularized empirical risk minimization

Abstract

This work considers the problem of binary classification: given training datax1, . . .,xnfrom a certain population, together with associated labelsy1,. . .,yn∈ {0,1}, determine the best label for an elementxnot among the training data. More specifically, this work considers a variant of the regularized empirical risk functional which is defined intrinsically to the observed data and does not depend on the underlying population. Tools from modern analysis are used to obtain a concise proof of asymptotic consistency as regularization parameters are taken to zero at rates related to the size of the sample. These analytical tools give a new framework for understanding overfitting and underfitting, and rigorously connect the notion of overfitting with a loss of compactness.