On Concentration for (Regularized) Empirical Risk Minimization

Abstract

Rates of convergence for empirical risk minimizers have been well studied in the literature. In this paper, we aim to provide a complementary set of results, in particular by showing that after normalization, the risk of the empirical minimizer concentrates on a single point. Such results have been established by Chatterjee (The Annals of Statistics, 42(6):2340–2381 2014) for constrained estimators in the normal sequence model. We first generalize and sharpen this result to regularized least squares with convex penalties, making use of a “direct” argument based on Borell’s theorem. We then study generalizations to other loss functions, including the negative log-likelihood for exponential families combined with a strictly convex regularization penalty. The results in this general setting are based on more “indirect” arguments as well as on concentration inequalities for maxima of empirical processes.