11
2

Robust learning and complexity dependent bounds for regularized problems

Abstract

We study Regularized Empirical Risk Minimizers (RERM) and minmax Median-Of-Means (MOM) estimators where the regularization function ϕ()\phi(\cdot) is an even convex function. We obtain bounds on the L2L_2-estimation error and the excess risk that depend on ϕ(f)\phi(f^*), where ff^* is the minimizer of the risk over a class FF. The estimators are based on loss functions that are both Lipschitz and convex. Results for the RERM are derived under weak assumptions on the outputs and a sub-Gaussian assumption on the class {(ff)(X),fF}\{ (f-f^*)(X), f \in F \}. Similar results are shown for minmax MOM estimators in a close setting where outliers may corrupt the dataset and where the class {(ff)(X),fF}\{ (f-f^*)(X), f \in F \} is only supposed to satisfy weak moment assumptions, relaxing the sub-Gaussian and the i.i.d hypothesis necessary for RERM. The analysis of RERM and minmax MOM estimators with Lipschitz and convex loss funtions is based on a weak local Bernstein Assumption. We obtain two "meta theorems" that we use to study linear estimators regularized by the Elastic Net. We also examine Support Vector Machines (SVM), where no sub-Gaussian assumption is required and when the target YY can be heavy-tailed, improving the existing literature.

View on arXiv
Comments on this paper