Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation

ArXi:2605.10290v1 Announce Type: cross This paper aims at analyzing the regularization effect that data augmentation induces on supervised regression methods in the proportional regime, where the number of covariates grows proportionally to the number of samples. We provide a tight characterization of the test error, measured in mean squared error, in terms only of the population quantities of the true data, as well as first and second order statistics of the augmentation scheme.