When Covariate-shifted Data Augmentation Increases Test Error And How to Fix It

no code implementations • 25 Sep 2019 • Sang Michael Xie*, Aditi Raghunathan*, Fanny Yang, John C. Duchi, Percy Liang

Empirically, data augmentation sometimes improves and sometimes hurts test error, even when only adding points with labels from the true conditional distribution that the hypothesis class is expressive enough to fit.

Data Augmentation regression