high dimensional statistics

Strong inductive biases provably prevent harmless interpolation
We show that the strength of a model’s inductive bias determines whether interpolation of noisy data is harmless or harmful.
Michael Aerni, Marco Milanta, Konstantin Donhauser, Fanny Yang
PDF Cite Code
Interpolation can hurt robust generalization even when there is no noise
We reveal unexpected benefits of regularization even in the overparameterized regime by proving that for both linear regression and classification, avoiding interpolation significantly improves generalization.
Konstantin Donhauser, Alexandru Țifrea, Michael Aerni, Reinhard Heckel, Fanny Yang
PDF Cite Code Poster