This website uses cookies to ensure you get the best experience on our website.
Learn more
Got it!
Home
Publications
Contact
deep learning theory
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
Cite
×