Benutzer: Gast  Login
Titel:

Interpolation can hurt robust generalization even when there is no noise

Dokumenttyp:
Konferenzbeitrag
Autor(en):
Donhauser, Konstantin; Tifrea, Alexandru; Aerni, Michael; Heckel, Reinhard; Yang, Fanny
Abstract:
Numerous recent works show that overparameterization implicitly reduces variance for min-norm interpolators and max-margin classifiers. These findings suggest that ridge regularization has vanishing benefits in high dimensions. We challenge this narrative by showing that, even in the absence of noise, avoiding interpolation through ridge regularization can significantly improve generalization. We prove this phenomenon for the robust risk of both linear regression and classification, and hence pr...     »
Kongress- / Buchtitel:
Conference on Neural Information Processing Systems (NeurIPS)
Jahr:
2021
 BibTeX