Följ
Michael Aerni
Michael Aerni
Doctoral student at Secure and Private AI (SPY) Lab, ETH Zurich
Verifierad e-postadress på inf.ethz.ch - Startsida
Titel
Citeras av
Citeras av
År
Interpolation can hurt robust generalization even when there is no noise
K Donhauser, A Tifrea, M Aerni, R Heckel, F Yang
Advances in Neural Information Processing Systems 34, 23465-23477, 2021
112021
Strong inductive biases provably prevent harmless interpolation
M Aerni, M Milanta, K Donhauser, F Yang
International Conference on Learning Representations (ICLR), 2023
42023
Maximizing the robust margin provably overfits on noiseless data
K Donhauser, A Tifrea, M Aerni, R Heckel, F Yang
ICML 2021 Workshop on Adversarial Machine Learning, 2021
2021
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–3