NTK neural networks achieve minimax optimal adversarial regression rates in Sobolev spaces using gradient flow with early stopping, but minimum norm interpolants are vulnerable in the overfitting regime.
Yifan Hao and Tong Zhang
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adversarial Robustness of NTK Neural Networks
NTK neural networks achieve minimax optimal adversarial regression rates in Sobolev spaces using gradient flow with early stopping, but minimum norm interpolants are vulnerable in the overfitting regime.