How benign is benign overfitting?
We investigate two causes for adversarial vulnerability in deep neural networks: bad data and (poorly) trained models. When trained with SGD, deep neural networks essentially achieve zero training error, even in the presence of label noise, while also exhibiting good generalization on natural test d...
| Hlavní autoři: | , , , |
|---|---|
| Médium: | Conference item |
| Jazyk: | English |
| Vydáno: |
OpenReview
2021
|