Adversarial Training Generalizes Data-dependent Spectral Norm Regularization

CoRR, 2019.

Cited by: 0|Views29
EI

Abstract:

We establish a theoretical link between adversarial training and operator norm regularization for deep neural networks. Specifically, we show that adversarial training is a data-dependent generalization of spectral norm regularization. This intriguing connection provides fundamental insights into the origin of adversarial vulnerability ...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments