ZeroGrad : Mitigating and Explaining Catastrophic Overfitting in FGSM Adversarial Training

1 code implementation • 29 Mar 2021 • Zeinab Golgooni, Mehrdad Saberi, Masih Eskandar, Mohammad Hossein Rohban

Making deep neural networks robust to small adversarial noises has recently been sought in many applications.

Conditioning and Processing: Techniques to Improve Information-Theoretic Generalization Bounds

no code implementations • NeurIPS 2020 • Hassan Hafez-Kolahi, Zeinab Golgooni, Shohreh Kasaei, Mahdieh Soleymani

This approach provides an insight into learning algorithms by considering the mutual information between the model and the training set.

Generalization Bounds