research
∙
06/02/2023
Why Clean Generalization and Robust Overfitting Both Happen in Adversarial Training
Adversarial training is a standard method to train deep neural networks ...
share
research
∙
05/27/2022
Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power
It is well-known that modern neural networks are vulnerable to adversari...
research
∙
02/23/2022
Reconstruction Task Finds Universal Winning Tickets
Pruning well-trained neural networks is effective to achieve a promising...
research
∙
07/01/2021