On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Binghui, Li, Yuanzhi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!