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

Documenti analoghi

• Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data
  di: Li, Binghui, et al.
  Pubblicazione: (2024)
• On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training
  di: Liu, Chen, et al.
  Pubblicazione: (2021)
• Benign Overfitting in Adversarial Training for Vision Transformers
  di: Zhang, Jiaming, et al.
  Pubblicazione: (2026)
• Revisiting the Relationship between Adversarial and Clean Training: Why Clean Training Can Make Adversarial Training Better
  di: Zhou, MingWei, et al.
  Pubblicazione: (2025)
• Understanding Generalization in Transformers: Error Bounds and Training Dynamics Under Benign and Harmful Overfitting
  di: Zhang, Yingying, et al.
  Pubblicazione: (2025)