Catastrophic Overfitting, Entropy Gap and Participation Ratio: A Noiseless l p Norm Solution for Fast Adversarial Training

arXiv:2505.02360 · cs.LG, cs.AI · Submitted 2025-05-05 · Read on arXiv

cs.LG, cs.AI

Submitted: 2025-05-05

Updated: 2026-10-23

Terminology

• Catastrophic Overfitting — 2× in this paper
• Overfitting — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Fast Gradient Sign Method — 1× in this paper
• Fixed Point — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 6 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks