On the Escaping Efficiency of Distributed Adversarial Training Algorithms

arXiv:2509.11337 · cs.LG · Submitted 2025-09-14 · Read on arXiv

cs.LG

Submitted: 2025-09-14

Updated: 2026-10-01

Terminology

• Adversarial Training — 5× in this paper · explained in 1 episode
• Robustness — 3× in this paper · explained in 5 episodes
• Adversarial Attacks — 1× in this paper · explained in 1 episode

Sources

• BlueFog: Make Decentralized Algorithms Practical for Optimization and Deep Learning
• Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples

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