arXiv:2410. 07719v4 Announce Type: replace Abstract: Despite being widely adopted as a canonical framework for learning robust models, adversarial training suffers from robust overfitting.
By Yuelin Xu, Xiao Zhang
arXiv:2301. 06308v2 Announce Type: replace-cross Abstract: Sharpness-aware minimization (SAM) is a training method that seeks to find flat minima in deep learning, resulting in state-of-the-art performance across various domains.
By Hoki Kim, Jinseong Park, Yujin Choi, Jaewook Lee
The paper introduces CoDRA, a cost-to-disturbance ratio approach for adversarial reinforcement learning that balances controller performance and disturbance exposure without extra penalty terms. CoDRA uses a self‑normalized actor–critic update, scaling value terms by a stop‑gradient normalization constant derived from the current batch. Experiments on MuJoCo pendulum tasks show that CoDRA achieves the lowest cost across a range of forces and masses, outperforming other methods especially on the more challenging InvertedDoublePendulum environment.
By Taeho Lee, Donghwan Lee
The paper investigates how deterministic Gradient Descent behaves when applied to Adversarial Training with large, constant step sizes. It analyzes both a linear logistic regression setting—examining where parameters converge (implicit bias) and how fast losses decrease (optimization)—and neural network training, focusing on the evolution of loss sharpness. The study reveals three key distinctions from Standard Training: the implicit bias gap persists even with large steps, there is no uniform convergence rate for optimization error, and sharpness follows a two‑stage dynamic unlike the Edge‑of‑Stability pattern seen in Standard Training.
By Yi Feng, Andrea Paudice
The paper presents a unified framework for regularization-based robust reinforcement learning by deriving upper bounds on the performance gap between nominal and worst-case policies. These bounds are expressed as a regularization objective plus a KL-divergence penalty, explaining why KL penalties enhance robustness. The authors reformulate robust training as a constrained optimization problem, updating the Lagrange multiplier jointly with the policy to automatically tune regularization, and validate the approach with extensive adversarial evaluations on continuous control tasks.
By Amine Andam, Jamal Bentahar, Mustapha Hedabou
arXiv:2606. 04476v1 Announce Type: new Abstract: In this paper, we study the gradient descent dynamics for jointly training both layers of a one-hidden-layer ReLU network to fit a linear target function.
By Berk Tinaz, Changzhi Xie, Mahdi Soltanolkotabi