2 papers
cs.LG2026
Factorized AdaBoost.MH Achieves the Same Convergence Rate as AdaBoost.MH
Xin Zou, Jingyuan Xu
{AdaBoost.MH} reduces multi-class classification to a collection of binary subproblems and enjoys the classical boosting-type convergence guarantee under a weak learning condition.…
cs.LG2026
Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization
Xinhai Zou, Chang Zhao, Alireza Aghabagherloo +3
Gradient-based adversarial attacks remain a dominant threat to deep neural networks (DNNs), as they exploit gradient information to efficiently optimize adversarial perturbations.…