arXiv · Machine Learning Theory· Philipp J. Schneider, Lukas Looser, Antoine Garin, Shuhan Liu, Daniel Kuhn·· 4 hr agoAI score25
WRAP：非平稳市场下深度对冲的对抗训练
Adversarial Training for Deep Hedging in Nonstationary Markets
AI brief
论文提出 WRAP（Wasserstein-Reweighting Adversarial Perturbation），一种源自双预算分布鲁棒优化（DRO）的漂移感知对抗训练框架，用于改进深度对冲策略。
Source: arXiv · Machine Learning Theory · arxiv.org