BriefGPT.xyz
May, 2023
（正则化的）Wasserstein鲁棒分布模型精确泛化保证
Exact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Models
HTML
PDF
Waïss Azizian, Franck Iutzeler, Jérôme Malick
TL;DR
本研究表明，Wasserstein分布鲁棒估计器的推广保证其可适用于一般模型类，并且不会受到维度诅咒，甚至可以涵盖测试中的分布偏移，这些结果可以延伸到新引入的Wasserstein分布性机器学习问题的正则化版本。
Abstract
Wasserstein distributionally
robust estimators
have emerged as powerful models for prediction and decision-making under uncertainty. These estimators provide attractive
generalization guarantees
: the robust objec
→