Stochastic Constrained DRO with a Complexity Independent of Sample Size

Transactions on Machine Learning Research, 2023 Distributionally Robust Optimization (DRO), as a popular method to train robust models against distribution shift between training and test sets, has received tremendous attention in recent years. In this paper, we propose and analyze stochastic algori...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Qi, Qi, Lyu, Jiameng, Chan, Kung sik, Bai, Er Wei, Yang, Tianbao
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Learning Mathematics - Optimization and Control
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!