BriefGPT.xyz
Mar, 2022
基于组合优化的大规模分布式鲁棒模型学习
Learning Distributionally Robust Models at Scale via Composite Optimization
HTML
PDF
Farzin Haddadpour, Mohammad Mahdi Kamani, Mehrdad Mahdavi, Amin Karbasi
TL;DR
本文提出通过有限和复合优化来提供可扩展的机器学习算法，用于训练鲁棒性强的模型，并展示本算法在超大数据集上学习鲁棒模型的有效性。
Abstract
To train
machine learning
models that are robust to
distribution shifts
in the data, distributionally
robust optimization
(DRO) has been p
→