论文标题
过度参数化如何影响少数群体的绩效？
How does overparametrization affect performance on minority groups?
论文作者
论文摘要
过度参数化对现代机器学习（ML）模型的整体性能的好处是众所周知的。但是，在更颗粒状的数据亚组水平上过度参数化的影响知之甚少。最近的经验研究表明了令人鼓舞的结果：（i）当群体未知时，对经验风险最小化训练的过度参数化模型（ERM）对少数群体的表现更好； （ii）当已知组时，对均衡组大小的数据进行的ERM产生了过度参数化的制度中最新的最差群体精确度。在本文中，我们通过对少数群体过度参数化特征模型的风险进行理论研究来补充这些经验研究。在大多数和少数群体的回归功能不同的环境中，我们表明过度参数始终可以改善少数群体的绩效。
The benefits of overparameterization for the overall performance of modern machine learning (ML) models are well known. However, the effect of overparameterization at a more granular level of data subgroups is less understood. Recent empirical studies demonstrate encouraging results: (i) when groups are not known, overparameterized models trained with empirical risk minimization (ERM) perform better on minority groups; (ii) when groups are known, ERM on data subsampled to equalize group sizes yields state-of-the-art worst-group-accuracy in the overparameterized regime. In this paper, we complement these empirical studies with a theoretical investigation of the risk of overparameterized random feature models on minority groups. In a setting in which the regression functions for the majority and minority groups are different, we show that overparameterization always improves minority group performance.
