How Does Promoting the Minority Fraction Affect Generalization? A Theoretical Study of One-Hidden-Layer Neural Network on Group Imbalance
Document Type
Article
Publication Date
1-1-2024
Abstract
Group imbalance has been a known problem in empirical risk minimization (ERM), where the achieved high average accuracy is accompanied by low accuracy in a minority group. Despite algorithmic efforts to improve the minority group accuracy, a theoretical generalization analysis of ERM on individual groups remains elusive. By formulating the group imbalance problem with the Gaussian Mixture Model, this paper quantifies the impact of individual groups on the sample complexity, the convergence rate, and the average and group-level testing performance. Although our theoretical framework is centered on binary classification using a one-hidden-layer neural network, to the best of our knowledge, we provide the first theoretical analysis of the group-level generalization of ERM in addition to the commonly studied average generalization performance. Sample insights of our theoretical results include that when all group-level co-variance is in the medium regime and all mean are close to zero, the learning performance is most desirable in the sense of a small sample complexity, a fast training rate, and a high average and group-level testing accuracy. Moreover, we show that increasing the fraction of the minority group in the training data does not necessarily improve the generalization performance of the minority group. Our theoretical results are validated on both synthetic and empirical datasets, such as CelebA and CIFAR-10 in image classification.
Identifier
85187379452 (Scopus)
Publication Title
IEEE Journal on Selected Topics in Signal Processing
External Full Text Location
https://doi.org/10.1109/JSTSP.2024.3374593
e-ISSN
19410484
ISSN
19324553
First Page
216
Last Page
231
Issue
2
Volume
18
Recommended Citation
Li, Hongkang; Zhang, Shuai; Zhang, Yihua; Wang, Meng; Liu, Sijia; and Chen, Pin Yu, "How Does Promoting the Minority Fraction Affect Generalization? A Theoretical Study of One-Hidden-Layer Neural Network on Group Imbalance" (2024). Faculty Publications. 1073.
https://digitalcommons.njit.edu/fac_pubs/1073
