When majority rules, minority loses: bias amplification of gradient descent
François Bachoc, Jerome Bolte, Ryan Boustany, Jean-Michel Loubes
Abstract
Despite growing empirical evidence of bias amplification in machine learning, its theoretical foundations remain poorly understood. We develop a formal framework for majority-minority learning tasks, showing how standard training can favor majority groups and produce stereotypical predictors that neglect minority-specific features. Assuming population and variance imbalance, our analysis reveals three key findings: (i) the close proximity between "full-data" and stereotypical predictors, (ii) the dominance of a region where training the entire model tends to merely learn the majority traits, and (iii) a lower bound on the additional training required. Our results are illustrated through experiments in deep learning for tabular and image classification tasks.
BibTeX
@inproceedings{
bachoc2025when,
title={When majority rules, minority loses: bias amplification of gradient descent},
author={Fran{\c{c}}ois Bachoc and Jerome Bolte and Ryan Boustany and Jean-Michel Loubes},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=RDe4Ntw2oy}
}