When majority rules, minority loses: bias amplification of gradient descent
François Bachoc,
Jérôme Bolte,
Ryan Boustany and
Jean-Michel Loubes
No 25-1641, TSE Working Papers from Toulouse School of Economics (TSE)
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.
Date: 2025-05-21
New Economics Papers: this item is included in nep-big and nep-cmp
References: View complete reference list from CitEc
Citations:
Downloads: (external link)
https://www.tse-fr.eu/sites/default/files/TSE/docu ... 2025/wp_tse_1641.pdf Working paper (application/pdf)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:tse:wpaper:130552
Access Statistics for this paper
More papers in TSE Working Papers from Toulouse School of Economics (TSE) Contact information at EDIRC.
Bibliographic data for series maintained by ().