EconPapers    
Economics at your fingertips  
 

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 ().

 
Page updated 2025-07-19
Handle: RePEc:tse:wpaper:130552