# When majority rules, minority loses: bias amplification of gradient descent Source: [When majority rules, minority loses: bias amplification of gradient descent]() Collection index: [llms.txt]() Data updated: 2025-10-28T10:33:27.964Z Authors: Fran\\c{c}ois Bachoc, J\\'er\\^ome Bolte, Ryan Boustany, Jean-Michel Loubes Published: 2025-05-19T13:51:49.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()