When majority rules, minority loses: bias amplification of gradient descent
Quick summary
arXiv:2505.13122v3 Announce Type: replace-cross 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 t
Key takeaways
- arXiv:2505.13122v3 Announce Type: replace-cross 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 t
Why it matters
The importance of “When majority rules, minority loses: bias amplification of gradient descent” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments