Active Sampling for Min-Max Fairness
Abstract
We propose simple active sampling and reweighting strategies for optimizing min-max fairness that can be applied to any classification or regression model learned via loss minimization. The key intuition behind our approach is to use at each timestep a datapoint from the group that is worst off under the current model for updating the model. The ease of implementation and the generality of our robust formulation make it an attractive option for improving model performance on disadvantaged groups. For convex learning problems, such as linear or logistic regression, we provide a fine-grained analysis, proving the rate of convergence to a min-max fair solution.
Cite
Text
Abernethy et al. "Active Sampling for Min-Max Fairness." International Conference on Machine Learning, 2022.Markdown
[Abernethy et al. "Active Sampling for Min-Max Fairness." International Conference on Machine Learning, 2022.](https://mlanthology.org/icml/2022/abernethy2022icml-active/)BibTeX
@inproceedings{abernethy2022icml-active,
title = {{Active Sampling for Min-Max Fairness}},
author = {Abernethy, Jacob D and Awasthi, Pranjal and Kleindessner, Matthäus and Morgenstern, Jamie and Russell, Chris and Zhang, Jie},
booktitle = {International Conference on Machine Learning},
year = {2022},
pages = {53-65},
volume = {162},
url = {https://mlanthology.org/icml/2022/abernethy2022icml-active/}
}