Calibrated Data-Dependent Constraints with Exact Satisfaction Guarantees
Authors
Authors
- Mikhail Yurochkin
- Songkai Xue
- Yuekai Sun
Authors
- Mikhail Yurochkin
- Songkai Xue
- Yuekai Sun
Categories
We consider the task of training machine learning models with data-dependent constraints. Such constraints often arise as empirical versions of expected value constraints that enforce fairness or stability goals. We reformulate data-dependent constraints so that they are calibrated: enforcing the reformulated constraints guarantees that their expected value counterparts are satisfied with a user-prescribed probability. The resulting optimization problem is amendable to standard stochastic optimization algorithms, and we demonstrate the efficacy of our method on a fairness-sensitive classification task where we wish to guarantee the classifier’s fairness (at test time).
Please cite our work using the BibTeX below.
@inproceedings{
xue2022calibrated,
title={Calibrated Data-Dependent Constraints with Exact Satisfaction Guarantees},
author={Songkai Xue and Yuekai Sun and Mikhail Yurochkin},
booktitle={Advances in Neural Information Processing Systems},
editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
year={2022},
url={https://openreview.net/forum?id=oWqWiazEb62}
}