Optimal Unbiased Randomizers for Regression with Label Differential Privacy
Ashwinkumar Badanidiyuru, Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Jacob Leeman, Pasin Manurangsi, Avinash V Varadarajan, Chiyuan Zhang
Abstract
We propose a new family of label randomizers for training _regression_ models under the constraint of label differential privacy (DP). In particular, we leverage the trade-offs between bias and variance to construct better label randomizers depending on a privately estimated prior distribution over the labels. We demonstrate that these randomizers achieve state-of-the-art privacy-utility trade-offs on several datasets, highlighting the importance of reducing bias when training neural networks with label DP. We also provide theoretical results shedding light on the structural properties of the optimal unbiased randomizers.
BibTeX
@inproceedings{
badanidiyuru2023optimal,
title={Optimal Unbiased Randomizers for Regression with Label Differential Privacy},
author={Ashwinkumar Badanidiyuru and Badih Ghazi and Pritish Kamath and Ravi Kumar and Ethan Jacob Leeman and Pasin Manurangsi and Avinash V Varadarajan and Chiyuan Zhang},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=aG6xOP9QY7}
}