Regression with Label Differential Privacy
Abstract
We study the task of training regression models with the guarantee of _label_ differential privacy (DP). Based on a global prior distribution of label values, which could be obtained privately, we derive a label DP randomization mechanism that is optimal under a given regression loss function. We prove that the optimal mechanism takes the form of a "randomized response on bins", and propose an efficient algorithm for finding the optimal bin values. We carry out a thorough experimental evaluation on several datasets demonstrating the efficacy of our algorithm.
Cite
Text
Ghazi et al. "Regression with Label Differential Privacy." International Conference on Learning Representations, 2023.Markdown
[Ghazi et al. "Regression with Label Differential Privacy." International Conference on Learning Representations, 2023.](https://mlanthology.org/iclr/2023/ghazi2023iclr-regression/)BibTeX
@inproceedings{ghazi2023iclr-regression,
title = {{Regression with Label Differential Privacy}},
author = {Ghazi, Badih and Kamath, Pritish and Kumar, Ravi and Leeman, Ethan and Manurangsi, Pasin and Varadarajan, Avinash and Zhang, Chiyuan},
booktitle = {International Conference on Learning Representations},
year = {2023},
url = {https://mlanthology.org/iclr/2023/ghazi2023iclr-regression/}
}