Private Query Release Assisted by Public Data
Abstract
We study the problem of differentially private query release assisted by access to public data. In this problem, the goal is to answer a large class $\mathcal{H}$ of statistical queries with error no more than $\alpha$ using a combination of public and private samples. The algorithm is required to satisfy differential privacy only with respect to the private samples. We study the limits of this task in terms of the private and public sample complexities. Our upper and lower bounds on the private sample complexity have matching dependence on the dual VC-dimension of $\mathcal{H}$. For a large category of query classes, our bounds on the public sample complexity have matching dependence on $\alpha$.
Cite
Text
Bassily et al. "Private Query Release Assisted by Public Data." International Conference on Machine Learning, 2020.Markdown
[Bassily et al. "Private Query Release Assisted by Public Data." International Conference on Machine Learning, 2020.](https://mlanthology.org/icml/2020/bassily2020icml-private/)BibTeX
@inproceedings{bassily2020icml-private,
title = {{Private Query Release Assisted by Public Data}},
author = {Bassily, Raef and Cheu, Albert and Moran, Shay and Nikolov, Aleksandar and Ullman, Jonathan and Wu, Steven},
booktitle = {International Conference on Machine Learning},
year = {2020},
pages = {695-703},
volume = {119},
url = {https://mlanthology.org/icml/2020/bassily2020icml-private/}
}