CoinPress: Practical Private Mean and Covariance Estimation
Abstract
We present simple differentially private estimators for the parameters of multivariate sub-Gaussian data that are accurate at small sample sizes. We demonstrate the effectiveness of our algorithms both theoretically and empirically using synthetic and real-world datasets---showing that their asymptotic error rates match the state-of-the-art theoretical bounds, and that they concretely outperform all previous methods. Specifically, previous estimators either have weak empirical accuracy at small sample sizes, perform poorly for multivariate data, or require the user to provide strong a priori estimates for the parameters.
Cite
Text
Biswas et al. "CoinPress: Practical Private Mean and Covariance Estimation." Neural Information Processing Systems, 2020.Markdown
[Biswas et al. "CoinPress: Practical Private Mean and Covariance Estimation." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/biswas2020neurips-coinpress/)BibTeX
@inproceedings{biswas2020neurips-coinpress,
title = {{CoinPress: Practical Private Mean and Covariance Estimation}},
author = {Biswas, Sourav and Dong, Yihe and Kamath, Gautam and Ullman, Jonathan},
booktitle = {Neural Information Processing Systems},
year = {2020},
url = {https://mlanthology.org/neurips/2020/biswas2020neurips-coinpress/}
}