CoinPress: Practical Private Mean and Covariance Estimation

June 11, 2020 · Entered Twilight · 🏛 Neural Information Processing Systems

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: README.md, algos.py, cov_estimation.py, data, demo.py, mean_estimation.py, multivariate_covariance_experiments.ipynb, multivariate_mean_experiments.ipynb, plot_cov.py, plot_mean.py, plots, results, utils.py

Authors Sourav Biswas, Yihe Dong, Gautam Kamath, Jonathan Ullman arXiv ID 2006.06618 Category stat.ML: Machine Learning (Stat) Cross-listed cs.CR, cs.DS, cs.IT, cs.LG, math.ST Citations 126 Venue Neural Information Processing Systems Repository https://github.com/twistedcubic/coin-press ⭐ 35 Last Checked 1 month ago

Abstract

We present simple differentially private estimators for the mean and covariance 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.