CoinPress: Practical Private Mean and Covariance Estimation
By Sourav Biswas, Yihe Dong, Gautam Kamath, Jonathan Ullman. 2020
131 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Statistics and Probability
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Pasin Manurangsi
- Badih Ghazi
- Ravi Kumar
- Rasmus Pagh
- Jonathan Ullman
- Gautam Kamath
- Vikrant Singhal
- Amer Sinha
In Statistics and Probability
- Jonathan Ullman
- Vikrant Singhal
- Gautam Kamath
- Ravi Kumar
- Rasmus Pagh
- Amer Sinha
- Badih Ghazi
- Pasin Manurangsi
Citations in the corpus
- Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message (2021, background): “This constitutes a basic building block within machine learning,”
- Private Mean Estimation of Heavy-Tailed Distributions (2020, background): “Bun, Kamath, Steinke, and Wu Bun et al. (2019) give general tools for private hypothesis selection and apply this to learning many distribution classes of interest. For further coverage of differentially private statistics, see Kamath and Ullman (2020). In the non-private setting, there has recently”