A Primer on Private Statistics
arXiv:2005.00010
Abstract
Differentially private statistical estimation has seen a flurry of developments over the last several years. Study has been divided into two schools of thought, focusing on empirical statistics versus population statistics. We suggest that these two lines of work are more similar than different by giving examples of methods that were initially framed for empirical statistics, but can be applied just as well to population statistics. We also provide a thorough coverage of recent work in this area.
20 pages. Comments welcome
References in corpus (10)
- Renyi Differential Privacy
- Scalable Privacy-Preserving Data Sharing Methodology for Genome-Wide Association Studies
- Gaussian Differential Privacy
- The Cost of Privacy: Rates of Convergence for Parameter Estimation with Differential Privacy
- Revisiting Differentially Private Hypothesis Tests for Categorical Data
- Differentially Private Change-Point Detection
- Differentially Private Identity and Closeness Testing of Discrete Distributions
- Differentially Private Assouad, Fano, and Le Cam
- Privately detecting changes in unknown distributions
- Privately Learning Markov Random Fields
Cited by in corpus (11)
- Private Mean Estimation of Heavy-Tailed Distributions
- CoinPress: Practical Private Mean and Covariance Estimation
- Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanism
- Locally Private Hypothesis Selection
- On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians
- Instance-optimal Mean Estimation Under Differential Privacy
- Private and polynomial time algorithms for learning Gaussians and beyond
- Privately Learning Markov Random Fields
- Differentially Private Quantiles
- Statistical Inference in the Differential Privacy Model
- Privately Learning Mixtures of Axis-Aligned Gaussians