Efficient, Differentially Private Point Estimators

Abstract

Differential privacy is a recent notion of privacy for statistical databases that provides rigorous, meaningful confidentiality guarantees, even in the presence of an attacker with access to arbitrary side information. We show that for a large class of parametric probability models, one can construct a differentially private estimator whose distribution converges to that of the maximum likelihood estimator. In particular, it is efficient and asymptotically unbiased. This result provides (further) compelling evidence that rigorous notions of privacy in statistical databases can be consistent with statistically valid inference.

9 pages

Cited by in corpus (12)

• Differential Privacy and Machine Learning: a Survey and Review
• Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo
• Inference using noisy degrees: Differentially private $\beta$-model and synthetic graphs
• Privacy-preserving parametric inference: a case for robust statistics
• Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation
• A Differentially Private Wilcoxon Signed-Rank Test
• Differentially Private Learning of Undirected Graphical Models using Collective Graphical Models
• A statistical framework for differential privacy
• The Big-O Problem
• Differentially Private Bayesian Inference for Generalized Linear Models
• Per-instance Differential Privacy
• Differentially Private Combinatorial Optimization