DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 2017 · 38 citations · 16 references
ComputingHealth InformaticsCryptographyPrivacy EngineeringStatisticsData ConfidentialityData ProtectionDifferential PrivacyAsymptotic CoverageCoverageDifferentially Private Mean EstimationDifferentially Private StatisticsFinite Sample EstimationFinite-sample CoverageLower BoundsPrivate Statistical Estimation
We study the problem of estimating finite sample confidence intervals of the mean of a normal population under the constraint of differential privacy. We consider both the known and unknown variance cases and construct differentially private algorithms to estimate confidence intervals. Crucially, our algorithms guarantee a finite sample coverage, as opposed to an asymptotic coverage. Unlike most previous differentially private algorithms, we do not require the domain of the samples to be bounded. We also prove lower bounds on the expected size of any differentially private confidence set showing that our the parameters are optimal up to polylogarithmic factors.
16
Local Privacy and Statistical Minimax Rates
John C. Duchi, Michael I. Jordan, Martin J. Wainwright · 2013 · 990 citations
Avrim Blum, Cynthia Dwork, Frank McSherry et al. · 2005 · 823 citations
Privacy-preserving statistical estimation with optimal convergence rates
Adam Smith · 2011 · 265 citations