2026-07-24T02:01:31Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:8344 2024-03-06T10:42:08Z ddc:004 open_access

Finite Sample Differentially Private Confidence Intervals Karwa, Vishesh Vadhan, Salil Differential Privacy Confidence Intervals Lower bounds Finite Sample 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. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Vishesh Karwa and Salil Vadhan 2018 Is Part Of LIPIcs, Volume 94, 9th Innovations in Theoretical Computer Science Conference (ITCS 2018) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.ITCS.2018.44 urn:nbn:de:0030-drops-83449 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ITCS.2018.44 eng https://creativecommons.org/licenses/by/3.0/legalcode