Abstract

We study statistical risk minimization problems under a privacy model in which the data is kept confidential even from the learner. In this local privacy framework, we establish sharp upper and lower bounds on the convergence rates of statistical estimation procedures. As a consequence, we exhibit a precise tradeoff between the amount of privacy the data preserves and the utility, as measured by convergence rate, of any statistical estimator or learning procedure.

Keywords

Computer scienceEstimatorConvergence (economics)Statistical learningRate of convergenceConfidentialityInformation privacyEmpirical risk minimizationMinificationStatistical modelArtificial intelligenceComputer securityStatisticsMathematicsKey (lock)

Affiliated Institutions

Related Publications

Publication Info

Year
2014
Type
article
Volume
61
Issue
6
Pages
1-57
Citations
176
Access
Closed

External Links

View on DOI.org

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

176
OpenAlex

Cite This

John C. Duchi, Michael I. Jordan, Martin J. Wainwright (2014). Privacy Aware Learning. Journal of the ACM , 61 (6) , 1-57. https://doi.org/10.1145/2666468

Identifiers

DOI
10.1145/2666468