optimal local privacy
Privacy Aware Learning
Martin J. Wainwright, Michael I. Jordan, John C. Duchi
We study statistical risk minimization problems under a version of privacy 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, measured by convergence rate, of any statistical estimator.
Privacy Aware Learning John C. Duchi 1 Michael I. Jordan
We study statistical risk minimization problems under a version of privacy 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, measured by convergence rate, of any statistical estimator.
Privacy Aware Learning
Duchi, John C., Jordan, Michael I., Wainwright, Martin J.
Natural tensions between learning and privacy arise whenever a learner must aggregate data across multiple individuals. The learner wishes to make optimal use of each data point, whereas the providers of the data may wish to limit detailed exposure, either to the learner or to other individuals. A characterization of such tensions in the form of quantitative tradeoffs is of great utility: it can inform public discourse surrounding the design of systems that learn from data, and the tradeoffs can be exploited as controllable degrees of freedom whenever such a system is deployed. In this paper, we approach this problem from the point of view of statistical decision theory. The decision-theoretic perspective offers a number of advantages.
Privacy Aware Learning
Wainwright, Martin J., Jordan, Michael I., Duchi, John C.
We study statistical risk minimization problems under a version of privacy 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 betweenthe amount of privacy the data preserves and the utility, measured by convergence rate, of any statistical estimator.