Local Privacy, Statistical Minimax Rates, and Learning

John Duchi
Graduate Student, UC Berkeley
Given on: May 10th, 2013

Abstract

We study statistical 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.