Privacy Aware Learning

TL;DR

This paper investigates the impact of local privacy constraints on statistical learning, establishing bounds that reveal the tradeoff between data privacy and learning accuracy.

Contribution

It provides sharp bounds on convergence rates under local privacy, quantifying the privacy-utility tradeoff in statistical estimation.

Findings

Derived upper and lower bounds on convergence rates

Quantified the privacy-utility tradeoff

Identified conditions for optimal estimation under privacy constraints

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.