pith. sign in

arxiv: 1210.2085 · v2 · pith:GXQMRDO2new · submitted 2012-10-07 · 📊 stat.ML · cs.IT· cs.LG· math.IT

Privacy Aware Learning

classification 📊 stat.ML cs.ITcs.LGmath.IT
keywords privacystatisticalconvergencedatalearningamountawarebounds
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.