pith. sign in

arxiv: 1708.00059 · v1 · pith:XLV46J66new · submitted 2017-07-31 · 🧮 math.ST · cs.IT· cs.LG· math.IT· stat.TH

Asymptotically optimal private estimation under mean square loss

classification 🧮 math.ST cs.ITcs.LGmath.ITstat.TH
keywords schemelossestimationoptimalsamplesunderepsilonestimator
0
0 comments X
read the original abstract

We consider the minimax estimation problem of a discrete distribution with support size $k$ under locally differential privacy constraints. A privatization scheme is applied to each raw sample independently, and we need to estimate the distribution of the raw samples from the privatized samples. A positive number $\epsilon$ measures the privacy level of a privatization scheme. In our previous work (arXiv:1702.00610), we proposed a family of new privatization schemes and the corresponding estimator. We also proved that our scheme and estimator are order optimal in the regime $e^{\epsilon} \ll k$ under both $\ell_2^2$ and $\ell_1$ loss. In other words, for a large number of samples the worst-case estimation loss of our scheme was shown to differ from the optimal value by at most a constant factor. In this paper, we eliminate this gap by showing asymptotic optimality of the proposed scheme and estimator under the $\ell_2^2$ (mean square) loss. More precisely, we show that for any $k$ and $\epsilon,$ the ratio between the worst-case estimation loss of our scheme and the optimal value approaches $1$ as the number of samples tends to infinity.

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.