English

Asymptotically optimal private estimation under mean square loss

Statistics Theory 2017-08-02 v1 Information Theory Machine Learning math.IT Statistics Theory

Abstract

We consider the minimax estimation problem of a discrete distribution with support size kk 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 ϵ\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 eϵke^{\epsilon} \ll k under both 22\ell_2^2 and 1\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 22\ell_2^2 (mean square) loss. More precisely, we show that for any kk and ϵ,\epsilon, the ratio between the worst-case estimation loss of our scheme and the optimal value approaches 11 as the number of samples tends to infinity.

Keywords

Cite

@article{arxiv.1708.00059,
  title  = {Asymptotically optimal private estimation under mean square loss},
  author = {Min Ye and Alexander Barg},
  journal= {arXiv preprint arXiv:1708.00059},
  year   = {2017}
}
R2 v1 2026-06-22T21:02:50.143Z