Minimax density estimation in the adversarial framework under local differential privacy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Albert, Mélisande, Chevallier, Juliette, Laurent, Béatrice, Sacko, Ousmane
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909692107685888
author Albert, Mélisande
Chevallier, Juliette
Laurent, Béatrice
Sacko, Ousmane
author_facet Albert, Mélisande
Chevallier, Juliette
Laurent, Béatrice
Sacko, Ousmane
contents We consider the problem of nonparametric density estimation under privacy constraints in an adversarial framework. To this end, we study minimax rates over Sobolev spaces under local differential privacy. We first obtain a lower bound which allows us to quantify the impact of privacy compared with the classical framework. Next, we introduce a new Coordinate block privacy mechanism that guarantees local differential privacy, which, coupled with a projection estimator, achieves the minimax optimal rates. Finally, we develop an adaptive procedure which is optimal in the minimax sense up to logarithmic terms.
format Preprint
id arxiv_https___arxiv_org_abs_2403_18357
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Minimax density estimation in the adversarial framework under local differential privacy
Albert, Mélisande
Chevallier, Juliette
Laurent, Béatrice
Sacko, Ousmane
Statistics Theory
We consider the problem of nonparametric density estimation under privacy constraints in an adversarial framework. To this end, we study minimax rates over Sobolev spaces under local differential privacy. We first obtain a lower bound which allows us to quantify the impact of privacy compared with the classical framework. Next, we introduce a new Coordinate block privacy mechanism that guarantees local differential privacy, which, coupled with a projection estimator, achieves the minimax optimal rates. Finally, we develop an adaptive procedure which is optimal in the minimax sense up to logarithmic terms.
title Minimax density estimation in the adversarial framework under local differential privacy
topic Statistics Theory
url https://arxiv.org/abs/2403.18357