References & Citations
Mathematics > Statistics Theory
Title: Minimax density estimation in the adversarial framework under local differential privacy
(Submitted on 27 Mar 2024)
Abstract: We consider the problem of nonparametric density estimation under privacy constraints in an adversarial framework. To this end, we study minimax rates under local differential privacy over Sobolev spaces. 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.
Link back to: arXiv, form interface, contact.