Locally differentially private estimation of nonlinear functionals of discrete distributions

07/08/2021
by   Cristina Butucea, et al.
6

We study the problem of estimating non-linear functionals of discrete distributions in the context of local differential privacy. The initial data x_1,…,x_n ∈ [K] are supposed i.i.d. and distributed according to an unknown discrete distribution p = (p_1,…,p_K). Only α-locally differentially private (LDP) samples z_1,...,z_n are publicly available, where the term 'local' means that each z_i is produced using one individual attribute x_i. We exhibit privacy mechanisms (PM) that are interactive (i.e. they are allowed to use already published confidential data) or non-interactive. We describe the behavior of the quadratic risk for estimating the power sum functional F_γ = ∑_k=1^K p_k^γ, γ >0 as a function of K, n and α. In the non-interactive case, we study two plug-in type estimators of F_γ, for all γ >0, that are similar to the MLE analyzed by Jiao et al. (2017) in the multinomial model. However, due to the privacy constraint the rates we attain are slower and similar to those obtained in the Gaussian model by Collier et al. (2020). In the interactive case, we introduce for all γ >1 a two-step procedure which attains the faster parametric rate (n α^2)^-1/2 when γ≥ 2. We give lower bounds results over all α-LDP mechanisms and all estimators using the private samples.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/26/2020

Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms

We find separation rates for testing multinomial or more general discret...
research
03/10/2020

Interactive versus non-interactive locally, differentially private estimation: Two elbows for the quadratic functional

Local differential privacy has recently received increasing attention fr...
research
06/11/2021

Differentially Private Algorithms for Clustering with Stability Assumptions

We study the problem of differentially private clustering under input-st...
research
12/27/2021

Differentially-Private Sublinear-Time Clustering

Clustering is an essential primitive in unsupervised machine learning. W...
research
07/06/2021

Goodness-of-fit testing for Hölder continuous densities under local differential privacy

We address the problem of goodness-of-fit testing for Hölder continuous ...
research
11/30/2020

Sharp phase transitions for exact support recovery under local differential privacy

We address the problem of variable selection in the Gaussian mean model ...
research
11/29/2018

Locally Differentially-Private Randomized Response for Discrete Distribution Learning

We consider a setup in which confidential i.i.d. samples X_1,,X_n from a...

Please sign up or login with your details

Forgot password? Click here to reset