Locally differentially private estimation of nonlinear functionals of discrete distributions

Abstract

We study the problem of estimating non-linear functionals of discrete distributions in the context of local differential privacy. The initial data $x_1,\dots ,x_n\in [K]$ are supposed i.i.d. and distributed according to an unknown discrete distribution $p=(p_1,\dots ,p_K)$. Only $\alpha$-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 $F_{\gamma }={\sum }_{k=1}^K{p}_k^{\gamma }$, $\gamma >0$ as a function of $K,n$ and $\alpha$. In the non-interactive case, we study two plug-in type estimators of $F_{\gamma }$, for all $\gamma >0$, 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 $\gamma >1$ a two-step procedure which attains the faster parametric rate $(n{\alpha }^2{)}^{-1/2}$ when $\gamma \ge 2$. We give lower bounds results over all $\alpha$-LDP mechanisms and all estimators using the private samples.

References in corpus (5)

• Does Dirichlet Prior Smoothing Solve the Shannon Entropy Estimation Problem?
• Maximum Likelihood Estimation of Functionals of Discrete Distributions
• Testing composite hypotheses, Hermite polynomials and optimal estimation of a nonsmooth functional
• Optimal rates of entropy estimation over Lipschitz balls
• Minimax Optimal Estimators for Additive Scalar Functionals of Discrete Distributions