DeepAI AI Chat
Log In Sign Up

Locally Differentially-Private Randomized Response for Discrete Distribution Learning

by   Adriano Pastore, et al.

We consider a setup in which confidential i.i.d. samples X_1,,X_n from an unknown finite-support distribution p are passed through n copies of a discrete privatization channel (a.k.a. mechanism) producing outputs Y_1,,Y_n. The channel law guarantees a local differential privacy of ϵ. Subject to a prescribed privacy level ϵ, the optimal channel should be designed such that an estimate of the source distribution based on the channel outputs Y_1,,Y_n converges as fast as possible to the exact value p. For this purpose we study the convergence to zero of three distribution distance metrics: f-divergence, mean-squared error and total variation. We derive the respective normalized first-order terms of convergence (as n→∞), which for a given target privacy ϵ represent a rule-of-thumb factor by which the sample size must be augmented so as to achieve the same estimation accuracy as that of a non-randomizing channel. We formulate the privacy-fidelity trade-off problem as being that of minimizing said first-order term under a privacy constraint ϵ. We further identify a scalar quantity that captures the essence of this trade-off, and prove bounds and data-processing inequalities on this quantity. For some specific instances of the privacy-fidelity trade-off problem, we derive inner and outer bounds on the optimal trade-off curve.


page 1

page 2

page 3

page 4


Fisher information under local differential privacy

We develop data processing inequalities that describe how Fisher informa...

Accuracy-Privacy Trade-off in Analyzing Randomized Responses

We consider the problem of analyzing a global property of private data, ...

Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling

Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and Th...

INSPECTRE: Privately Estimating the Unseen

We develop differentially private methods for estimating various distrib...

On the Statistical Complexity of Estimation and Testing under Privacy Constraints

Producing statistics that respect the privacy of the samples while still...

The Gaussian lossy Gray-Wyner network

We consider the problem of source coding subject to a fidelity criterion...