DeepAI AI Chat
Log In Sign Up

INSPECTRE: Privately Estimating the Unseen

by   Jayadev Acharya, et al.
cornell university

We develop differentially private methods for estimating various distributional properties. Given a sample from a discrete distribution p, some functional f, and accuracy and privacy parameters α and ε, the goal is to estimate f(p) up to accuracy α, while maintaining ε-differential privacy of the sample. We prove almost-tight bounds on the sample size required for this problem for several functionals of interest, including support size, support coverage, and entropy. We show that the cost of privacy is negligible in a variety of settings, both theoretically and experimentally. Our methods are based on a sensitivity analysis of several state-of-the-art methods for estimating these properties with sublinear sample complexities.


page 1

page 2

page 3

page 4


Differentially Private Identity and Closeness Testing of Discrete Distributions

We investigate the problems of identity and closeness testing over a dis...

Prior-Aware Distribution Estimation for Differential Privacy

Joint distribution estimation of a dataset under differential privacy is...

Privately Estimating Graph Parameters in Sublinear time

We initiate a systematic study of algorithms that are both differentiall...

Classification under local differential privacy

We consider the binary classification problem in a setup that preserves ...

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...

Efficiently Estimating Erdos-Renyi Graphs with Node Differential Privacy

We give a simple, computationally efficient, and node-differentially-pri...

Differentially private depth functions and their associated medians

In this paper, we investigate the differentially private estimation of d...

Code Repositories