Near Instance-Optimality in Differential Privacy

05/16/2020
by   Hilal Asi, et al.
0

We develop two notions of instance optimality in differential privacy, inspired by classical statistical theory: one by defining a local minimax risk and the other by considering unbiased mechanisms and analogizing the Cramer-Rao bound, and we show that the local modulus of continuity of the estimand of interest completely determines these quantities. We also develop a complementary collection mechanisms, which we term the inverse sensitivity mechanisms, which are instance optimal (or nearly instance optimal) for a large class of estimands. Moreover, these mechanisms uniformly outperform the smooth sensitivity framework on each instance for several function classes of interest, including real-valued continuous functions. We carefully present two instantiations of the mechanisms for median and robust regression estimation with corresponding experiments.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

06/01/2021

Instance-optimal Mean Estimation Under Differential Privacy

Mean estimation under differential privacy is a fundamental problem, but...
05/03/2018

Geometrizing rates of convergence under differential privacy constraints

We study estimation of a functional θ( P) of an unknown probability dist...
01/18/2018

On the Contractivity of Privacy Mechanisms

We present a novel way to compare the statistical cost of privacy mechan...
06/06/2019

Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation

The simplest and most widely applied method for guaranteeing differentia...
02/11/2020

Minimax optimal goodness-of-fit testing for densities under a local differential privacy constraint

Finding anonymization mechanisms to protect personal data is at the hear...
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 ...
09/17/2021

Robust Control Under Uncertainty via Bounded Rationality and Differential Privacy

The rapid development of affordable and compact high-fidelity sensors (e...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.