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

page 1

page 2

page 3

page 4

research
06/01/2021

Instance-optimal Mean Estimation Under Differential Privacy

Mean estimation under differential privacy is a fundamental problem, but...
research
01/31/2023

Gaussian Noise is Nearly Instance Optimal for Private Unbiased Mean Estimation

We investigate unbiased high-dimensional mean estimators in differential...
research
05/03/2018

Geometrizing rates of convergence under differential privacy constraints

We study estimation of a functional θ( P) of an unknown probability dist...
research
05/31/2022

On rate optimal private regression under local differential privacy

We consider the problem of estimating a regression function from anonymi...
research
01/25/2023

Efficiency in local differential privacy

We develop a theory of asymptotic efficiency in regular parametric model...
research
06/06/2019

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

The simplest and most widely applied method for guaranteeing differentia...
research
11/14/2020

Inference Functions for Semiparametric Models

The paper discusses inference techniques for semiparametric models based...

Please sign up or login with your details

Forgot password? Click here to reset