DeepAI
Log In Sign Up

Fisher information under local differential privacy

05/21/2020
by   Leighton Pate Barnes, et al.
0

We develop data processing inequalities that describe how Fisher information from statistical samples can scale with the privacy parameter ε under local differential privacy constraints. These bounds are valid under general conditions on the distribution of the score of the statistical model, and they elucidate under which conditions the dependence on ε is linear, quadratic, or exponential. We show how these inequalities imply order optimal lower bounds for private estimation for both the Gaussian location model and discrete distribution estimation for all levels of privacy ε>0. We further apply these inequalities to sparse Bernoulli models and demonstrate privacy mechanisms and estimators with order-matching squared ℓ^2 error.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/01/2019

Lower Bounds for Locally Private Estimation via Communication Complexity

We develop lower bounds for estimation under local privacy constraints--...
02/11/2021

Fisher Information and Mutual Information Constraints

We consider the processing of statistical samples X∼ P_θ by a channel p(...
11/29/2018

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...
11/24/2019

Four accuracy bounds and one estimator for frequency estimation under local differential privacy

We present four lower bounds on the mean squared error of both frequency...
02/12/2019

Inequalities and Approximations for Fisher Information in the Presence of Nuisance Parameters

Many imaging systems are used to estimate a vector of parameters associa...
11/07/2022

Discrete Distribution Estimation under User-level Local Differential Privacy

We study discrete distribution estimation under user-level local differe...
12/02/2022

Integer Subspace Differential Privacy

We propose new differential privacy solutions for when external invarian...