Locally Differentially Private Minimum Finding

05/27/2019
by   Kazuto Fukuchi, et al.
0

We investigate a problem of finding the minimum, in which each user has a real value and we want to estimate the minimum of these values under the local differential privacy constraint. We reveal that this problem is fundamentally difficult, and we cannot construct a mechanism that is consistent in the worst case. Instead of considering the worst case, we aim to construct a private mechanism whose error rate is adaptive to the easiness of estimation of the minimum. As a measure of easiness, we introduce a parameter α that characterizes the fatness of the minimum-side tail of the user data distribution. As a result, we reveal that the mechanism can achieve O((^6N/ϵ^2N)^1/2α) error without knowledge of α and the error rate is near-optimal in the sense that any mechanism incurs Ω((1/ϵ^2N)^1/2α) error. Furthermore, we demonstrate that our mechanism outperforms a naive mechanism by empirical evaluations on synthetic datasets. Also, we conducted experiments on the MovieLens dataset and a purchase history dataset and demonstrate that our algorithm achieves Õ((1/N)^1/2α) error adaptively to α.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/15/2021

Locally Differentially Private Frequency Estimation

We present two new local differentially private algorithms for frequency...
research
06/01/2021

Instance-optimal Mean Estimation Under Differential Privacy

Mean estimation under differential privacy is a fundamental problem, but...
research
05/28/2022

Differentially Private Covariance Revisited

In this paper, we present three new error bounds, in terms of the Froben...
research
11/03/2017

Optimal Data Acquisition for Statistical Estimation

We consider a data analyst's problem of purchasing data from strategic a...
research
05/09/2019

Differentially Private Learning with Adaptive Clipping

We introduce a new adaptive clipping technique for training learning mod...
research
03/08/2021

Efficient Accuracy Prediction for Differentially Private Algorithms

Differential privacy is a strong mathematical notion of privacy. Still, ...

Please sign up or login with your details

Forgot password? Click here to reset