Mean Estimation with User-level Privacy under Data Heterogeneity

A key challenge in many modern data analysis tasks is that user data are heterogeneous. Different users may possess vastly different numbers of data points. More importantly, it cannot be assumed that all users sample from the same underlying distribution. This is true, for example in language data,...

Full description

Saved in:
Bibliographic Details
Main Authors Cummings, Rachel, Feldman, Vitaly, McMillan, Audra, Talwar, Kunal
Format Journal Article
LanguageEnglish
Published 28.07.2023
Subjects
Computer Science - Cryptography and Security
Computer Science - Data Structures and Algorithms
Computer Science - Learning
Statistics - Machine Learning
Online AccessGet full text

Cover

More Information
Summary:A key challenge in many modern data analysis tasks is that user data are heterogeneous. Different users may possess vastly different numbers of data points. More importantly, it cannot be assumed that all users sample from the same underlying distribution. This is true, for example in language data, where different speech styles result in data heterogeneity. In this work we propose a simple model of heterogeneous user data that allows user data to differ in both distribution and quantity of data, and provide a method for estimating the population-level mean while preserving user-level differential privacy. We demonstrate asymptotic optimality of our estimator and also prove general lower bounds on the error achievable in the setting we introduce.
DOI:10.48550/arxiv.2307.15835