Improving the Variance of Differentially Private Randomized Experiments through Clustering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Javanmard, Adel, Mirrokni, Vahab, Pouget-Abadie, Jean
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908381668704256
author Javanmard, Adel
Mirrokni, Vahab
Pouget-Abadie, Jean
author_facet Javanmard, Adel
Mirrokni, Vahab
Pouget-Abadie, Jean
contents Estimating causal effects from randomized experiments is only possible if participants are willing to disclose their potentially sensitive responses. Differential privacy, a widely used framework for ensuring an algorithms privacy guarantees, can encourage participants to share their responses without the risk of de-anonymization. However, many mechanisms achieve differential privacy by adding noise to the original dataset, which reduces the precision of causal effect estimation. This introduces a fundamental trade-off between privacy and variance when performing causal analyses on differentially private data. In this work, we propose a new differentially private mechanism, "Cluster-DP", which leverages a given cluster structure in the data to improve the privacy-variance trade-off. While our results apply to any clustering, we demonstrate that selecting higher-quality clusters, according to a quality metric we introduce, can decrease the variance penalty without compromising privacy guarantees. Finally, we evaluate the theoretical and empirical performance of our Cluster-DP algorithm on both real and simulated data, comparing it to common baselines, including two special cases of our algorithm: its unclustered version and a uniform-prior version.
format Preprint
id arxiv_https___arxiv_org_abs_2308_00957
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Improving the Variance of Differentially Private Randomized Experiments through Clustering
Javanmard, Adel
Mirrokni, Vahab
Pouget-Abadie, Jean
Machine Learning
Cryptography and Security
Methodology
Estimating causal effects from randomized experiments is only possible if participants are willing to disclose their potentially sensitive responses. Differential privacy, a widely used framework for ensuring an algorithms privacy guarantees, can encourage participants to share their responses without the risk of de-anonymization. However, many mechanisms achieve differential privacy by adding noise to the original dataset, which reduces the precision of causal effect estimation. This introduces a fundamental trade-off between privacy and variance when performing causal analyses on differentially private data. In this work, we propose a new differentially private mechanism, "Cluster-DP", which leverages a given cluster structure in the data to improve the privacy-variance trade-off. While our results apply to any clustering, we demonstrate that selecting higher-quality clusters, according to a quality metric we introduce, can decrease the variance penalty without compromising privacy guarantees. Finally, we evaluate the theoretical and empirical performance of our Cluster-DP algorithm on both real and simulated data, comparing it to common baselines, including two special cases of our algorithm: its unclustered version and a uniform-prior version.
title Improving the Variance of Differentially Private Randomized Experiments through Clustering
topic Machine Learning
Cryptography and Security
Methodology
url https://arxiv.org/abs/2308.00957