Analyzing the Differentially Private Theil-Sen Estimator for Simple Linear Regression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sarathy, Jayshree, Vadhan, Salil
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909134218067968
author Sarathy, Jayshree
Vadhan, Salil
author_facet Sarathy, Jayshree
Vadhan, Salil
contents In this paper, we study differentially private point and confidence interval estimators for simple linear regression. Motivated by recent work that highlights the strong empirical performance of an algorithm based on robust statistics, DPTheilSen, we provide a rigorous, finite-sample analysis of its privacy and accuracy properties, offer guidance on setting hyperparameters, and show how to produce differentially private confidence intervals to accompany its point estimates.
format Preprint
id arxiv_https___arxiv_org_abs_2207_13289
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Analyzing the Differentially Private Theil-Sen Estimator for Simple Linear Regression
Sarathy, Jayshree
Vadhan, Salil
Cryptography and Security
Applications
In this paper, we study differentially private point and confidence interval estimators for simple linear regression. Motivated by recent work that highlights the strong empirical performance of an algorithm based on robust statistics, DPTheilSen, we provide a rigorous, finite-sample analysis of its privacy and accuracy properties, offer guidance on setting hyperparameters, and show how to produce differentially private confidence intervals to accompany its point estimates.
title Analyzing the Differentially Private Theil-Sen Estimator for Simple Linear Regression
topic Cryptography and Security
Applications
url https://arxiv.org/abs/2207.13289