Differentially Private Two-Stage Gradient Descent for Instrumental Variable Regression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Haodong, Jin, Yanhao, Balasubramanian, Krishnakumar, Lai, Lifeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918339156115456
author Liang, Haodong
Jin, Yanhao
Balasubramanian, Krishnakumar
Lai, Lifeng
author_facet Liang, Haodong
Jin, Yanhao
Balasubramanian, Krishnakumar
Lai, Lifeng
contents We study instrumental variable regression (IVaR) under differential privacy constraints. Classical IVaR methods (like two-stage least squares regression) rely on solving moment equations that directly use sensitive covariates and instruments, creating significant risks of privacy leakage and posing challenges in designing algorithms that are both statistically efficient and differentially private. We propose a noisy two-stage gradient descent algorithm that ensures $ρ$-zero-concentrated differential privacy by injecting carefully calibrated noise into the gradient updates. Our analysis establishes finite-sample convergence rates for the proposed method, showing that the algorithm achieves consistency while preserving privacy. In particular, we derive precise bounds quantifying the trade-off among optimization, privacy, and sampling error. To the best of our knowledge, this is the first work to provide both privacy guarantees and provable convergence rates for instrumental variable regression in linear models. We further validate our theoretical findings with experiments on both synthetic and real datasets, demonstrating that our method offers practical accuracy-privacy trade-offs.
format Preprint
id arxiv_https___arxiv_org_abs_2509_22794
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Differentially Private Two-Stage Gradient Descent for Instrumental Variable Regression
Liang, Haodong
Jin, Yanhao
Balasubramanian, Krishnakumar
Lai, Lifeng
Machine Learning
Artificial Intelligence
Econometrics
Statistics Theory
We study instrumental variable regression (IVaR) under differential privacy constraints. Classical IVaR methods (like two-stage least squares regression) rely on solving moment equations that directly use sensitive covariates and instruments, creating significant risks of privacy leakage and posing challenges in designing algorithms that are both statistically efficient and differentially private. We propose a noisy two-stage gradient descent algorithm that ensures $ρ$-zero-concentrated differential privacy by injecting carefully calibrated noise into the gradient updates. Our analysis establishes finite-sample convergence rates for the proposed method, showing that the algorithm achieves consistency while preserving privacy. In particular, we derive precise bounds quantifying the trade-off among optimization, privacy, and sampling error. To the best of our knowledge, this is the first work to provide both privacy guarantees and provable convergence rates for instrumental variable regression in linear models. We further validate our theoretical findings with experiments on both synthetic and real datasets, demonstrating that our method offers practical accuracy-privacy trade-offs.
title Differentially Private Two-Stage Gradient Descent for Instrumental Variable Regression
topic Machine Learning
Artificial Intelligence
Econometrics
Statistics Theory
url https://arxiv.org/abs/2509.22794