Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Xuxing, Roy, Abhishek, Hu, Yifan, Balasubramanian, Krishnakumar
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910464112328704
author Chen, Xuxing
Roy, Abhishek
Hu, Yifan
Balasubramanian, Krishnakumar
author_facet Chen, Xuxing
Roy, Abhishek
Hu, Yifan
Balasubramanian, Krishnakumar
contents We develop and analyze algorithms for instrumental variable regression by viewing the problem as a conditional stochastic optimization problem. In the context of least-squares instrumental variable regression, our algorithms neither require matrix inversions nor mini-batches and provides a fully online approach for performing instrumental variable regression with streaming data. When the true model is linear, we derive rates of convergence in expectation, that are of order $\mathcal{O}(\log T/T)$ and $\mathcal{O}(1/T^{1-ι})$ for any $ι>0$, respectively under the availability of two-sample and one-sample oracles, respectively, where $T$ is the number of iterations. Importantly, under the availability of the two-sample oracle, our procedure avoids explicitly modeling and estimating the relationship between confounder and the instrumental variables, demonstrating the benefit of the proposed approach over recent works based on reformulating the problem as minimax optimization problems. Numerical experiments are provided to corroborate the theoretical results.
format Preprint
id arxiv_https___arxiv_org_abs_2405_19463
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data
Chen, Xuxing
Roy, Abhishek
Hu, Yifan
Balasubramanian, Krishnakumar
Machine Learning
Econometrics
Optimization and Control
We develop and analyze algorithms for instrumental variable regression by viewing the problem as a conditional stochastic optimization problem. In the context of least-squares instrumental variable regression, our algorithms neither require matrix inversions nor mini-batches and provides a fully online approach for performing instrumental variable regression with streaming data. When the true model is linear, we derive rates of convergence in expectation, that are of order $\mathcal{O}(\log T/T)$ and $\mathcal{O}(1/T^{1-ι})$ for any $ι>0$, respectively under the availability of two-sample and one-sample oracles, respectively, where $T$ is the number of iterations. Importantly, under the availability of the two-sample oracle, our procedure avoids explicitly modeling and estimating the relationship between confounder and the instrumental variables, demonstrating the benefit of the proposed approach over recent works based on reformulating the problem as minimax optimization problems. Numerical experiments are provided to corroborate the theoretical results.
title Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data
topic Machine Learning
Econometrics
Optimization and Control
url https://arxiv.org/abs/2405.19463