EconBase
← All papers

Differentially Private Estimation of Heterogeneous Causal Effects

Fengshi Niu, Harsha Nori, Brian Quistorff, Rich Caruana, Donald Ngwe, Aadharsh Kannan

arXiv 22 Feb 2022 · Statistics — Machine Learning · 5 citations (OpenAlex)

arXiv:2202.11043 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Estimating heterogeneous treatment effects in domains such as healthcare or social science often involves sensitive data where protecting privacy is important. We introduce a general meta-algorithm for estimating conditional average treatment effects (CATE) with differential privacy (DP) guarantees. Our meta-algorithm can work with simple, single-stage CATE estimators such as S-learner and more complex multi-stage estimators such as DR and R-learner. We perform a tight privacy analysis by taking advantage of sample splitting in our meta-algorithm and the parallel composition property of differential privacy. In this paper, we implement our approach using DP-EBMs as the base learner. DP-EBMs are interpretable, high-accuracy models with privacy guarantees, which allow us to directly observe the impact of DP noise on the learned causal model. Our experiments show that multi-stage CATE estimators incur larger accuracy loss than single-stage CATE or ATE estimators and that most of the accuracy loss from differential privacy is due to an increase in variance, not biased estimates of treatment effects.

Citation extraction

35
references
60
in-text mentions
35
distinct cited
6
self-citations
6,610
main-text words

appendix boundary found by appendix_titled_section at “Appendix: Proof of Theorem \ref{thm: DP guarantee}” · 93% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1X Nie and S Wager (2020) Quasi-oracle estimation of heterogeneous treatment effects1.00073100%
2Edward H Kennedy (2020) Optimal doubly robust estimation of heterogeneous causal effects1.00053100%
3Harsha Nori, Rich Caruana, Zhiqi Bu, Judy Hanwen Shen, and Janardhan… (2021) Accuracy, interpretability, and differential privacy via explainable boosting self0.92843100%
4Victor Chernozhukov, Denis Chetverikov, Mert Demirer, Esther Duflo,… (2018) Double/debiased machine learning for treatment and structural parameters0.73732100%
5Jinshuo Dong, Aaron Roth, and Weijie J Su (2019) Gaussian differential privacy0.73732100%
6Harsha Nori, Samuel Jenkins, Paul Koch, and Rich Caruana (2019) Interpretml: A unified framework for machine learning interpretability self0.73732100%
7Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith (2006) Calibrating noise to sensitivity in private data analysis0.64422100%
8Sören R. Künzel, Jasjeet S. Sekhon, Peter J. Bickel, and Bin Yu (2019) Metalearners for estimating heterogeneous treatment effects using machine learning0.64422100%
9James M. Robins, Andrea Rotnitzky, and Lue Ping Zhao (1994) Estimation of regression coefficients when some regressors are not always observed0.64422100%
10Mark J Van der Laan and Sherri Rose (2011) Targeted learning: Causal inference for observational and experimental data0.64422100%

Showing the top 10 of 35 scored citations.