Double Machine Learning for Causal Inference under Shared-State Interference

Chris Hays, Manish Raghavan
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22318-22350, 2025.

Abstract

Researchers and practitioners often wish to measure treatment effects in settings where units interact via markets and recommendation systems. In these settings, units are affected by certain shared states, like prices, algorithmic recommendations or social signals. We formalize this structure, calling it shared-state interference, and argue that our formulation captures many relevant applied settings. Our key modeling assumption is that individuals’ potential outcomes are independent conditional on the shared state. We then prove an extension of a double machine learning (DML) theorem providing conditions for achieving efficient inference under shared-state interference. We also instantiate our general theorem in several models of interest where it is possible to efficiently estimate the average direct effect (ADE) or global average treatment effect (GATE).

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-hays25a, title = {Double Machine Learning for Causal Inference under Shared-State Interference}, author = {Hays, Chris and Raghavan, Manish}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {22318--22350}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/hays25a/hays25a.pdf}, url = {https://proceedings.mlr.press/v267/hays25a.html}, abstract = {Researchers and practitioners often wish to measure treatment effects in settings where units interact via markets and recommendation systems. In these settings, units are affected by certain shared states, like prices, algorithmic recommendations or social signals. We formalize this structure, calling it shared-state interference, and argue that our formulation captures many relevant applied settings. Our key modeling assumption is that individuals’ potential outcomes are independent conditional on the shared state. We then prove an extension of a double machine learning (DML) theorem providing conditions for achieving efficient inference under shared-state interference. We also instantiate our general theorem in several models of interest where it is possible to efficiently estimate the average direct effect (ADE) or global average treatment effect (GATE).} }
Endnote
%0 Conference Paper %T Double Machine Learning for Causal Inference under Shared-State Interference %A Chris Hays %A Manish Raghavan %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-hays25a %I PMLR %P 22318--22350 %U https://proceedings.mlr.press/v267/hays25a.html %V 267 %X Researchers and practitioners often wish to measure treatment effects in settings where units interact via markets and recommendation systems. In these settings, units are affected by certain shared states, like prices, algorithmic recommendations or social signals. We formalize this structure, calling it shared-state interference, and argue that our formulation captures many relevant applied settings. Our key modeling assumption is that individuals’ potential outcomes are independent conditional on the shared state. We then prove an extension of a double machine learning (DML) theorem providing conditions for achieving efficient inference under shared-state interference. We also instantiate our general theorem in several models of interest where it is possible to efficiently estimate the average direct effect (ADE) or global average treatment effect (GATE).
APA
Hays, C. & Raghavan, M.. (2025). Double Machine Learning for Causal Inference under Shared-State Interference. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:22318-22350 Available from https://proceedings.mlr.press/v267/hays25a.html.

Related Material