ICML 2022spotlight24 citations
End-to-End Balancing for Causal Continuous Treatment-Effect Estimation
Taha Bahadori, Eric Tchetgen Tchetgen, David Heckerman
Abstract
We study the problem of observational causal inference with continuous treatment. We focus on the challenge of estimating the causal response curve for infrequently-observed treatment values. We design a new algorithm based on the framework of entropy balancing which learns weights that directly maximize causal inference accuracy using end-to-end optimization. Our weights can be customized for different datasets and causal inference algorithms. We propose a new theory for consistency of entropy balancing for continuous treatments. Using synthetic and real-world data, we show that our proposed algorithm outperforms the entropy balancing in terms of causal inference accuracy.
BibTeX
@InProceedings{pmlr-v162-bahadori22a,
title = {End-to-End Balancing for Causal Continuous Treatment-Effect Estimation},
author = {Bahadori, Taha and Tchetgen, Eric Tchetgen and Heckerman, David},
booktitle = {Proceedings of the 39th International Conference on Machine Learning},
pages = {1313--1326},
year = {2022},
editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
volume = {162},
series = {Proceedings of Machine Learning Research},
month = {17--23 Jul},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v162/bahadori22a/bahadori22a.pdf},
url = {https://proceedings.mlr.press/v162/bahadori22a.html},
abstract = {We study the problem of observational causal inference with continuous treatment. We focus on the challenge of estimating the causal response curve for infrequently-observed treatment values. We design a new algorithm based on the framework of entropy balancing which learns weights that directly maximize causal inference accuracy using end-to-end optimization. Our weights can be customized for different datasets and causal inference algorithms. We propose a new theory for consistency of entropy balancing for continuous treatments. Using synthetic and real-world data, we show that our proposed algorithm outperforms the entropy balancing in terms of causal inference accuracy.}
}