Stochastic Causal Programming for Bounding Treatment Effects

Kirtan Padh, Jakob Zeitler, David Watson, Matt Kusner, Ricardo Silva, Niki Kilbertus
Proceedings of the Second Conference on Causal Learning and Reasoning, PMLR 213:142-176, 2023.

Abstract

Causal effect estimation is important for many tasks in the natural and social sciences. We design algorithms for the continuous partial identification problem: bounding the effects of multivariate, continuous treatments when unmeasured confounding makes identification impossible. Specifically, we cast causal effects as objective functions within a constrained optimization problem, and minimize/maximize these functions to obtain bounds. We combine flexible learning algorithms with Monte Carlo methods to implement a family of solutions under the name of stochastic causal programming. In particular, we show how the generic framework can be efficiently formulated in settings where auxiliary variables are clustered into pre-treatment and post-treatment sets, where no fine-grained causal graph can be easily specified. In these settings, we can avoid the need for fully specifying the distribution family of hidden common causes. Monte Carlo computation is also much simplified, leading to algorithms which are more computationally stable against alternatives.

Cite this Paper

BibTeX
@InProceedings{pmlr-v213-padh23a, title = {Stochastic Causal Programming for Bounding Treatment Effects}, author = {Padh, Kirtan and Zeitler, Jakob and Watson, David and Kusner, Matt and Silva, Ricardo and Kilbertus, Niki}, booktitle = {Proceedings of the Second Conference on Causal Learning and Reasoning}, pages = {142--176}, year = {2023}, editor = {van der Schaar, Mihaela and Zhang, Cheng and Janzing, Dominik}, volume = {213}, series = {Proceedings of Machine Learning Research}, month = {11--14 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v213/padh23a/padh23a.pdf}, url = {https://proceedings.mlr.press/v213/padh23a.html}, abstract = {Causal effect estimation is important for many tasks in the natural and social sciences. We design algorithms for the continuous partial identification problem: bounding the effects of multivariate, continuous treatments when unmeasured confounding makes identification impossible. Specifically, we cast causal effects as objective functions within a constrained optimization problem, and minimize/maximize these functions to obtain bounds. We combine flexible learning algorithms with Monte Carlo methods to implement a family of solutions under the name of stochastic causal programming. In particular, we show how the generic framework can be efficiently formulated in settings where auxiliary variables are clustered into pre-treatment and post-treatment sets, where no fine-grained causal graph can be easily specified. In these settings, we can avoid the need for fully specifying the distribution family of hidden common causes. Monte Carlo computation is also much simplified, leading to algorithms which are more computationally stable against alternatives.} }
Endnote
%0 Conference Paper %T Stochastic Causal Programming for Bounding Treatment Effects %A Kirtan Padh %A Jakob Zeitler %A David Watson %A Matt Kusner %A Ricardo Silva %A Niki Kilbertus %B Proceedings of the Second Conference on Causal Learning and Reasoning %C Proceedings of Machine Learning Research %D 2023 %E Mihaela van der Schaar %E Cheng Zhang %E Dominik Janzing %F pmlr-v213-padh23a %I PMLR %P 142--176 %U https://proceedings.mlr.press/v213/padh23a.html %V 213 %X Causal effect estimation is important for many tasks in the natural and social sciences. We design algorithms for the continuous partial identification problem: bounding the effects of multivariate, continuous treatments when unmeasured confounding makes identification impossible. Specifically, we cast causal effects as objective functions within a constrained optimization problem, and minimize/maximize these functions to obtain bounds. We combine flexible learning algorithms with Monte Carlo methods to implement a family of solutions under the name of stochastic causal programming. In particular, we show how the generic framework can be efficiently formulated in settings where auxiliary variables are clustered into pre-treatment and post-treatment sets, where no fine-grained causal graph can be easily specified. In these settings, we can avoid the need for fully specifying the distribution family of hidden common causes. Monte Carlo computation is also much simplified, leading to algorithms which are more computationally stable against alternatives.
APA
Padh, K., Zeitler, J., Watson, D., Kusner, M., Silva, R. & Kilbertus, N.. (2023). Stochastic Causal Programming for Bounding Treatment Effects. Proceedings of the Second Conference on Causal Learning and Reasoning, in Proceedings of Machine Learning Research 213:142-176 Available from https://proceedings.mlr.press/v213/padh23a.html.

Related Material