Your Assumed DAG is Wrong And Here’s How To Deal With It

Kirtan Padh, Zhufeng Li, Cecilia Casolo, Niki Kilbertus
Proceedings of the Fourth Conference on Causal Learning and Reasoning, PMLR 275:1239-1267, 2025.

Abstract

Assuming a directed acyclic graph (DAG) that represents prior knowledge of causal relationships between variables is a common starting point for cause-effect estimation. Existing literature typically invokes hypothetical domain expert knowledge or causal discovery algorithms to justify this assumption. In practice, neither may propose a single DAG with high confidence: domain experts are hesitant to rule out dependencies with certainty or have ongoing disputes about relationships, whereas causal discovery often only provides an equivalence class of DAGs, relies on untestable assumptions itself, or are sensitive to hyperparameter and threshold choices. We propose an efficient, gradient-based optimization method that provides bounds for causal queries over a collection of plausible causal graphs given prior knowledge that may still be too large for exhaustive enumeration. We demonstrate excellent coverage and sharpness of our bounds for causal queries such as average treatment effect estimation in linear and non-linear synthetic settings as well as on real-world data. Our approach is an easy-to-use and widely applicable rebuttal to the valid critique of ‘What if your assumed DAG is wrong?’.

Cite this Paper

BibTeX
@InProceedings{pmlr-v275-padh25a, title = {Your Assumed DAG is Wrong And Here’s How To Deal With It}, author = {Padh, Kirtan and Li, Zhufeng and Casolo, Cecilia and Kilbertus, Niki}, booktitle = {Proceedings of the Fourth Conference on Causal Learning and Reasoning}, pages = {1239--1267}, year = {2025}, editor = {Huang, Biwei and Drton, Mathias}, volume = {275}, series = {Proceedings of Machine Learning Research}, month = {07--09 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v275/main/assets/padh25a/padh25a.pdf}, url = {https://proceedings.mlr.press/v275/padh25a.html}, abstract = {Assuming a directed acyclic graph (DAG) that represents prior knowledge of causal relationships between variables is a common starting point for cause-effect estimation. Existing literature typically invokes hypothetical domain expert knowledge or causal discovery algorithms to justify this assumption. In practice, neither may propose a single DAG with high confidence: domain experts are hesitant to rule out dependencies with certainty or have ongoing disputes about relationships, whereas causal discovery often only provides an equivalence class of DAGs, relies on untestable assumptions itself, or are sensitive to hyperparameter and threshold choices. We propose an efficient, gradient-based optimization method that provides bounds for causal queries over a collection of plausible causal graphs given prior knowledge that may still be too large for exhaustive enumeration. We demonstrate excellent coverage and sharpness of our bounds for causal queries such as average treatment effect estimation in linear and non-linear synthetic settings as well as on real-world data. Our approach is an easy-to-use and widely applicable rebuttal to the valid critique of ‘What if your assumed DAG is wrong?’.} }
Endnote
%0 Conference Paper %T Your Assumed DAG is Wrong And Here’s How To Deal With It %A Kirtan Padh %A Zhufeng Li %A Cecilia Casolo %A Niki Kilbertus %B Proceedings of the Fourth Conference on Causal Learning and Reasoning %C Proceedings of Machine Learning Research %D 2025 %E Biwei Huang %E Mathias Drton %F pmlr-v275-padh25a %I PMLR %P 1239--1267 %U https://proceedings.mlr.press/v275/padh25a.html %V 275 %X Assuming a directed acyclic graph (DAG) that represents prior knowledge of causal relationships between variables is a common starting point for cause-effect estimation. Existing literature typically invokes hypothetical domain expert knowledge or causal discovery algorithms to justify this assumption. In practice, neither may propose a single DAG with high confidence: domain experts are hesitant to rule out dependencies with certainty or have ongoing disputes about relationships, whereas causal discovery often only provides an equivalence class of DAGs, relies on untestable assumptions itself, or are sensitive to hyperparameter and threshold choices. We propose an efficient, gradient-based optimization method that provides bounds for causal queries over a collection of plausible causal graphs given prior knowledge that may still be too large for exhaustive enumeration. We demonstrate excellent coverage and sharpness of our bounds for causal queries such as average treatment effect estimation in linear and non-linear synthetic settings as well as on real-world data. Our approach is an easy-to-use and widely applicable rebuttal to the valid critique of ‘What if your assumed DAG is wrong?’.
APA
Padh, K., Li, Z., Casolo, C. & Kilbertus, N.. (2025). Your Assumed DAG is Wrong And Here’s How To Deal With It. Proceedings of the Fourth Conference on Causal Learning and Reasoning, in Proceedings of Machine Learning Research 275:1239-1267 Available from https://proceedings.mlr.press/v275/padh25a.html.

Related Material