Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis
Abstract
Many algorithms have been recently proposed for causal machine learning. Yet, there is little to no theory on their quality, especially considering finite samples. In this work, we propose a theory based on generalization bounds that provides such guarantees. By introducing a novel change-of-measure inequality, we are able to tightly bound the model loss in terms of the deviation of the treatment propensities over the population, which we show can be empirically limited. Our theory is fully rigorous and holds even in the face of hidden confounding and violations of positivity. We demonstrate our bounds on semi-synthetic and real data, showcasing their remarkable tightness and practical utility.
Cite
Text
Csillag et al. "Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis." International Conference on Machine Learning, 2024.Markdown
[Csillag et al. "Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis." International Conference on Machine Learning, 2024.](https://mlanthology.org/icml/2024/csillag2024icml-generalization/)BibTeX
@inproceedings{csillag2024icml-generalization,
title = {{Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis}},
author = {Csillag, Daniel and Struchiner, Claudio Jose and Goedert, Guilherme Tegoni},
booktitle = {International Conference on Machine Learning},
year = {2024},
pages = {9576-9602},
volume = {235},
url = {https://mlanthology.org/icml/2024/csillag2024icml-generalization/}
}