Counterfactual Density Estimation Using Kernel Stein Discrepancies
Abstract
Causal effects are usually studied in terms of the means of counterfactual distributions, which may be insufficient in many scenarios. Given a class of densities known up to normalizing constants, we propose to model counterfactual distributions by minimizing kernel Stein discrepancies in a doubly robust manner. This enables the estimation of counterfactuals over large classes of distributions while exploiting the desired double robustness. We present a theoretical analysis of the proposed estimator, providing sufficient conditions for consistency and asymptotic normality, as well as an examination of its empirical performance.
Cite
Text
Martinez-Taboada and Kennedy. "Counterfactual Density Estimation Using Kernel Stein Discrepancies." International Conference on Learning Representations, 2024.Markdown
[Martinez-Taboada and Kennedy. "Counterfactual Density Estimation Using Kernel Stein Discrepancies." International Conference on Learning Representations, 2024.](https://mlanthology.org/iclr/2024/martineztaboada2024iclr-counterfactual/)BibTeX
@inproceedings{martineztaboada2024iclr-counterfactual,
title = {{Counterfactual Density Estimation Using Kernel Stein Discrepancies}},
author = {Martinez-Taboada, Diego and Kennedy, Edward},
booktitle = {International Conference on Learning Representations},
year = {2024},
url = {https://mlanthology.org/iclr/2024/martineztaboada2024iclr-counterfactual/}
}