Spectral Representation for Causal Estimation with Hidden Confounders
Abstract
We study the problem of causal effect estimation in the presence of unobserved confounders, focusing on two settings: instrumental variable (IV) regression with additional observed confounders, and proxy causal learning. Our approach uses a singular value decomposition of a conditional expectation operator combined with a saddle-point optimization method. In the IV regression setting, this can be viewed as a neural network generalization of the seminal approach due to Darolles et al. (2011). Saddle-point formulations have recently gained attention because they mitigate the double-sampling bias and are compatible with modern function approximation methods. We provide experimental validation across various settings and show that our approach outperforms existing methods on common benchmarks.
Cite
Text
Sun et al. "Spectral Representation for Causal Estimation with Hidden Confounders." Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, 2025.Markdown
[Sun et al. "Spectral Representation for Causal Estimation with Hidden Confounders." Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, 2025.](https://mlanthology.org/aistats/2025/sun2025aistats-spectral/)BibTeX
@inproceedings{sun2025aistats-spectral,
title = {{Spectral Representation for Causal Estimation with Hidden Confounders}},
author = {Sun, Haotian and Moulin, Antoine and Ren, Tongzheng and Gretton, Arthur and Dai, Bo},
booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics},
year = {2025},
pages = {2719-2727},
volume = {258},
url = {https://mlanthology.org/aistats/2025/sun2025aistats-spectral/}
}