Identifying Confounders Using Additive Noise Models
Abstract
We propose a method for inferring the existence of a latent common cause ("confounder") of two observed random variables. The method assumes that the two effects of the confounder are (possibly nonlinear) functions of the confounder plus independent, additive noise. We discuss under which conditions the model is identifiable (up to an arbitrary reparameterization of the confounder) from the joint distribution of the effects. We state and prove a theoretical result that provides evidence for the conjecture that the model is generically identifiable under suitable technical conditions. In addition, we propose a practical method to estimate the confounder from a finite i.i.d. sample of the effects and illustrate that the method works well on both simulated and real-world data.
Cite
Text
Janzing et al. "Identifying Confounders Using Additive Noise Models." Conference on Uncertainty in Artificial Intelligence, 2009.Markdown
[Janzing et al. "Identifying Confounders Using Additive Noise Models." Conference on Uncertainty in Artificial Intelligence, 2009.](https://mlanthology.org/uai/2009/janzing2009uai-identifying/)BibTeX
@inproceedings{janzing2009uai-identifying,
title = {{Identifying Confounders Using Additive Noise Models}},
author = {Janzing, Dominik and Peters, Jonas and Mooij, Joris M. and Schölkopf, Bernhard},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {2009},
pages = {249-257},
url = {https://mlanthology.org/uai/2009/janzing2009uai-identifying/}
}