A Kernel-Based Causal Learning Algorithm
Abstract
We describe a causal learning method, which employs measuring the strength of statistical dependences in terms of the Hilbert-Schmidt norm of kernel-based cross-covariance operators. Following the line of the common faithfulness assumption of constraint-based causal learning, our approach assumes that a variable Z is likely to be a common effect of X and Y , if conditioning on Z increases the dependence between X and Y . Based on this assumption, we collect "votes" for hypothetical causal directions and orient the edges by the majority principle. In most experiments with known causal structures, our method provided plausible results and outperformed the conventional constraint-based PC algorithm.
Cite
Text
Sun et al. "A Kernel-Based Causal Learning Algorithm." International Conference on Machine Learning, 2007. doi:10.1145/1273496.1273604Markdown
[Sun et al. "A Kernel-Based Causal Learning Algorithm." International Conference on Machine Learning, 2007.](https://mlanthology.org/icml/2007/sun2007icml-kernel/) doi:10.1145/1273496.1273604BibTeX
@inproceedings{sun2007icml-kernel,
title = {{A Kernel-Based Causal Learning Algorithm}},
author = {Sun, Xiaohai and Janzing, Dominik and Schölkopf, Bernhard and Fukumizu, Kenji},
booktitle = {International Conference on Machine Learning},
year = {2007},
pages = {855-862},
doi = {10.1145/1273496.1273604},
url = {https://mlanthology.org/icml/2007/sun2007icml-kernel/}
}