Latent Tree Models and Approximate Inference in Bayesian Networks
Abstract
We propose a novel method for approximate inference in Bayesian networks (BNs). The idea is to sample data from a BN, learn a latent tree model (LTM) from the data offline, and when online, make inference with the LTM instead of the original BN. Because LTMs are tree-structured, inference takes linear time. In the meantime, they can represent complex relationship among leaf nodes and hence the approximation accuracy is often good. Empirical evidence shows that our method can achieve good approximation accuracy at low online computational cost.
Cite
Text
Wang et al. "Latent Tree Models and Approximate Inference in Bayesian Networks." Journal of Artificial Intelligence Research, 2008. doi:10.1613/JAIR.2530Markdown
[Wang et al. "Latent Tree Models and Approximate Inference in Bayesian Networks." Journal of Artificial Intelligence Research, 2008.](https://mlanthology.org/jair/2008/wang2008jair-latent/) doi:10.1613/JAIR.2530BibTeX
@article{wang2008jair-latent,
title = {{Latent Tree Models and Approximate Inference in Bayesian Networks}},
author = {Wang, Yi and Zhang, Nevin Lianwen and Chen, Tao},
journal = {Journal of Artificial Intelligence Research},
year = {2008},
pages = {879-900},
doi = {10.1613/JAIR.2530},
volume = {32},
url = {https://mlanthology.org/jair/2008/wang2008jair-latent/}
}