Large-Sample Learning of Bayesian Networks is NP-Hard
Abstract
In this paper, we provide new complexity results for algorithms that learn discrete-variable Bayesian networks from data. Our results apply whenever the learning algorithm uses a scoring criterion that favors the simplest model able to represent the generative distribution exactly. Our results therefore hold whenever the learning algorithm uses a consistent scoring criterion and is applied to a sufficiently large dataset. We show that identifying high-scoring structures is hard, even when we are given an independence oracle, an inference oracle, and/or an information oracle. Our negative results also apply to the learning of discrete-variable Bayesian networks in which each node has at most k parents, for all k > 3.
Cite
@article{arxiv.1212.2468,
title = {Large-Sample Learning of Bayesian Networks is NP-Hard},
author = {David Maxwell Chickering and Christopher Meek and David Heckerman},
journal= {arXiv preprint arXiv:1212.2468},
year = {2012}
}
Comments
Appears in Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence (UAI2003)