NeurIPS 2021poster9 citations
Learning Fast-Inference Bayesian Networks
Vaidyanathan Peruvemba Ramaswamy, Stefan Szeider
Abstract
We propose new methods for learning Bayesian networks (BNs) that reliably support fast inference. We utilize maximum state space size as a more fine-grained measure for the BN's reasoning complexity than the standard treewidth measure, thereby accommodating the possibility that variables range over domains of different sizes. Our methods combine heuristic BN structure learning algorithms with the recently introduced MaxSAT-powered local improvement method (Peruvemba Ramaswamy and Szeider, AAAI'21). Our experiments show that our new learning methods produce BNs that support significantly faster exact probabilistic inference than BNs learned with treewidth bounds.
Bayesian Network Structure LearningExact Probabilistic ReasoningMaxSATPropositional Satisfiability
BibTeX
@inproceedings{
ramaswamy2021learning,
title={Learning Fast-Inference Bayesian Networks},
author={Vaidyanathan Peruvemba Ramaswamy and Stefan Szeider},
booktitle={Advances in Neural Information Processing Systems},
editor={A. Beygelzimer and Y. Dauphin and P. Liang and J. Wortman Vaughan},
year={2021},
url={https://openreview.net/forum?id=UmCsy3C4xj}
}