On theoretical properties of sum-product networks
METADATA ONLY
Loading...
Author / Producer
Date
2015
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
METADATA ONLY
Data
Rights / License
Abstract
Sum-product networks (SPNs) are a promising avenue for probabilistic modeling and have been successfully applied to various tasks. However, some theoretic properties about SPNs are not yet well understood. In this paper we fill some gaps in the theoretic foundation of SPNs. First, we show that the weights of any complete and consistent SPN can be transformed into locally normalized weights without changing the SPN distribution. Second, we show that consistent SPNs cannot model distributions significantly (exponentially) more compactly than decomposable SPNs. As a third contribution, we extend the inference mechanisms known for SPNs with finite states to generalized SPNs with arbitrary input distributions.
Permanent link
Publication status
published
Book title
Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics
Journal / series
Volume
38
Pages / Article No.
744 - 752
Publisher
PMLR
Event
18th International Conference on Artificial Intelligence and Statistics (AISTATS 2015)