Tractable Inference for Hybrid Bayesian Networks with NAT-Modeled Dynamic Discretization

Hybrid BNs (HBNs) extend Bayesian networks (BNs) to both discrete and continuous variables. Among inference methods for HBNs, we focus on dynamic discretization (DD) that converts HBN to discrete BN for inference. Complexity of BN inference is exponential on treewidth, which extends to DD for HBNs....

Full description

Saved in:
Bibliographic Details
Main Authors: Yang Xiang, Hanwen Zheng
Format: Article
Language:English
Published: LibraryPress@UF 2022-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Subjects:
Online Access:https://journals.flvc.org/FLAIRS/article/view/130561
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849763353648431104
author Yang Xiang
Hanwen Zheng
author_facet Yang Xiang
Hanwen Zheng
author_sort Yang Xiang
collection DOAJ
description Hybrid BNs (HBNs) extend Bayesian networks (BNs) to both discrete and continuous variables. Among inference methods for HBNs, we focus on dynamic discretization (DD) that converts HBN to discrete BN for inference. Complexity of BN inference is exponential on treewidth, which extends to DD for HBNs. We presents a novel framework where HBN is transformed into NAT-modeled BN (NAT: Non-impeding noisy-AND Tree) for tractable inference. A case-study under the framework is presented on sum of continuous variables. We report significant efficiency gain of approximate inference by NAT-modeled DD over alternative methods.
format Article
id doaj-art-8ece1e15f45c4a96ac09811237a832e0
institution DOAJ
issn 2334-0754
2334-0762
language English
publishDate 2022-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-8ece1e15f45c4a96ac09811237a832e02025-08-20T03:05:26ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622022-05-013510.32473/flairs.v35i.13056166760Tractable Inference for Hybrid Bayesian Networks with NAT-Modeled Dynamic DiscretizationYang Xiang0Hanwen ZhengUniversity of GuelphHybrid BNs (HBNs) extend Bayesian networks (BNs) to both discrete and continuous variables. Among inference methods for HBNs, we focus on dynamic discretization (DD) that converts HBN to discrete BN for inference. Complexity of BN inference is exponential on treewidth, which extends to DD for HBNs. We presents a novel framework where HBN is transformed into NAT-modeled BN (NAT: Non-impeding noisy-AND Tree) for tractable inference. A case-study under the framework is presented on sum of continuous variables. We report significant efficiency gain of approximate inference by NAT-modeled DD over alternative methods.https://journals.flvc.org/FLAIRS/article/view/130561bayesian netscausal independence modelsprobabilistic inferencedynamic discretization
spellingShingle Yang Xiang
Hanwen Zheng
Tractable Inference for Hybrid Bayesian Networks with NAT-Modeled Dynamic Discretization
Proceedings of the International Florida Artificial Intelligence Research Society Conference
bayesian nets
causal independence models
probabilistic inference
dynamic discretization
title Tractable Inference for Hybrid Bayesian Networks with NAT-Modeled Dynamic Discretization
title_full Tractable Inference for Hybrid Bayesian Networks with NAT-Modeled Dynamic Discretization
title_fullStr Tractable Inference for Hybrid Bayesian Networks with NAT-Modeled Dynamic Discretization
title_full_unstemmed Tractable Inference for Hybrid Bayesian Networks with NAT-Modeled Dynamic Discretization
title_short Tractable Inference for Hybrid Bayesian Networks with NAT-Modeled Dynamic Discretization
title_sort tractable inference for hybrid bayesian networks with nat modeled dynamic discretization
topic bayesian nets
causal independence models
probabilistic inference
dynamic discretization
url https://journals.flvc.org/FLAIRS/article/view/130561
work_keys_str_mv AT yangxiang tractableinferenceforhybridbayesiannetworkswithnatmodeleddynamicdiscretization
AT hanwenzheng tractableinferenceforhybridbayesiannetworkswithnatmodeleddynamicdiscretization