TU Darmstadt / ULB / TUprints

Continuous Time Bayesian Networks with Clocks

Engelmann, Nicolai ; Linzner, Dominik ; Koeppl, Heinz (2022):
Continuous Time Bayesian Networks with Clocks. (Publisher's Version)
In: Proceedings of Machine Learning Research, 119, In: Proceedings of the 37th International Conference on Machine Learning, pp. 2912-2921,
Darmstadt, PMLR, 37th International Conference on Machine Learning, Online, 12.-18.07.2020, DOI: 10.26083/tuprints-00021516,
[Conference or Workshop Item]

[img] Text
engelmann20a.pdf
Available under: CC BY 4.0 International - Creative Commons, Attribution.

Download (1MB)
[img] Text (Supplement)
engelmann20a-supp.pdf
Available under: CC BY 4.0 International - Creative Commons, Attribution.

Download (278kB)
Item Type: Conference or Workshop Item
Origin: Secondary publication service
Status: Publisher's Version
Title: Continuous Time Bayesian Networks with Clocks
Language: English
Abstract:

Structured stochastic processes evolving in continuous time present a widely adopted framework to model phenomena occurring in nature and engineering. However, such models are often chosen to satisfy the Markov property to maintain tractability. One of the more popular of such memoryless models are Continuous Time Bayesian Networks (CTBNs). In this work, we lift its restriction to exponential survival times to arbitrary distributions. Current extensions achieve this via auxiliary states, which hinder tractability. To avoid that, we introduce a set of node-wise clocks to construct a collection of graph-coupled semi-Markov chains. We provide algorithms for parameter and structure inference, which make use of local dependencies and conduct experiments on synthetic data and a data-set generated through a benchmark tool for gene regulatory networks. In doing so, we point out advantages compared to current CTBN extensions.

Book Title: Proceedings of the 37th International Conference on Machine Learning
Series: Proceedings of Machine Learning Research
Series Volume: 119
Place of Publication: Darmstadt
Publisher: PMLR
Classification DDC: 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik
600 Technik, Medizin, angewandte Wissenschaften > 620 Ingenieurwissenschaften
Divisions: 18 Department of Electrical Engineering and Information Technology > Institute for Telecommunications > Bioinspired Communication Systems
18 Department of Electrical Engineering and Information Technology > Self-Organizing Systems Lab
Event Title: 37th International Conference on Machine Learning
Event Location: Online
Event Dates: 12.-18.07.2020
Date Deposited: 20 Jul 2022 13:43
Last Modified: 20 Jul 2022 13:43
DOI: 10.26083/tuprints-00021516
Corresponding Links:
URN: urn:nbn:de:tuda-tuprints-215165
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/21516
PPN:
Export:
Actions (login required)
View Item View Item