D-separation for the strong extension and the main natural extension of a credal network

Andrey G. Bronevich, Igor N. Rozenberg
Proceedings of the Fourteenth International Symposium on Imprecise Probabilities: Theories and Applications, PMLR 290:23-32, 2025.

Abstract

In the paper, we consider two possible extensions of a credal network: the strong extension and the main natural extension. We prove that for both extensions the condition of the $d$-separation is preserved. The proof is based on some properties of conditional independence in such credal networks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v290-bronevich25a, title = {D-separation for the strong extension and the main natural extension of a credal network}, author = {Bronevich, Andrey G. and Rozenberg, Igor N.}, booktitle = {Proceedings of the Fourteenth International Symposium on Imprecise Probabilities: Theories and Applications}, pages = {23--32}, year = {2025}, editor = {Destercke, Sébastien and Erreygers, Alexander and Nendel, Max and Riedel, Frank and Troffaes, Matthias C. M.}, volume = {290}, series = {Proceedings of Machine Learning Research}, month = {15--18 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v290/main/assets/bronevich25a/bronevich25a.pdf}, url = {https://proceedings.mlr.press/v290/bronevich25a.html}, abstract = {In the paper, we consider two possible extensions of a credal network: the strong extension and the main natural extension. We prove that for both extensions the condition of the $d$-separation is preserved. The proof is based on some properties of conditional independence in such credal networks.} }
Endnote
%0 Conference Paper %T D-separation for the strong extension and the main natural extension of a credal network %A Andrey G. Bronevich %A Igor N. Rozenberg %B Proceedings of the Fourteenth International Symposium on Imprecise Probabilities: Theories and Applications %C Proceedings of Machine Learning Research %D 2025 %E Sébastien Destercke %E Alexander Erreygers %E Max Nendel %E Frank Riedel %E Matthias C. M. Troffaes %F pmlr-v290-bronevich25a %I PMLR %P 23--32 %U https://proceedings.mlr.press/v290/bronevich25a.html %V 290 %X In the paper, we consider two possible extensions of a credal network: the strong extension and the main natural extension. We prove that for both extensions the condition of the $d$-separation is preserved. The proof is based on some properties of conditional independence in such credal networks.
APA
Bronevich, A.G. & Rozenberg, I.N.. (2025). D-separation for the strong extension and the main natural extension of a credal network. Proceedings of the Fourteenth International Symposium on Imprecise Probabilities: Theories and Applications, in Proceedings of Machine Learning Research 290:23-32 Available from https://proceedings.mlr.press/v290/bronevich25a.html.

Related Material