Creative Commons Attribution 3.0 Unported license (CC-BY 3.0)when quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.MFCS.2017.21
URN: urn:nbn:de:0030-drops-80896
URL: https://drops.dagstuhl.de/opus/volltexte/2017/8089/
Jacobs, Bart ; Zanasi, Fabio
A Formal Semantics of Influence in Bayesian Reasoning
| pdf-format: |
|
Abstract
This paper proposes a formal definition of influence in Bayesian reasoning, based on the notions of state (as probability distribution), predicate, validity and conditioning. Our approach highlights how conditioning a joint entwined/entangled state with a predicate on one of its components has 'crossover' influence on the other components. We use the total variation metric on probabilitydistributions to quantitatively measure such influence. These insights are applied to give a rigorous explanation of the fundamental concept of d-separation in Bayesian networks.
BibTeX - Entry
@InProceedings{jacobs_et_al:LIPIcs:2017:8089,
author = {Bart Jacobs and Fabio Zanasi},
title = {{A Formal Semantics of Influence in Bayesian Reasoning}},
booktitle = {42nd International Symposium on Mathematical Foundations of Computer Science (MFCS 2017)},
pages = {21:1--21:14},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {978-3-95977-046-0},
ISSN = {1868-8969},
year = {2017},
volume = {83},
editor = {Kim G. Larsen and Hans L. Bodlaender and Jean-Francois Raskin},
publisher = {Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
address = {Dagstuhl, Germany},
URL = {http://drops.dagstuhl.de/opus/volltexte/2017/8089},
URN = {urn:nbn:de:0030-drops-80896},
doi = {10.4230/LIPIcs.MFCS.2017.21},
annote = {Keywords: probability distribution, Bayesian network, influence}
}
| Keywords: | probability distribution, Bayesian network, influence | |
| Seminar: | 42nd International Symposium on Mathematical Foundations of Computer Science (MFCS 2017) | |
| Issue date: | 2017 | |
| Date of publication: | 01.12.2017 |
