Probabilistic Reasoning with Inconsistent Beliefs Using Inconsistency Measures
Abstract
The classical probabilistic entailment problem is to determine upper and lower bounds on the probability of formulas, given a consistent set of probabilistic assertions. We generalize this problem by omitting the consistency assumption and, thus, provide a general framework for probabilistic reasoning under inconsistency. To do so, we utilize inconsistency measures to determine probability functions that are closest to satisfying the knowledge base. We illustrate our approach on several examples and show that it has both nice formal and computational properties.
Cite
Text
Potyka and Thimm. "Probabilistic Reasoning with Inconsistent Beliefs Using Inconsistency Measures." International Joint Conference on Artificial Intelligence, 2015.Markdown
[Potyka and Thimm. "Probabilistic Reasoning with Inconsistent Beliefs Using Inconsistency Measures." International Joint Conference on Artificial Intelligence, 2015.](https://mlanthology.org/ijcai/2015/potyka2015ijcai-probabilistic/)BibTeX
@inproceedings{potyka2015ijcai-probabilistic,
title = {{Probabilistic Reasoning with Inconsistent Beliefs Using Inconsistency Measures}},
author = {Potyka, Nico and Thimm, Matthias},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2015},
pages = {3156-3163},
url = {https://mlanthology.org/ijcai/2015/potyka2015ijcai-probabilistic/}
}