Probabilistic Belief Revision with Structural Constraints
Abstract
Experts (human or computer) are often required to assess the probability of uncertain events. When a collection of experts independently assess events that are structurally interrelated, the resulting assessment may violate fundamental laws of probability. Such an assessment is termed incoherent. In this work we investigate how the problem of incoherence may be affected by allowing experts to specify likelihood models and then update their assessments based on the realization of a globally-observable random sequence.
Cite
Text
Jones et al. "Probabilistic Belief Revision with Structural Constraints." Neural Information Processing Systems, 2010.Markdown
[Jones et al. "Probabilistic Belief Revision with Structural Constraints." Neural Information Processing Systems, 2010.](https://mlanthology.org/neurips/2010/jones2010neurips-probabilistic/)BibTeX
@inproceedings{jones2010neurips-probabilistic,
title = {{Probabilistic Belief Revision with Structural Constraints}},
author = {Jones, Peter and Saligrama, Venkatesh and Mitter, Sanjoy},
booktitle = {Neural Information Processing Systems},
year = {2010},
pages = {1036-1044},
url = {https://mlanthology.org/neurips/2010/jones2010neurips-probabilistic/}
}