Conditional probability estimation

Cattaneo, Marco

Abstract

This paper studies in particular an aspect of the estimation of conditional probability distributions by maximum likelihood that seems to have been overlooked in the literature on Bayesian networks: The information conveyed by the conditioning event should be included in the likelihood function as well.

Citation

Cattaneo, M. (2016). Conditional probability estimation. Proceedings of Machine Learning Research, 52, 86-97

• Journal Article Type: Article
• Acceptance Date: May 1, 2016
• Publication Date: 2016-08
• Deposit Date: Aug 19, 2016
• Publicly Available Date: Aug 31, 2016
• Journal: JMLR : workshop and conference proceedings
• Print ISSN: 2640-3498
• Peer Reviewed: Peer Reviewed
• Volume: 52
• Pages: 86-97
• Keywords: Bayesian networks, Maximum likelihood, Conditional probabilities
• Public URL: https://hull-repository.worktribe.com/output/442248
• Publisher URL: http://www.jmlr.org/proceedings/papers/v52/cattaneo16.html
• Additional Information: This is a copy of a paper published in: JMLR : workshop and conference proceedings, 2016, v.52. Originally presented at Proceedings of the Eighth International Conference on Probabilistic Graphical Models.