English

Entropy, Information, and the Updating of Probabilities

Data Analysis, Statistics and Probability 2021-08-04 v1 Artificial Intelligence Methodology

Abstract

This paper is a review of a particular approach to the method of maximum entropy as a general framework for inference. The discussion emphasizes the pragmatic elements in the derivation. An epistemic notion of information is defined in terms of its relation to the Bayesian beliefs of ideally rational agents. The method of updating from a prior to a posterior probability distribution is designed through an eliminative induction process. The logarithmic relative entropy is singled out as the unique tool for updating that (a) is of universal applicability; (b) that recognizes the value of prior information; and (c) that recognizes the privileged role played by the notion of independence in science. The resulting framework -- the ME method -- can handle arbitrary priors and arbitrary constraints. It includes MaxEnt and Bayes' rule as special cases and, therefore, it unifies entropic and Bayesian methods into a single general inference scheme. The ME method goes beyond the mere selection of a single posterior, but also addresses the question of how much less probable other distributions might be, which provides a direct bridge to the theories of fluctuations and large deviations.

Keywords

Cite

@article{arxiv.2107.04529,
  title  = {Entropy, Information, and the Updating of Probabilities},
  author = {Ariel Caticha},
  journal= {arXiv preprint arXiv:2107.04529},
  year   = {2021}
}

Comments

28 pages. Invited paper to appear in Entropy in the special volume "Statistical Foundations of Entropy", ed. by P. Jizba and J. Korbel. arXiv admin note: text overlap with arXiv:1412.5644