The generalized IFS Bayesian method and an associated variational principle covering the classical and dynamical cases

DOI10.1080/14689367.2023.2257609arXiv2212.01147OpenAlexW4386819992MaRDI QIDQ6419331FDOQ6419331

A. O. Lopes, J. Mengue

Publication date: 2 December 2022

Abstract: We introduce a general IFS Bayesian method for getting posterior probabilities from prior probabilities, and also a generalized Bayes' rule, which will contemplate a dynamical, as well as a non dynamical setting. Given a loss function $l$, we detail the prior and posterior items, their consequences and exhibit several examples. Taking $Theta$ as the set of parameters and $Y$ as the set of data (which usually provides {random samples}), a general IFS is a measurable map $au:ThetaimesYoY$, which can be interpreted as a family of maps $a{u}_{h}eta:YoY,,hetainTheta$. The main inspiration for the results we will get here comes from a paper by Zellner (with no dynamics), where Bayes' rule is related to a principle of minimization of {information.} We will show that our IFS Bayesian method which produces posterior probabilities (which are associated to holonomic probabilities) is related to the optimal solution of a variational principle, somehow corresponding to the pressure in Thermodynamic Formalism, and also to the principle of minimization of information in Information Theory.

Full work available at URL: https://doi.org/10.1080/14689367.2023.2257609

Mathematics Subject Classification ID

Dynamical systems and ergodic theory (37-XX)

Cited In (1)

• Level-2 IFS thermodynamic formalism: Gibbs probabilities in the space of probabilities and the push-forward map

This page was built for publication: The generalized IFS Bayesian method and an associated variational principle covering the classical and dynamical cases

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6419331)