Partition function approach to non-Gaussian likelihoods: information theory and state variables for Bayesian inference

The significance of statistical physics concepts such as entropy extends far beyond classical thermodynamics. We interpret the similarity between partitions in statistical mechanics and partitions in Bayesian inference as an articulation of a result by Jaynes (1957), who clarified that thermodynamic...

Full description

Saved in:
Bibliographic Details
Main Authors: Rebecca Maria Kuntz, Heinrich von Campe, Tobias Röspel, Maximilian Philipp Herzog, Björn Malte Schäfer
Format: Article
Language:English
Published: Maynooth Academic Publishing 2025-03-01
Series:The Open Journal of Astrophysics
Online Access:https://doi.org/10.33232/001c.131858
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849414758407602176
author Rebecca Maria Kuntz
Heinrich von Campe
Tobias Röspel
Maximilian Philipp Herzog
Björn Malte Schäfer
author_facet Rebecca Maria Kuntz
Heinrich von Campe
Tobias Röspel
Maximilian Philipp Herzog
Björn Malte Schäfer
author_sort Rebecca Maria Kuntz
collection DOAJ
description The significance of statistical physics concepts such as entropy extends far beyond classical thermodynamics. We interpret the similarity between partitions in statistical mechanics and partitions in Bayesian inference as an articulation of a result by Jaynes (1957), who clarified that thermodynamics is in essence a theory of information. In this, every sampling process has a mechanical analogue. Consequently, the divide between ensembles of samplers in parameter space and sampling from a mechanical system in thermodynamic equilibrium would be artificial. Based on this realisation, we construct a continuous modelling of a Bayes update akin to a transition between thermodynamic ensembles. This leads to an information theoretic interpretation of Jazinsky's equality, relating the expenditure of work to the influence of data via the likelihood. We propose one way to transfer the vocabulary and the formalism of thermodynamics (energy, work, heat) and statistical mechanics (partition functions) to statistical inference, starting from Bayes' law. Different kinds of inference processes are discussed and relative entropies are shown to follow from suitably constructed partitions as an analytical formulation of sampling processes. Lastly, we propose an effective dimension as a measure of system complexity. A numerical example from cosmology is put forward to illustrate these results.
format Article
id doaj-art-8bdf2b1cb97b45cb882f15c5492c66da
institution Kabale University
issn 2565-6120
language English
publishDate 2025-03-01
publisher Maynooth Academic Publishing
record_format Article
series The Open Journal of Astrophysics
spelling doaj-art-8bdf2b1cb97b45cb882f15c5492c66da2025-08-20T03:33:43ZengMaynooth Academic PublishingThe Open Journal of Astrophysics2565-61202025-03-01810.33232/001c.131858Partition function approach to non-Gaussian likelihoods: information theory and state variables for Bayesian inferenceRebecca Maria KuntzHeinrich von CampeTobias RöspelMaximilian Philipp HerzogBjörn Malte SchäferThe significance of statistical physics concepts such as entropy extends far beyond classical thermodynamics. We interpret the similarity between partitions in statistical mechanics and partitions in Bayesian inference as an articulation of a result by Jaynes (1957), who clarified that thermodynamics is in essence a theory of information. In this, every sampling process has a mechanical analogue. Consequently, the divide between ensembles of samplers in parameter space and sampling from a mechanical system in thermodynamic equilibrium would be artificial. Based on this realisation, we construct a continuous modelling of a Bayes update akin to a transition between thermodynamic ensembles. This leads to an information theoretic interpretation of Jazinsky's equality, relating the expenditure of work to the influence of data via the likelihood. We propose one way to transfer the vocabulary and the formalism of thermodynamics (energy, work, heat) and statistical mechanics (partition functions) to statistical inference, starting from Bayes' law. Different kinds of inference processes are discussed and relative entropies are shown to follow from suitably constructed partitions as an analytical formulation of sampling processes. Lastly, we propose an effective dimension as a measure of system complexity. A numerical example from cosmology is put forward to illustrate these results.https://doi.org/10.33232/001c.131858
spellingShingle Rebecca Maria Kuntz
Heinrich von Campe
Tobias Röspel
Maximilian Philipp Herzog
Björn Malte Schäfer
Partition function approach to non-Gaussian likelihoods: information theory and state variables for Bayesian inference
The Open Journal of Astrophysics
title Partition function approach to non-Gaussian likelihoods: information theory and state variables for Bayesian inference
title_full Partition function approach to non-Gaussian likelihoods: information theory and state variables for Bayesian inference
title_fullStr Partition function approach to non-Gaussian likelihoods: information theory and state variables for Bayesian inference
title_full_unstemmed Partition function approach to non-Gaussian likelihoods: information theory and state variables for Bayesian inference
title_short Partition function approach to non-Gaussian likelihoods: information theory and state variables for Bayesian inference
title_sort partition function approach to non gaussian likelihoods information theory and state variables for bayesian inference
url https://doi.org/10.33232/001c.131858
work_keys_str_mv AT rebeccamariakuntz partitionfunctionapproachtonongaussianlikelihoodsinformationtheoryandstatevariablesforbayesianinference
AT heinrichvoncampe partitionfunctionapproachtonongaussianlikelihoodsinformationtheoryandstatevariablesforbayesianinference
AT tobiasrospel partitionfunctionapproachtonongaussianlikelihoodsinformationtheoryandstatevariablesforbayesianinference
AT maximilianphilippherzog partitionfunctionapproachtonongaussianlikelihoodsinformationtheoryandstatevariablesforbayesianinference
AT bjornmalteschafer partitionfunctionapproachtonongaussianlikelihoodsinformationtheoryandstatevariablesforbayesianinference