Partition function approach to non-Gaussian likelihoods: information theory and state variables for Bayesian inference
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909526565847040 |
|---|---|
| author | Kuntz, Rebecca Maria von Campe, Heinrich Röspel, Tobias Herzog, Maximilian Philipp Schäfer, Björn Malte |
| author_facet | Kuntz, Rebecca Maria von Campe, Heinrich Röspel, Tobias Herzog, Maximilian Philipp Schäfer, Björn Malte |
| contents | 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 | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_13625 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Partition function approach to non-Gaussian likelihoods: information theory and state variables for Bayesian inference Kuntz, Rebecca Maria von Campe, Heinrich Röspel, Tobias Herzog, Maximilian Philipp Schäfer, Björn Malte Statistical Mechanics Cosmology and Nongalactic Astrophysics Information Theory 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. |
| title | Partition function approach to non-Gaussian likelihoods: information theory and state variables for Bayesian inference |
| topic | Statistical Mechanics Cosmology and Nongalactic Astrophysics Information Theory |
| url | https://arxiv.org/abs/2411.13625 |