License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.MFCS.2023.24
URN: urn:nbn:de:0030-drops-185584
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2023/18558/
Go to the corresponding LIPIcs Volume Portal

Braithwaite, Dylan ; Hedges, Jules ; St Clere Smithe, Toby

The Compositional Structure of Bayesian Inference

pdf-format:
LIPIcs-MFCS-2023-24.pdf (0.7 MB)

Abstract

Bayes' rule tells us how to invert a causal process in order to update our beliefs in light of new evidence. If the process is believed to have a complex compositional structure, we may observe that the inversion of the whole can be computed piecewise in terms of the component processes. We study the structure of this compositional rule, noting that it relates to the lens pattern in functional programming. Working in a suitably general axiomatic presentation of a category of Markov kernels, we see how we can think of Bayesian inversion as a particular instance of a state-dependent morphism in a fibred category. We discuss the compositional nature of this, formulated as a functor on the underlying category and explore how this can used for a more type-driven approach to statistical inference.

BibTeX - Entry

@InProceedings{braithwaite_et_al:LIPIcs.MFCS.2023.24,
  author =	{Braithwaite, Dylan and Hedges, Jules and St Clere Smithe, Toby},
  title =	{{The Compositional Structure of Bayesian Inference}},
  booktitle =	{48th International Symposium on Mathematical Foundations of Computer Science (MFCS 2023)},
  pages =	{24:1--24:15},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-292-1},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{272},
  editor =	{Leroux, J\'{e}r\^{o}me and Lombardy, Sylvain and Peleg, David},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2023/18558},
  URN =		{urn:nbn:de:0030-drops-185584},
  doi =		{10.4230/LIPIcs.MFCS.2023.24},
  annote =	{Keywords: monoidal categories, probabilistic programming, Bayesian inference}
}

Keywords: monoidal categories, probabilistic programming, Bayesian inference
Collection: 48th International Symposium on Mathematical Foundations of Computer Science (MFCS 2023)
Issue Date: 2023
Date of publication: 21.08.2023

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI