Disintegration and Bayesian inversion via string diagrams

DOI10.1017/S0960129518000488zbMATH Open1452.18008arXiv1709.00322OpenAlexW2949602009WikidataQ128221956 ScholiaQ128221956MaRDI QIDQ5243152FDOQ5243152

Kenta Cho, Bart Jacobs

Publication date: 15 November 2019

Published in: Mathematical Structures in Computer Science (Search for Journal in Brave)

Abstract: The notions of disintegration and Bayesian inversion are fundamental in conditional probability theory. They produce channels, as conditional probabilities, from a joint state, or from an already given channel (in opposite direction). These notions exist in the literature, in concrete situations, but are presented here in abstract graphical formulations. The resulting abstract descriptions are used for proving basic results in conditional probability theory. The existence of disintegration and Bayesian inversion is discussed for discrete probability, and also for measure-theoretic probability --- via standard Borel spaces and via likelihoods. Finally, the usefulness of disintegration and Bayesian inversion is illustrated in several examples.

Full work available at URL: https://arxiv.org/abs/1709.00322

Recommendations

• Conditioning as disintegration
• Towards a categorical account of conditional probability
• Picturing classical and quantum Bayesian inference
• A non-commutative Bayes' theorem
• A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statistics

zbMATH Keywords

disintegrationconditional probabilitymonoidal categorystring diagram

Mathematics Subject Classification ID

Bayesian problems; characterization of Bayes procedures (62C10) Monads (= standard construction, triple or triad), algebras for monads, homology and derived functors for monads (18C15) Integration and disintegration of measures (28A50)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Identifying independence in bayesian networks
• Title not available (Why is that?)
• The geometry of tensor calculus. I
• Categorical quantum mechanics
• A Survey of Graphical Languages for Monoidal Categories
• Title not available (Why is that?)
• Title not available (Why is that?)
• Conditioning as disintegration
• Labelled Markov processes.
• Stochastic Relations
• A user's guide to measure theoretic probability
• Quantum Theory from First Principles
• New Directions in Categorical Logic, for Classical, Probabilistic and Quantum Logic
• States of Convex Sets
• Separoids: a mathematical framework for conditional independence and irrelevance
• The existence of regular conditional probabilities: Necessary and sufficient conditions
• Bayesian Reasoning and Machine Learning
• Title not available (Why is that?)
• The Logical Essentials of Bayesian Reasoning
• Disintegration and compact measures.
• A categorical foundation for Bayesian probability
• Random Measures, Theory and Applications
• Understanding Probabilistic Programs
• Category-theoretic structure for independence and conditional independence
• A predicate/state transformer semantics for Bayesian learning
• Picturing Quantum Processes
• Terminality implies no-signalling\dots and much more than that
• From probability monads to commutative effectuses
• Semantics for probabilistic programming
• Scalars, Monads, and Categories
• Measure transformer semantics for Bayesian machine learning
• An effect-theoretic account of Lebesgue integration
• The EfProb Library for Probabilistic Calculations
• Exact Bayesian inference by symbolic disintegration
• Pointless Learning
• Commutative Semantics for Probabilistic Programming
• A Formal Semantics of Influence in Bayesian Reasoning

Cited In (32)

• Stick breaking, in coalgebra and probability
• Monoidal Width: Capturing Rank Width
• Open Dynamical Systems as Coalgebras for Polynomial Functors, with Application to Predictive Processing
• Representable Markov categories and comparison of statistical experiments in categorical probability
• Title not available (Why is that?)
• Monoidal Width
• A non-commutative Bayes' theorem
• Weak and TV consistency in Bayesian uncertainty quantification using disintegration
• Title not available (Why is that?)
• Categorical information geometry
• Multisets and distributions, in drawing and learning
• Structure in machine learning
• A category-theoretic proof of the ergodic decomposition theorem
• Free gs-monoidal categories and free Markov categories
• DisCoPy: Monoidal Categories in Python
• Cyber Kittens, or Some First Steps Towards Categorical Cybernetics
• A principled approach to expectation maximisation and latent Dirichlet allocation using Jeffrey's update rule
• From gs-monoidal to oplax cartesian categories: constructions and functorial completeness
• Non-commutative disintegrations: existence and uniqueness in finite dimensions
• Towards a compositional framework for convex analysis (with applications to probability theory)
• Disintegration of Gaussian measures for sequential assimilation of linear operator data
• A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statistics
• Conditional distributions for quantum systems
• Partitions and Ewens distributions in element-free probability theory
• Monoidal streams for dataflow programming
• Probability monads with submonads of deterministic states
• Learning from what's right and learning from what's wrong
• Multinomial and hypergeometric distributions in Markov categories
• Causal inference via string diagram surgery
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)

Uses Software

• Separoids
• EfProb

This page was built for publication: Disintegration and Bayesian inversion via string diagrams

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5243152)