A categorical foundation for Bayesian probability
From MaRDI portal
Abstract: Given two measurable spaces and with countably generated -algebras, a perfect prior probability measure on and a sampling distribution , there is a corresponding inference map which is unique up to a set of measure zero. Thus, given a data measurement , a posterior probability can be computed. This procedure is iterative: with each updated probability , we obtain a new joint distribution which in turn yields a new inference map and the process repeats with each additional measurement. The main result uses an existence theorem for regular conditional probabilities by Faden, which holds in more generality than the setting of Polish spaces. This less stringent setting then allows for non-trivial decision rules (Eilenberg--Moore algebras) on finite (as well as non finite) spaces, and also provides for a common framework for decision theory and Bayesian probability.
Recommendations
- A categorical approach to probability theory
- Categorical probabilistic theories
- Towards a categorical account of conditional probability
- Fruits of a categorical approach to probability theory
- A Convenient Category for Higher-Order Probability Theory
- scientific article; zbMATH DE number 1746710
- Foundations of Bayesian theory
- Categorical Stochastic Processes and Likelihood
- Foundations of Bayesianism
- A note on probability metrics in a categorical setting
Cites work
- scientific article; zbMATH DE number 3761167 (Why is no real title available?)
- scientific article; zbMATH DE number 720878 (Why is no real title available?)
- scientific article; zbMATH DE number 2222246 (Why is no real title available?)
- Commutative monads as a theory of distributions
- Disintegration and compact measures.
- Kleisli morphisms and randomized congruences for the Giry monad
- Nuclear and trace ideals in tensored \(^*\)-categories
- Optimal transportation with capacity constraints
- Perfect Probability Measures and Regular Conditional Probabilities
- Perfect mixtures of perfect measures
- Probability Theory
- Real Analysis and Probability
- Statistical decision theory and Bayesian analysis. 2nd ed
- The existence of regular conditional probabilities: Necessary and sufficient conditions
Cited in
(18)- Pointless learning
- A Convenient Category for Higher-Order Probability Theory
- Quantum GestART: identifying and applying correlations between mathematics, art, and perceptual organization
- The factorization of the Giry monad
- A non-commutative Bayes' theorem
- scientific article; zbMATH DE number 7052238 (Why is no real title available?)
- Weak and TV consistency in Bayesian uncertainty quantification using disintegration
- Categorical Stochastic Processes and Likelihood
- Giry and the Machine
- Belief propagation in monoidal categories
- Infinite products and zero-one laws in categorical probability
- Categorical approach to modelling and to coupling of models
- A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statistics
- From probability monads to commutative effectuses
- Conditional distributions for quantum systems
- Multinomial and hypergeometric distributions in Markov categories
- A channel-based perspective on conjugate priors
- Disintegration and Bayesian inversion via string diagrams
This page was built for publication: A categorical foundation for Bayesian probability
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q742929)