Disintegration and Bayesian inversion via string diagrams
From MaRDI portal
(Redirected from Publication:5243152)
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.
Recommendations
Cites work
- scientific article; zbMATH DE number 3764843 (Why is no real title available?)
- scientific article; zbMATH DE number 48812 (Why is no real title available?)
- scientific article; zbMATH DE number 1216133 (Why is no real title available?)
- scientific article; zbMATH DE number 1082253 (Why is no real title available?)
- scientific article; zbMATH DE number 1782877 (Why is no real title available?)
- scientific article; zbMATH DE number 1432028 (Why is no real title available?)
- A categorical foundation for Bayesian probability
- A formal semantics of influence in Bayesian reasoning
- A predicate/state transformer semantics for Bayesian learning
- A survey of graphical languages for monoidal categories
- A user's guide to measure theoretic probability
- An effect-theoretic account of Lebesgue integration
- Bayesian reasoning and machine learning.
- Categorical quantum mechanics
- Category-theoretic structure for independence and conditional independence
- Commutative semantics for probabilistic programming
- Conditioning as disintegration
- Disintegration and compact measures.
- Exact Bayesian inference by symbolic disintegration
- From probability monads to commutative effectuses
- Identifying independence in bayesian networks
- Labelled Markov processes.
- Measure transformer semantics for Bayesian machine learning
- New directions in categorical logic, for classical, probabilistic and quantum logic
- Picturing quantum processes. A first course in quantum theory and diagrammatic reasoning
- Pointless learning
- Quantum theory from first principles. An informational approach
- Random measures, theory and applications
- Scalars, monads and categories
- Semantics for probabilistic programming: higher-order functions, continuous distributions, and soft constraints
- Separoids: a mathematical framework for conditional independence and irrelevance
- States of convex sets
- Stochastic Relations
- Terminality implies no-signalling\dots and much more than that
- The EfProb library for probabilistic calculations
- The Logical Essentials of Bayesian Reasoning
- The existence of regular conditional probabilities: Necessary and sufficient conditions
- The geometry of tensor calculus. I
- Understanding probabilistic programs
Cited in
(59)- Overdrawing urns using categories of signed probabilities
- Approximate inference via fibrations of statistical games
- String diagrams with factorized densities
- Constructor theory as process theory
- Stick breaking, in coalgebra and probability
- Monoidal Width: Capturing Rank Width
- Open Dynamical Systems as Coalgebras for Polynomial Functors, with Application to Predictive Processing
- Causal inference via string diagram surgery. A diagrammatic approach to interventions and counterfactuals
- scientific article; zbMATH DE number 7199585 (Why is no real title available?)
- Representable Markov categories and comparison of statistical experiments in categorical probability
- A non-commutative Bayes' theorem
- Monoidal Width
- Weak and TV consistency in Bayesian uncertainty quantification using disintegration
- A categorical construction of the real unit interval
- Polynomial life: the structure of adaptive systems
- Some probabilistic riddles and some logical solutions
- Probabilistic programming with exact conditions
- Categorical information geometry
- A category-theoretic proof of the ergodic decomposition theorem
- Multisets and distributions, in drawing and learning
- Structure in machine learning
- A model of stochastic memoization and name generation in probabilistic programming: categorical semantics via monads on presheaf categories
- Pearl's and Jeffrey's update as modes of learning in probabilistic programming
- Sufficient statistics and split idempotents in discrete probability theory
- Free gs-monoidal categories and free Markov categories
- Graphical quadratic algebra
- Boundary disintegration for weighted residual energy trees
- Independent states are orthogonal: a categorical framework to treat probability geometrically
- Categories of abstract and noncommutative measurable spaces
- 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
- The produoidal algebra of process decomposition
- 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
- The Aldous-Hoover theorem in categorical probability
- Bayesian inversion and the Tomita–Takesaki modular group
- Empirical measures and strong laws of large numbers in categorical probability
- A categorical approach to DIBI models
- 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
- Classical linear logic in perfect Banach lattices
- A categorical semantics of fuzzy concepts in conceptual spaces
- A channel-based perspective on conjugate priors
- scientific article; zbMATH DE number 7350768 (Why is no real title available?)
- Picturing classical and quantum Bayesian inference
- De Finetti's theorem in categorical probability
- Coinductive streams in monoidal categories
- A categorical treatment of open linear systems
- DisCoPy: monoidal categories in Python
- Cyber kittens, or some first steps towards categorical cybernetics
- mathlib4 Module Mathlib/CategoryTheory/CopyDiscardCategory/Basic
- mathlib4 Module Mathlib/CategoryTheory/MarkovCategory/Basic
- Identification of causal influences in quantum processes
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)
