Disintegration and Bayesian Inversion via String Diagrams

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.

Accepted for publication in Mathematical Structures in Computer Science

References in corpus (1)

• Causal Networks: Semantics and Expressiveness

Cited by in corpus (56)

• A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statistics
• DisCoPy: Monoidal Categories in Python
• Axioms for retrodiction: achieving time-reversal symmetry with a prior
• Representable Markov Categories and Comparison of Statistical Experiments in Categorical Probability
• On quantum states over time
• A non-commutative Bayes' theorem
• Infinite products and zero-one laws in categorical probability
• Free gs-monoidal categories and free Markov categories
• Bayesian Updates Compose Optically
• Dilations and information flow axioms in categorical probability
• A category-theoretic proof of the ergodic decomposition theorem
• Supplying bells and whistles in symmetric monoidal categories
• Markov Categories and Entropy
• The information loss of a stochastic map
• Probabilistic morphisms and Bayesian nonparametrics
• Inverses, disintegrations, and Bayesian inversion in quantum Markov categories
• Category Theory in Machine Learning
• Bayesian inversion and the Tomita-Takesaki modular group
• A functorial characterization of von Neumann entropy
• Non-commutative disintegrations: existence and uniqueness in finite dimensions
• Learning from What's Right and Learning from What's Wrong
• Probability monads with submonads of deterministic states - Extended version
• Categorical Stochastic Processes and Likelihood
• The algebra and machine representation of statistical models
• Effectuses in Categorical Quantum Foundations
• A Categorical Semantics of Fuzzy Concepts in Conceptual Spaces
• Cyber Kittens, or Some First Steps Towards Categorical Cybernetics
• Conditional Distributions for Quantum Systems
• Open Dynamical Systems as Coalgebras for Polynomial Functors, with Application to Predictive Processing
• Complete extension: the non-signaling analog of quantum purification
• Polynomial Life: the Structure of Adaptive Systems
• Hidden Markov Models and the Bayes Filter in Categorical Probability
• Monoidal Width
• Sufficient Statistics and Split Idempotents in Discrete Probability Theory
• From Gs-monoidal to Oplax Cartesian Categories: Constructions and Functorial Completeness
• A category theory framework for Bayesian learning
• A Categorical Construction of the Real Unit Interval
• On a 2-relative entropy
• A model of stochastic memoization and name generation in probabilistic programming: categorical semantics via monads on presheaf categories
• Compositional Semantics for Probabilistic Programs with Exact Conditioning
• Pearl's and Jeffrey's Update as Modes of Learning in Probabilistic Programming
• Coalgebraic Semantics for Probabilistic Logic Programming
• Overdrawing Urns using Categories of Signed Probabilities
• Constructor Theory as Process Theory
• Bipartite quantum states admitting a causal explanation
• String Diagrams with Factorized Densities
• Functors induced by comma categories
• Combs, Causality and Contractions in Atomic Markov Categories
• Approximate Inference via Fibrations of Statistical Games
• Quasi-Measurable Spaces: A Convenient Foundation of Probability Theory
• The Aldous$\unicode{x2013}$Hoover Theorem in Categorical Probability
• A decompositional framework for process theories in spacetime
• Categorical algebra of conditional probability
• Categories of abstract and noncommutative measurable spaces
• Monoidal Width: Capturing Rank Width
• Identification of Causal Influences in Quantum Processes