A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statistics

DOI10.1016/j.aim.2020.107239zbMath1505.60004arXiv1908.07021OpenAlexW2969875089MaRDI QIDQ2189508

Tobias Fritz

Publication date: 15 June 2020

Published in: Advances in Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1908.07021

zbMATH Keywords

conditional independencesufficient statisticfoundations of statisticsfoundations of probabilityalmost surelymonoidal categories with structure

Mathematics Subject Classification ID

Foundations and philosophical topics in statistics (62A01) Semantics in the theory of computing (68Q55) Monads (= standard construction, triple or triad), algebras for monads, homology and derived functors for monads (18C15) Axioms; other general questions in probability (60A05) Sufficient statistics and fields (62B05) Monoidal categories, symmetric monoidal categories (18M05)

Related Items (27)

A non-commutative Bayes' theorem ⋮ Causal inference via string diagram surgery ⋮ Representable Markov categories and comparison of statistical experiments in categorical probability ⋮ A category-theoretic proof of the ergodic decomposition theorem ⋮ Cyber Kittens, or Some First Steps Towards Categorical Cybernetics ⋮ Monoidal Width ⋮ From gs-monoidal to oplax cartesian categories: constructions and functorial completeness ⋮ Non-commutative disintegrations: existence and uniqueness in finite dimensions ⋮ A higher-order language for Markov kernels and linear operators ⋮ Free gs-monoidal categories and free Markov categories ⋮ A reconstruction of Ewens' sampling formula via lists of coins ⋮ Parametric models and information geometry on \(W^\star\)-algebras ⋮ The groupoidal picture of quantum mechanics ⋮ Weak Cartesian properties of simplicial sets ⋮ Coend Optics for Quantum Combs ⋮ Monoidal Width: Capturing Rank Width ⋮ Open Dynamical Systems as Coalgebras for Polynomial Functors, with Application to Predictive Processing ⋮ Categorical composable cryptography: extended version ⋮ A categorical approach to statistical mechanics ⋮ Categorical information geometry ⋮ Value Iteration is Optic Composition ⋮ A principled approach to expectation maximisation and latent Dirichlet allocation using Jeffrey's update rule ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Categorial independence and Lévy processes ⋮ Stick breaking, in coalgebra and probability

Uses Software

• Separoids

Cites Work

• Causal categories: relativistically interacting processes
• Picturing classical and quantum Bayesian inference
• Matrices, relations, and group representations
• Borel structures for function spaces
• Markov invariant geometry and manifolds of states
• Codensity and the Giry monad
• The existence of regular conditional probabilities: Necessary and sufficient conditions
• Cartesian bicategories. I
• Conditional independence for statistical operations
• A class of fuzzy theories
• The geometry of tensor calculus. I
• Extremal families and systems of sufficient statistics
• Theory of fuzzy sets as a theory of uncertainty and decision-making problems in fuzzy experiments
• Informativity in the category of multivalued information transformers
• Informativity in the category of linear measurement systems
• Semantics of weakening and contraction
• Modelling environments in call-by-value programming languages.
• Axiomatic description of categories of information transformers
• Functional distribution monads in functional-analytic contexts
• A predicate/state transformer semantics for Bayesian learning
• Relative informativity and a priori information in the category of linear information transformers
• What is a statistical model? (With comments and rejoinder).
• Hypergraph categories
• Algebras of the extended probabilistic powerdomain monad
• Borel kernels and their approximation, categorically
• Kantorovich problems and conditional measures depending on a parameter
• Separoids: a mathematical framework for conditional independence and irrelevance
• Categories tannakiennes
• Sur quelques points d'algèbre homologique
• Tensors, monads and actions
• From Kleisli Categories to Commutative C*-algebras: Probabilistic Gelfand Duality
• Compositories and Gleaves
• A Survey of Graphical Languages for Monoidal Categories
• Selected Works of Debabrata Basu
• Selected Works of E. L. Lehmann
• Classical and quantum structuralism
• Categorical semantics for arrows
• Framed bicategories and monoidal fibrations
• Algebraic foundation of mathematical statistics²
• Probability Sheaves and the Giry Monad
• Terminality implies non-signalling
• A Convenient Category for Higher-Order Probability Theory
• An Algebraic Theory of Markov Processes
• Disintegration and Bayesian inversion via string diagrams
• Every Standard Construction is Induced by a Pair of Adjoint Functors
• Statistical Isomorphism
• A Note on Statistical Equivalence
• Application of the Radon-Nikodym Theorem to the Theory of Sufficient Statistics
• Probability theory. A comprehensive course
• General Relativity
• Beyond Bell's theorem. II: Scenarios with arbitrary causal structure
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statistics