A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statistics
From MaRDI portal
Publication:2189508
conditional independencefoundations of statisticsfoundations of probabilitysufficient statisticalmost surelymonoidal categories with structure
Foundations and philosophical topics in statistics (62A01) Sufficient statistics and fields (62B05) Monads (= standard construction, triple or triad), algebras for monads, homology and derived functors for monads (18C15) Axioms; other general questions in probability (60A05) Semantics in the theory of computing (68Q55) Monoidal categories, symmetric monoidal categories (18M05)
Abstract: We develop Markov categories as a framework for synthetic probability and statistics, following work of Golubtsov as well as Cho and Jacobs. This means that we treat the following concepts in purely abstract categorical terms: conditioning and disintegration; various versions of conditional independence and its standard properties; conditional products; almost surely; sufficient statistics; versions of theorems on sufficient statistics due to Fisher--Neyman, Basu, and Bahadur. Besides the conceptual clarity offered by our categorical setup, its main advantage is that it provides a uniform treatment of various types of probability theory, including discrete probability theory, measure-theoretic probability with general measurable spaces, Gaussian probability, stochastic processes of either of these kinds, and many others.
Recommendations
Cites work
- scientific article; zbMATH DE number 3115454 (Why is no real title available?)
- scientific article; zbMATH DE number 5501718 (Why is no real title available?)
- scientific article; zbMATH DE number 5546942 (Why is no real title available?)
- scientific article; zbMATH DE number 3975284 (Why is no real title available?)
- scientific article; zbMATH DE number 4094468 (Why is no real title available?)
- scientific article; zbMATH DE number 3739847 (Why is no real title available?)
- scientific article; zbMATH DE number 3749236 (Why is no real title available?)
- scientific article; zbMATH DE number 3761167 (Why is no real title available?)
- scientific article; zbMATH DE number 3764843 (Why is no real title available?)
- scientific article; zbMATH DE number 46732 (Why is no real title available?)
- scientific article; zbMATH DE number 3635280 (Why is no real title available?)
- scientific article; zbMATH DE number 1216133 (Why is no real title available?)
- scientific article; zbMATH DE number 1076783 (Why is no real title available?)
- scientific article; zbMATH DE number 1107499 (Why is no real title available?)
- scientific article; zbMATH DE number 1134987 (Why is no real title available?)
- scientific article; zbMATH DE number 3434546 (Why is no real title available?)
- scientific article; zbMATH DE number 2079599 (Why is no real title available?)
- scientific article; zbMATH DE number 2150792 (Why is no real title available?)
- scientific article; zbMATH DE number 2087428 (Why is no real title available?)
- scientific article; zbMATH DE number 765034 (Why is no real title available?)
- scientific article; zbMATH DE number 3204678 (Why is no real title available?)
- scientific article; zbMATH DE number 3229156 (Why is no real title available?)
- scientific article; zbMATH DE number 3323562 (Why is no real title available?)
- scientific article; zbMATH DE number 3063453 (Why is no real title available?)
- A Convenient Category for Higher-Order Probability Theory
- A Note on Statistical Equivalence
- A class of fuzzy theories
- A predicate/state transformer semantics for Bayesian learning
- A survey of graphical languages for monoidal categories
- Algebraic foundation of mathematical statistics2
- Algebras of the extended probabilistic powerdomain monad
- An algebraic theory of Markov processes
- Application of the Radon-Nikodym Theorem to the Theory of Sufficient Statistics
- Axiomatic description of categories of information transformers
- Beyond Bell's theorem. II: Scenarios with arbitrary causal structure
- Borel kernels and their approximation, categorically
- Borel structures for function spaces
- Cartesian bicategories. I
- Categorical semantics for arrows
- Categories tannakiennes
- Causal categories: relativistically interacting processes
- Causality. Models, reasoning, and inference
- Classical and quantum structuralism
- Codensity and the Giry monad
- Combining statistical models
- Compositories and Gleaves
- Conditional independence for statistical operations
- Disintegration and Bayesian inversion via string diagrams
- Every Standard Construction is Induced by a Pair of Adjoint Functors
- Extremal families and systems of sufficient statistics
- Framed bicategories and monoidal fibrations
- From Kleisli categories to commutative \(C^*\)-algebras: probabilistic Gelfand duality
- Functional distribution monads in functional-analytic contexts
- General Relativity
- Hypergraph categories
- Information transformers: category-theoretical structure, informativeness, decision-making problems
- Informativity in the category of linear measurement systems
- Informativity in the category of multivalued information transformers
- Kantorovich problems and conditional measures depending on a parameter
- Labelled Markov processes.
- Markov invariant geometry and manifolds of states
- Matrices, relations, and group representations
- Measure theory. Vol. 3. Measure algebras
- Method of additional structures on the objects of a monoidal Kleisli category as a background for information transformers theory
- Modelling environments in call-by-value programming languages.
- Picturing classical and quantum Bayesian inference
- Probability sheaves and the Giry monad
- Probability theory. A comprehensive course
- Purity through factorisation
- Relative informativity and a priori information in the category of linear information transformers
- Selected Works of Debabrata Basu
- Selected works of E. L. Lehmann. Edited by Javier Rojo
- Semantics of weakening and contraction
- Separoids: a mathematical framework for conditional independence and irrelevance
- Statistical Isomorphism
- Sur quelques points d'algèbre homologique
- Tensors, monads and actions
- Terminality implies non-signalling
- The beta-Bernoulli process and algebraic effects
- The existence of regular conditional probabilities: Necessary and sufficient conditions
- The geometry of tensor calculus. I
- Theory of fuzzy sets as a theory of uncertainty and decision-making problems in fuzzy experiments
- What is a statistical model? (With comments and rejoinder).
Cited in
(46)- Stick breaking, in coalgebra and probability
- The existence of regular conditional probabilities for Markov kernels
- 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
- Causal inference via string diagram surgery. A diagrammatic approach to interventions and counterfactuals
- Representable Markov categories and comparison of statistical experiments in categorical probability
- A non-commutative Bayes' theorem
- Monoidal Width
- Monotone metric tensors in quantum information geometry
- A categorical construction of the real unit interval
- Functorial manifold learning
- Categorical composable cryptography: extended version
- A categorical approach to statistical mechanics
- Categorical information geometry
- Conditional expectation of a Markov kernel given another with some applications in statistical inference and disease diagnosis
- A category-theoretic proof of the ergodic decomposition theorem
- Multisets and distributions, in drawing and learning
- Free gs-monoidal categories and free Markov categories
- Infinite products and zero-one laws in categorical probability
- Value Iteration is Optic Composition
- On independence of Markov kernels and a generalization of two theorems of Basu
- 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
- Drawing from an urn is isometric
- Towards a compositional framework for convex analysis (with applications to probability theory)
- Parametric models and information geometry on \(W^\star\)-algebras
- scientific article; zbMATH DE number 3858151 (Why is no real title available?)
- A higher-order language for Markov kernels and linear operators
- Cartesian double theories: a double-categorical framework for categorical doctrines
- 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
- Categorial independence and Lévy processes
- Learning from what's right and learning from what's wrong
- Multinomial and hypergeometric distributions in Markov categories
- A categorical semantics of fuzzy concepts in conceptual spaces
- A reconstruction of Ewens' sampling formula via lists of coins
- Cyber kittens, or some first steps towards categorical cybernetics
- mathlib4 Module Mathlib/CategoryTheory/CopyDiscardCategory/Basic
- mathlib4 Module Mathlib/CategoryTheory/MarkovCategory/Basic
- Disintegration and Bayesian inversion via string diagrams
This page was built for publication: A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statistics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2189508)
