Representable Markov Categories and Comparison of Statistical Experiments in Categorical Probability

Abstract

Markov categories are a recent categorical approach to the mathematical foundations of probability and statistics. Here, this approach is advanced by stating and proving equivalent conditions for second-order stochastic dominance, a widely used way of comparing probability distributions by their spread. Furthermore, we lay foundation for the theory of comparing statistical experiments within Markov categories by stating and proving the classical Blackwell-Sherman-Stein Theorem. Our version not only offers new insight into the proof, but its abstract nature also makes the result more general, automatically specializing to the standard Blackwell-Sherman-Stein Theorem in measure-theoretic probability as well as a Bayesian version that involves prior-dependent garbling. Along the way, we define and characterize representable Markov categories, within which one can talk about Markov kernels to or from spaces of distributions. We do so by exploring the relation between Markov categories and Kleisli categories of probability monads.

63 pages, color used in text and diagrams. v3: To be published in Theoretical Computer Science. Section 6 on strongly representable Markov categories removed to streamline the narrative, plus other minor changes

References in corpus (2)

• Tensor categorical foundations of algebraic geometry
• The algebra and machine representation of statistical models

Cited by in corpus (15)

• From time-reversal symmetry to quantum Bayes' rules
• Dilations and information flow axioms in categorical probability
• Markov Categories and Entropy
• Category Theory in Machine Learning
• A Categorical Construction of the Real Unit Interval
• Hidden Markov Models and the Bayes Filter in Categorical Probability
• Sufficient Statistics and Split Idempotents in Discrete Probability Theory
• From Gs-monoidal to Oplax Cartesian Categories: Constructions and Functorial Completeness
• Compositional Semantics for Probabilistic Programs with Exact Conditioning
• Unifilar Machines and the Adjoint Structure of Bayesian Filtering
• Reinforcement Learning in Categorical Cybernetics
• On the categorical foundations of quantum information theory: Categories and the Cramer-Rao inequality
• The Aldous$\unicode{x2013}$Hoover Theorem in Categorical Probability
• Categorical algebra of conditional probability
• Combs, Causality and Contractions in Atomic Markov Categories