Probabilistic programming interfaces for random graphs: Markov categories, graphons, and nominal sets
arXiv:2312.17127 · doi:10.1145/3632903
Abstract
We study semantic models of probabilistic programming languages over graphs, and establish a connection to graphons from graph theory and combinatorics. We show that every well-behaved equational theory for our graph probabilistic programming language corresponds to a graphon, and conversely, every graphon arises in this way. We provide three constructions for showing that every graphon arises from an equational theory. The first is an abstract construction, using Markov categories and monoidal indeterminates. The second and third are more concrete. The second is in terms of traditional measure theoretic probability, which covers 'black-and-white' graphons. The third is in terms of probability monads on the nominal sets of Gabbay and Pitts. Specifically, we use a variation of nominal sets induced by the theory of graphs, which covers Erdős-Rényi graphons. In this way, we build new models of graph probabilistic programming from graphons.
arXiv commentAccepted for POPL 2024
References in corpus (15)
- Sparse graphs using exchangeable random measures
- A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statistics
- A Convenient Category for Higher-Order Probability Theory
- A Domain Theory for Statistical Probabilistic Programming
- Commutative monads as a theory of distributions
- Measurable Cones and Stable, Measurable Functions
- Graphons, cut norm and distance, couplings and rearrangements
- Computable de Finetti measures
- The Expectation Monad in Quantum Foundations
- Commutative Monads for Probabilistic Programming Languages
- Invariant measures concentrated on countable structures
- Categorical Stochastic Processes and Likelihood
- Concrete categories and higher-order recursion (With applications including probability, differentiability, and full abstraction)
- Universal Properties of Partial Quantum Maps
- A model of stochastic memoization and name generation in probabilistic programming: categorical semantics via monads on presheaf categories