A convenient category for higher-order probability theory
Higher-order probabilistic programming languages allow programmers to write sophisticated models in machine learning and statistics in a succinct and structured way, but step outside the standard measure-theoretic formalization of probability theory. Programs may use both higher-order functions and...
Glavni autori: | Heunen, C, Kammar, O, Staton, S, Yang, H |
---|---|
Format: | Conference item |
Izdano: |
IEEE
2017
|
Slični predmeti
-
Semantics for probabilistic programming: higher-order functions, continuous distributions, and soft constraints
od: Yang, H, i dr.
Izdano: (2016) -
Concrete categories and higher-order recursion
od: Matache, C, i dr.
Izdano: (2022) -
Denotational validation of higher-order Bayesian inference
od: Scibior, A, i dr.
Izdano: (2018) -
A domain theory for statistical probabilistic programming
od: Vákár, M, i dr.
Izdano: (2019) -
Compositional imprecise probability: a solution from graded monads and Markov categories
od: Liell-Cock, J, i dr.
Izdano: (2025)