Categorical Stochastic Processes and Likelihood
arXiv:2005.04735 · doi:10.32408/compositionality-3-1
Abstract
In this work we take a Category Theoretic perspective on the relationship between probabilistic modeling and function approximation. We begin by defining two extensions of function composition to stochastic process subordination: one based on the co-Kleisli category under the comonad (Omega x -) and one based on the parameterization of a category with a Lawvere theory. We show how these extensions relate to the category Stoch and other Markov Categories. Next, we apply the Para construction to extend stochastic processes to parameterized statistical models and we define a way to compose the likelihood functions of these models. We conclude with a demonstration of how the Maximum Likelihood Estimation procedure defines an identity-on-objects functor from the category of statistical models to the category of Learners. Code to accompany this paper can be found at https://github.com/dshieble/Categorical_Stochastic_Processes_and_Likelihood
References in corpus (11)
- SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
- A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statistics
- Disintegration and Bayesian Inversion via String Diagrams
- A Convenient Category for Higher-Order Probability Theory
- How Deep is the Feature Analysis underlying Rapid Visual Categorization?
- Towards Foundations of Categorical Cybernetics
- A categorical foundation for Bayesian probability
- Bayesian machine learning via category theory
- Lenses and Learners
- Compositional Deep Learning
- What is Stochastic Independence?