Categorical Stochastic Processes and Likelihood
Compositionality · 2021
DOI: 10.32408/compositionality-3-1 ↗Kurz gefasst
Fachartikel in der Zeitschrift Compositionality, 2021. Verfasst von Dan Shiebler. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We take a category-theoretic perspective on the relationship between probabilistic modeling and gradient based optimization. We define two extensions of function composition to stochastic process subordination: one based on a co-Kleisli category and one based on the parameterization of a category with a Lawvere theory. We show how these extensions relate to the category of Markov kernels S t o c h through a pushforward procedure.We extend stochastic processes to parametric statistical models and define a way to compose the likelihood functions of these models. We demonstrate how the maximum likelihood estimation procedure defines a family of identity-on-objects functors from categories of statistical models to the category of supervised learning algorithms L e a r n .Code to accompany this paper can be found on GitHub (https://github.com/dshieble/Categorical_Stochastic_Processes_and_Likelihood).
Zitieren
APA
Shiebler, D. (2021). Categorical Stochastic Processes and Likelihood. Compositionality. https://doi.org/10.32408/compositionality-3-1
Vancouver
Shiebler D. Categorical Stochastic Processes and Likelihood. Compositionality. 2021. doi:10.32408/compositionality-3-1
BibTeX
@article{Shiebler2021,
author = {Shiebler, Dan},
title = {Categorical Stochastic Processes and Likelihood},
journal = {Compositionality},
year = {2021},
doi = {10.32408/compositionality-3-1}
}
EUVIMED