Probabilistic morphisms and Bayesian supervised learning

2025/02/21 by Lê, Hông Vân · 1 citation
#18B40 #62C10 #62G05 #62G08 #Category Theory (math.CT) #FOS: Mathematics #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.2502.15408

Abstract

In this paper, we develop category theory of Markov kernels to study categorical aspects of Bayesian inversions. As a result, we present a unified model for Bayesian supervised learning, encompassing Bayesian density estimation. We illustrate this model with Gaussian process regressions.

Cited by

• Categorical and geometric methods in statistical, manifold, and machine learning

Related

• Bayesian machine learning via category theory
• A category theory framework for Bayesian learning
• Batch learning equals online learning in Bayesian supervised learning
• Supervised learning with probabilistic morphisms and kernel mean embeddings
• The Bayesian Learning Rule