Bayesian machine learning via category theory

Abstract

From the Bayesian perspective, the category of conditional probabilities (a variant of the Kleisli category of the Giry monad, whose objects are measurable spaces and arrows are Markov kernels) gives a nice framework for conceptualization and analysis of many aspects of machine learning. Using categorical methods, we construct models for parametric and nonparametric Bayesian reasoning on function spaces, thus providing a basis for the supervised learning problem. In particular, stochastic processes are arrows to these function spaces which serve as prior probabilities. The resulting inference maps can often be analytically constructed in this symmetric monoidal weakly closed category. We also show how to view general stochastic processes using functor categories and demonstrate the Kalman filter as an archetype for the hidden Markov model.

74 pages, comments welcome

References in corpus (1)

• A presentation of the category of stochastic matrices

Cited by in corpus (6)

• Formal verification of higher-order probabilistic programs
• Quantum GestART: Identifying and Applying Correlations between Mathematics, Art, and Perceptual Organization
• Category Theory in Machine Learning
• Categorical Stochastic Processes and Likelihood
• Compositional Deep Learning
• Characterizing the invariances of learning algorithms using category theory