Neural Network Symmetrisation in Concrete Settings

TL;DR

This work gives a high-level overview of general theory of neural network symmetrisation in the abstract context of Markov categories, and their concrete implications for the symmetrisation of deterministic functions and of Markov kernels.

Abstract

Cornish (2024) recently gave a general theory of neural network symmetrisation in the abstract context of Markov categories. We give a high-level overview of these results, and their concrete implications for the symmetrisation of deterministic functions and of Markov kernels.