
ALT Stochastic Neural Network Symmetrisation in Markov Categories Rob Cornish Department of Statistics, University of Oxford Abstract We consider the problem of symmetrising a neural network along a group homomor- phism: given a homomorphism φ : H → G, we would like a procedure that converts H-equivariant neural networks to G-equivariant ones. We formulate this in terms of Markov categories, which allows us to consider neural networks whose outputs may be stochastic, but with measure-theoretic details abstracted away. We obtain a flexible and compositional framework for symmetrisation that relies on minimal assumptions about the structure of the group and the underlying neural network architecture. Our approach recovers existing canonicalisation and averaging techniques for symmetris- ing deterministic models, and extends to provide a novel methodology for symmetrising stochastic models also. Beyond this, our findings also demonstrate the utility of Markov categories for addressing complex































