Work

Notes on algebraic perspective on neural network conformal theories

Year: 2026
Type: preprint
Abstract: Neural network conformal theories were first introduced in \cite{Halverson:2024axc} and exact two-, three- and four-point correlators were computed from an ensemble of infinite-width neural networks. In particular, the four-point correlator of any scalar operator satisfied crossing-symmetry and conformal block decomposition across different channels were in agreement without any constraint on moments. An infinite tower of degenerate operators with the same scaling dimension were found. In this note, we take a closer look at the structure of correlators and relation between operators. We also layout a recipe to construct the algebra of the theory.
Language: English
Open Access status: green
OpenAlex ID: W7214974187
Cites: 37
Cited by: 1
Related to: 10