aiqbench analysis
This research establishes a rigorous mathematical bridge between neural network ensembles and conformal field theory, demonstrating how specific neuron architectures can recover known physical models like the 4d Maxwell CFT in high-dimensional limits. By constructing spinning fields directly from networks using embedding formalism, the study advances our understanding of the fundamental statistical mechanics underlying deep learning structures beyond simple scalar approximations.
Spinning Conformal Correlators from Neural Networks
arXiv:2608.15001v1 Announce Type: cross Abstract: We construct spinning conformal fields from neural networks and the embedding formalism, computing their two-, three- and four-point functions in examples, building on scalar conformal field techniques introduced in \cite{Halverson:2024axc}. For a particular ensemble of i.i.d. neurons we recover the 4d Maxwell CFT in the infinite-width limit.
Abstract:We construct spinning conformal fields from neural networks and the embedding formalism, computing their two-, three- and four-point functions in examples, building on scalar conformal field techniques introduced in \cite{Halverson:2024axc}. For a particular ensemble of i.i.d. neurons we recover the 4d Maxwell CFT in the infinite-width limit.
High Energy Physics - Theory (hep-th); Machine Learning (cs.LG)
arXiv:2608.15001 [hep-th]
(or arXiv:2608.15001v1 [hep-th] for this version)
https://doi.org/10.48550/arXiv.2608.15001 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 147 words
Related coverage
Order Parameter Discovery for Quantum Many-Body Systems
Quantum Journal · Sep 29, 2026
Symmetry-enriched topological order in tensor networks: Defects, gauging and anyon condensation
Quantum Journal · Sep 1, 2026
Magnetic HIP-NN for spin dynamics in disordered itinerant magnets
arXiv · Jun 10, 2026
Towards Interpretability of Neural Quantum States
arXiv · Jun 16, 2026