Simple feed-forward neural networks trained on crossing symmetry plus a single anchor value reproduce CFT correlators to percent-level accuracy, and the authors conjecture this works because physical correlators are the smoothest allowed functions.
On the Inductive Bias of Neural Tangent Kernels
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
hep-th 2years
2026 2verdicts
CONDITIONAL 2roles
background 2polarities
background 2representative citing papers
Simple neural networks trained on crossing symmetry and one anchor point reproduce conformal correlators to within a few percent across many CFTs.
citing papers explorer
-
Neural Spectral Bias and Conformal Correlators I: Introduction and Applications
Simple feed-forward neural networks trained on crossing symmetry plus a single anchor value reproduce CFT correlators to percent-level accuracy, and the authors conjecture this works because physical correlators are the smoothest allowed functions.
-
Neural Networks Reveal a Universal Bias in Conformal Correlators
Simple neural networks trained on crossing symmetry and one anchor point reproduce conformal correlators to within a few percent across many CFTs.