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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
hep-th 2verdicts
CONDITIONAL 2roles
background 1polarities
background 1representative citing papers
Imposing a duality-inspired fusion rule that forbids the [ε] sector from appearing in the [ε] × [ε] OPE yields numerical bounds on (Δ_σ, Δ_ε) that include the 2d Ising model but exclude the 3d Ising model.
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.
-
Conformal Bootstrap with Duality-Inspired Fusion Rule
Imposing a duality-inspired fusion rule that forbids the [ε] sector from appearing in the [ε] × [ε] OPE yields numerical bounds on (Δ_σ, Δ_ε) that include the 2d Ising model but exclude the 3d Ising model.