Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ghosh, Kausik, Kumar, Sidhaarth, Niarchos, Vasilis, Stergiou, Andreas
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.18673
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917423628681216
author Ghosh, Kausik
Kumar, Sidhaarth
Niarchos, Vasilis
Stergiou, Andreas
author_facet Ghosh, Kausik
Kumar, Sidhaarth
Niarchos, Vasilis
Stergiou, Andreas
contents We propose that simple neural networks (NNs) trained on crossing symmetry can reconstruct conformal correlators restricted to a line to remarkable accuracy. The input is minimal: an external scaling dimension, a spectral gap, and the value of the correlator at a single point. We present evidence across a wide range of conformal theories and dimensions, for both four-point and thermal two-point functions. We attribute these observations to the spectral bias of gradient-based NN training, which appears to align with an intrinsic smoothness property of conformal field theory. This suggests a novel variational principle for conformal correlators and opens a path towards a powerful new computational framework for non-perturbative quantum field theory.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18673
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neural Networks Reveal a Universal Bias in Conformal Correlators
Ghosh, Kausik
Kumar, Sidhaarth
Niarchos, Vasilis
Stergiou, Andreas
High Energy Physics - Theory
We propose that simple neural networks (NNs) trained on crossing symmetry can reconstruct conformal correlators restricted to a line to remarkable accuracy. The input is minimal: an external scaling dimension, a spectral gap, and the value of the correlator at a single point. We present evidence across a wide range of conformal theories and dimensions, for both four-point and thermal two-point functions. We attribute these observations to the spectral bias of gradient-based NN training, which appears to align with an intrinsic smoothness property of conformal field theory. This suggests a novel variational principle for conformal correlators and opens a path towards a powerful new computational framework for non-perturbative quantum field theory.
title Neural Networks Reveal a Universal Bias in Conformal Correlators
topic High Energy Physics - Theory
url https://arxiv.org/abs/2604.18673