Saved in:
Bibliographic Details
Main Authors: Ghosh, Kausik, Kumar, Sidhaarth, Niarchos, Vasilis, Stergiou, Andreas
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.18686
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918457738526720
author Ghosh, Kausik
Kumar, Sidhaarth
Niarchos, Vasilis
Stergiou, Andreas
author_facet Ghosh, Kausik
Kumar, Sidhaarth
Niarchos, Vasilis
Stergiou, Andreas
contents We demonstrate that simple feed-forward neural networks (NNs) can accurately compute correlation functions of conformal field theories (CFTs) on a line. Strikingly, by optimising a NN solely on crossing symmetry and providing only the scaling dimension of the leading non-trivial operator and the correlator's value at a single "anchor point", we can reconstruct target physical correlators to within a few percent. We establish the robustness of this minimal-data approach across a broad class of theories and dimensions, including generalised free fields, contact and one-loop Witten diagrams in AdS$_2$, unitary and non-unitary 2d minimal models, the 3d Ising model, and half-BPS correlators in 4d $\mathcal{N}=4$ super-Yang-Mills theory, together with several thermal two-point functions, notably including those of the 3d Ising model. We argue that this remarkable alignment between NNs and CFTs stems from the spectral bias of gradient-based training, which heavily favours smooth functions. To ground this connection, we analyse the smoothness of conformal correlators using fractional Sobolev semi-norms, Chebyshev spectral decompositions, and a measure based on curvature. Finally, we establish the broader reconstructive power of this technique by extending it beyond the diagonal kinematics of the line.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18686
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neural Spectral Bias and Conformal Correlators I: Introduction and Applications
Ghosh, Kausik
Kumar, Sidhaarth
Niarchos, Vasilis
Stergiou, Andreas
High Energy Physics - Theory
We demonstrate that simple feed-forward neural networks (NNs) can accurately compute correlation functions of conformal field theories (CFTs) on a line. Strikingly, by optimising a NN solely on crossing symmetry and providing only the scaling dimension of the leading non-trivial operator and the correlator's value at a single "anchor point", we can reconstruct target physical correlators to within a few percent. We establish the robustness of this minimal-data approach across a broad class of theories and dimensions, including generalised free fields, contact and one-loop Witten diagrams in AdS$_2$, unitary and non-unitary 2d minimal models, the 3d Ising model, and half-BPS correlators in 4d $\mathcal{N}=4$ super-Yang-Mills theory, together with several thermal two-point functions, notably including those of the 3d Ising model. We argue that this remarkable alignment between NNs and CFTs stems from the spectral bias of gradient-based training, which heavily favours smooth functions. To ground this connection, we analyse the smoothness of conformal correlators using fractional Sobolev semi-norms, Chebyshev spectral decompositions, and a measure based on curvature. Finally, we establish the broader reconstructive power of this technique by extending it beyond the diagonal kinematics of the line.
title Neural Spectral Bias and Conformal Correlators I: Introduction and Applications
topic High Energy Physics - Theory
url https://arxiv.org/abs/2604.18686