arXiv · 2604.18673
Neural Networks Reveal a Universal Bias in Conformal Correlators
Abstract
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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Kausik Ghosh, Sidhaarth Kumar, Vasilis Niarchos, Andreas Stergiou. 2026-04-20. Neural Networks Reveal a Universal Bias in Conformal Correlators. https://arxiv.org/abs/2604.18673
Cite the original work for its findings. Save a collection to share your selection of sources.