Conformal Fields from Neural Networks

Abstract

We use the embedding formalism to construct conformal fields in $D$ dimensions, by restricting Lorentz-invariant ensembles of homogeneous neural networks in $(D+2)$ dimensions to the projective null cone. Conformal correlators may be computed using the parameter space description of the neural network. Exact four-point correlators are computed in a number of examples, and we perform a 4D conformal block decomposition that elucidates the spectrum. In some examples the analysis is facilitated by recent approaches to Feynman integrals. Generalized free CFTs are constructed using the infinite-width Gaussian process limit of the neural network, enabling a realization of the free boson. The extension to deep networks constructs conformal fields at each subsequent layer, with recursion relations relating their conformal dimensions and four-point functions. Numerical approaches are discussed.

v1: 48 pages; v2 60 pages (journal version)

References in corpus (33)

• Bounding scalar operator dimensions in 4D CFT
• The Conformal Bootstrap: Theory, Numerical Techniques, and Applications
• Solving the 3D Ising Model with the Conformal Bootstrap
• Conformal Partial Waves and the Operator Product Expansion
• Solving the 3d Ising Model with the Conformal Bootstrap II. c-Minimization and Precise Critical Exponents
• Precision Islands in the Ising and $O(N)$ Models
• The Analytic Bootstrap and AdS Superhorizon Locality
• Spinning Conformal Correlators
• FIRE6: Feynman Integral REduction with Modular Arithmetic
• Universality of Long-Distance AdS Physics from the CFT Bootstrap
• Bootstrapping the O(N) Vector Models
• Lectures on differential equations for Feynman integrals
• EPFL Lectures on Conformal Field Theory in D>= 3 Dimensions
• Bootstrapping Mixed Correlators in the 3D Ising Model
• Carving Out the Space of 4D CFTs
• The N=4 Superconformal Bootstrap
• Radial Coordinates for Conformal Blocks
• Six-dimensional Methods for Four-dimensional Conformal Field Theories
• Two-Loop Master Integrals for ${\gamma }^{\ast }\to 3$ Jets: The non-planar topologies
• Sharp Boundaries for the Swampland
• Bounds in 4D Conformal Field Theories with Global Symmetry
• Carving out OPE space and precise $O(2)$ model critical exponents
• Conformal Field Theories in Fractional Dimensions
• Conformal Bootstrap Dashing Hopes of Emergent Symmetry
• Deep Inelastic Scattering in Conformal QCD
• Five dimensional $O(N)$-symmetric CFTs from conformal bootstrap
• Neural Networks and Quantum Field Theory
• Bootstrapping the 3d Ising Stress Tensor
• New Developments in the Numerical Conformal Bootstrap
• Solving Conformal Field Theories with Artificial Intelligence
• 6D (2,0) Bootstrap with soft-Actor-Critic
• Automorphic Spectra and the Conformal Bootstrap
• Axiomatic conformal theory in dimensions >2 and AdS/CT correspondence

Cited by in corpus (6)

• Holographic flavour and neural networks
• Gravity Dual of Networks
• On the solution of Euclidean path integrals with neural networks
• Gauge-covariant stochastic neural fields: Stability and finite-width effects
• Approximating Grassmann valued path integrals with radial basis function neural networks
• Conformal Defects in Neural Network Field Theories