Targeting multi-loop integrals with neural networks

Numerical evaluations of Feynman integrals often proceed via a deformation of the integration contour into the complex plane. While valid contours are easy to construct, the numerical precision for a multi-loop integral can depend critically on the chosen contour. We present methods to optimize this...

Full description

Saved in:
Bibliographic Details
Published inSciPost physics Vol. 12; no. 4; p. 129
Main Authors Winterhalder, Ramon, Magerya, Vitaly, Villa, Emilio, Jones, Stephen, Kerner, Matthias, Butter, Anja, Heinrich, Gudrun, Plehn, Tilman
Format Journal Article
LanguageEnglish
Published SciPost 01.04.2022
Online AccessGet full text

Cover

More Information
Summary:Numerical evaluations of Feynman integrals often proceed via a deformation of the integration contour into the complex plane. While valid contours are easy to construct, the numerical precision for a multi-loop integral can depend critically on the chosen contour. We present methods to optimize this contour using a combination of optimized, global complex shifts and a normalizing flow. They can lead to a significant gain in precision.
ISSN:2542-4653
2542-4653
DOI:10.21468/SciPostPhys.12.4.129