Optimising simulations for diphoton production at hadron colliders using amplitude neural networks

• Published in: The journal of high energy physics 2021-08, Vol.2021 (8), p.1-30, Article 66
• Main Authors: Aylett-Bullock, Joseph, Badger, Simon, Moodie, Ryan
• Format: Article
• Language: English
• Subjects: Amplitudes; Classical and Quantum Gravitation; Computer simulation; Elementary Particles; Gluons; High energy physics; Machine learning; Network reliability; Neural networks; NLO Computations; Optimization; Physics; Physics and Astronomy; QCD Phenomenology; Quantum Field Theories; Quantum Field Theory; Quantum Physics; Regular Article - Theoretical Physics; Relativity Theory; Scattering; Simulation; String Theory
• ISSN: 1029-8479; 1029-8479
• DOI: 10.1007/JHEP08(2021)066

A bstract Machine learning technology has the potential to dramatically optimise event generation and simulations. We continue to investigate the use of neural networks to approximate matrix elements for high-multiplicity scattering processes. We focus on the case of loop-induced diphoton production through gluon fusion, and develop a realistic simulation method that can be applied to hadron collider observables. Neural networks are trained using the one-loop amplitudes implemented in the NJet C++ library, and interfaced to the Sherpa Monte Carlo event generator, where we perform a detailed study for 2 → 3 and 2 → 4 scattering problems. We also consider how the trained networks perform when varying the kinematic cuts effecting the phase space and the reliability of the neural network simulations.