Optimising hadronic collider simulations using amplitude neural networks

Abstract

Precision phenomenological studies of high-multiplicity scattering processes at collider experiments present a substantial theoretical challenge and are vitally important ingredients in experimental measurements. Machine learning technology has the potential to dramatically optimise simulations for complicated final states. We investigate the use of neural networks to approximate matrix elements, studying the case of loop-induced diphoton production through gluon fusion. We train neural network models on one-loop amplitudes from the NJet C++ library and interface them with the Sherpa Monte Carlo event generator to provide the matrix element within a realistic hadronic collider simulation. Computing some standard observables with the models and comparing to conventional techniques, we find excellent agreement in the distributions and a reduced total simulation time by a factor of thirty.

6 pages, 6 figures, Proceedings of the 20th International Workshop on Advanced Computing and Analysis Techniques in Physics Research (ACAT 2021)

References in corpus (11)

• LHAPDF6: parton density access in the LHC precision era
• Reducing full one-loop amplitudes to scalar integrals at the integrand level
• Automation of next-to-leading order computations in QCD: the FKS subtraction
• Robust Independent Validation of Experiment and Theory: Rivet version 3
• FiniteFlow: multivariate functional reconstruction using finite fields and dataflow graphs
• Direct Extraction Of One Loop Rational Terms
• NNLO QCD corrections to diphoton production with an additional jet at the LHC
• Two-loop helicity amplitudes for diphoton plus jet production in full color
• A factorisation-aware Matrix element emulator
• Next-to-leading order QCD corrections to diphoton-plus-jet production through gluon fusion at the LHC
• Three-loop helicity amplitudes for diphoton production in gluon fusion