Optimising hadronic collider simulations using amplitude neural networks

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 use neural networks approximate matrix elements, studying case loop-induced diphoton production through gluon fusion. train network models on one-loop amplitudes from NJet C++ library interface them with Sherpa Monte Carlo event generator provide element within realistic hadronic simulation. Computing some standard observables comparing conventional techniques, we find excellent agreement distributions reduced total simulation time by factor thirty.