A factorisation-aware matrix element emulator

In this contribution I present a neural network based model to emulate matrix elements. This model improves on existing methods by taking advantage of the known factorisation properties of matrix elements to drastically improve per-point accuracy. By building in the factorisation properties into the model we can control the behaviour of simulated matrix elements when extrapolating into more singular regions than the ones used for training the neural network. I apply this model to the case of leading-order jet production in e + e − collisions with up to five jets where this model can reproduce the matrix elements with errors below the one-percent level on the phase-space covered during fitting and testing, with a robust extrapolation to the parts of the phase-space where the matrix elements are more singular than seen at the fitting stage. Finally I discuss the usage and performance of the model on a GPU system.