FlashSim: Accelerating HEP simulation with an end-to-end Machine Learning framework

Abstract

We developed a first prototype of an end-to-end machine learning based simulation framework for arbitrary analysis ntuples at the CMS experiment. Such a framework, called FlashSim, was capable of simulating a wide variety of physical objects with good performance on 1d distributions, correlations and desired physical content when compared to the current state-of-theart simulation. Current methods are based on MC techniques, computationally expensive and requiring a long time to compute. Our prototype was trained to replicate the samples from state-of-the-art methods through the use of the Normalizing Flows algorithm. It showed compatible results with a speedup of several orders of magnitude. This type of approach opens the way to general, analysis agnostic simulation frameworks which may be able to tackle the challenges of the simulation needs for HL-LHC and future collaborations.