Understanding Event-Generation Networks via Uncertainties

Marco Bellagente, Michel Luchmann, Manuel Haussmann, Tilman Plehn

Keywords: normalizing flow, bayesian neural network, LHC

TL;DR: We combine the real non-volume preserving flow with BNNs to model uncertainty in the transformation and evaluate it on illustrative toy data and LHC simulations.

Abstract: Generative models and normalizing flow based models have made great progress in recent years both in their theoretical development as well as in a growing number of applications. As such models become applied more and more with it increases the desire for predictive uncertainty to know when to trust the underlying model. In this extended abstract we target the application area of Large Hadron Collider (LHC) simulations and show how to extend normalizing flows with probabilistic Bayesian Neural Network based transformations to model LHC events with uncertainties.