How to GAN away Detector Effects
This addresses the challenge of using first-principle predictions as black-box simulations in LHC data analysis, offering a method to invert detector effects for improved accuracy.
The paper tackles the problem of inverting detector effect simulations in LHC analyses by using generative networks to reconstruct parton level information from measured events, demonstrating that fully conditional generative networks can statistically invert Monte Carlo simulations.
LHC analyses directly comparing data and simulated events bear the danger of using first-principle predictions only as a black-box part of event simulation. We show how simulations, for instance, of detector effects can instead be inverted using generative networks. This allows us to reconstruct parton level information from measured events. Our results illustrate how, in general, fully conditional generative networks can statistically invert Monte Carlo simulations. As a technical by-product we show how a maximum mean discrepancy loss can be staggered or cooled.