%0 Electronic Article
%A Bieringer, Sebastian Guido
%A Anja Butter
%A Diefenbacher, Sascha Daniel
%A Eren, Engin
%A Gaede, Frank
%A Hundhausen, Daniel Christian
%A Kasieczka, Gregor
%A Nachman, Benjamin
%A Plehn, Tilman
%A Mathias Trabs, KIT
%T Calomplification - The Power of Generative Calorimeter Models
%N DESY-22-031
%M PUBDB-2022-00968
%M DESY-22-031
%M arXiv:2202.07352
%D 2022
%Z 17 pages, 10 figures
%X Motivated by the high computational costs of classical simulations, machine-learned gen- erative models can be extremely useful in particle physics and elsewhere. They become especially attractive when surrogate models can efficiently learn the underlying distri- bution, such that a generated sample outperforms a training sample of limited size. This kind of GANplification has been observed for simple Gaussian models. We show the same effect for a physics simulation, specifically photon showers in a highly-granular electromagnetic calorimeter.
%K photon, showers (INSPIRE)
%K calorimeter, electromagnetic (INSPIRE)
%K costs (INSPIRE)
%F PUB:(DE-HGF)25
%9 Preprint
%R 10.3204/PUBDB-2022-00968
%U https://bib-pubdb1.desy.de/record/474749