TY  - EJOUR
AU  - Bieringer, Sebastian Guido
AU  - Anja Butter
AU  - Diefenbacher, Sascha Daniel
AU  - Eren, Engin
AU  - Gaede, Frank
AU  - Hundhausen, Daniel Christian
AU  - Kasieczka, Gregor
AU  - Nachman, Benjamin
AU  - Plehn, Tilman
AU  - Mathias Trabs, KIT
TI  - Calomplification - The Power of Generative Calorimeter Models
IS  - DESY-22-031
M1  - PUBDB-2022-00968
M1  - DESY-22-031
M1  - arXiv:2202.07352
PY  - 2022
N1  - 17 pages, 10 figures
AB  - 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.
KW  - photon, showers (INSPIRE)
KW  - calorimeter, electromagnetic (INSPIRE)
KW  - costs (INSPIRE)
LB  - PUB:(DE-HGF)25
DO  - DOI:10.3204/PUBDB-2022-00968
UR  - https://bib-pubdb1.desy.de/record/474749
ER  -