% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Gaede:478310,
author = {Gaede, Frank and Eren, Engin and Krüger, Katja and
Diefenbacher, Sascha Daniel and Korol, Anatolii and
Kasieczka, Gregor and Buhmann, Erik},
title = {{G}etting {H}igh: {H}igh {F}idelity {S}imulation of {H}igh
{G}ranularity {C}alorimeters with {H}igh {S}peed},
journal = {Computing and software for big science},
volume = {5},
number = {1},
issn = {2510-2036},
address = {Cham, Switzerland},
publisher = {Springer International Publishing},
reportid = {PUBDB-2022-02526, arXiv:2005.05334. DESY-20-075},
pages = {13},
year = {2021},
note = {Computing and Software for Big Science 5, 13 (2021). 17
pages, 12 figures},
abstract = {Accurate simulation of physical processes is crucial for
the success of modern particle physics. However, simulating
the development and interaction of particle showers with
calorimeter detectors is a time consuming process and drives
the computing needs of large experiments at the LHC and
future colliders. Recently, generative machine learning
models based on deep neural networks have shown promise in
speeding up this task by several orders of magnitude. We
investigate the use of a new architecture—the Bounded
Information Bottleneck Autoencoder—for modelling
electromagnetic showers in the central region of the
Silicon-Tungsten calorimeter of the proposed International
Large Detector. Combined with a novel second post-processing
network, this approach achieves an accurate simulation of
differential distributions including for the first time the
shape of the minimum-ionizing-particle peak compared to a
full Geant4 simulation for a high-granularity calorimeter
with 27k simulated channels. The results are validated by
comparing to established architectures. Our results further
strengthen the case of using generative networks for fast
simulation and demonstrate that physically relevant
differential distributions can be described with high
accuracy.},
keywords = {calorimeter (INSPIRE) / iron (INSPIRE) / tungsten (INSPIRE)
/ showers: electromagnetic (INSPIRE) / particle: interaction
(INSPIRE) / neural network (INSPIRE) / GEANT (INSPIRE) / ILD
detector (INSPIRE) / artificial intelligence (INSPIRE) /
numerical calculations (INSPIRE) / numerical methods
(INSPIRE) / performance (INSPIRE) / Deep learning (autogen)
/ Generative models (autogen) / Calorimeter (autogen) /
Simulation (autogen) / High granularity (autogen) / GAN
(autogen) / WGAN (autogen) / BIB-AE (autogen)},
cin = {FLC},
ddc = {004},
cid = {I:(DE-H253)FLC-20120731},
pnm = {611 - Fundamental Particles and Forces (POF3-611)},
pid = {G:(DE-HGF)POF3-611},
experiment = {EXP:(DE-H253)ILC(machine)-20150101},
typ = {PUB:(DE-HGF)16},
eprint = {2005.05334},
howpublished = {arXiv:2005.05334},
archivePrefix = {arXiv},
SLACcitation = {$\%\%CITATION$ = $arXiv:2005.05334;\%\%$},
doi = {10.1007/s41781-021-00056-0},
url = {https://bib-pubdb1.desy.de/record/478310},
}