Ephemeral Learning - Augmenting Triggers with Online-Trained Normalizing Flows

Butter, Anja; Diefenbacher, Sascha; Kasieczka, Gregor; Nachman, Benjamin; Plehn, Tilman; Shih, David; Winterhalder, Ramon

doi:10.21468/SciPostPhys.13.4.087

SciPost Physics

Ephemeral Learning - Augmenting Triggers with Online-Trained Normalizing Flows

Anja Butter, Sascha Diefenbacher, Gregor Kasieczka, Benjamin Nachman, Tilman Plehn, David Shih, Ramon Winterhalder

SciPost Phys. 13, 087 (2022) · published 7 October 2022

doi: 10.21468/SciPostPhys.13.4.087
pdf
Submissions/Reports

Abstract

The large data rates at the LHC require an online trigger system to select relevant collisions. Rather than compressing individual events, we propose to compress an entire data set at once. We use a normalizing flow as a deep generative model to learn the probability density of the data online. The events are then represented by the generative neural network and can be inspected offline for anomalies or used for other analysis purposes. We demonstrate our new approach for a toy model and a correlation-enhanced bump hunt.

TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhys.13.4.087
TI  - Ephemeral Learning - Augmenting Triggers with Online-Trained Normalizing Flows
PY  - 2022/10/07
UR  - https://scipost.org/SciPostPhys.13.4.087
JF  - SciPost Physics
JA  - SciPost Phys.
VL  - 13
IS  - 4
SP  - 087
A1  - Butter, Anja
AU  - Diefenbacher, Sascha
AU  - Kasieczka, Gregor
AU  - Nachman, Benjamin
AU  - Plehn, Tilman
AU  - Shih, David
AU  - Winterhalder, Ramon
AB  - The large data rates at the LHC require an online trigger system to select relevant collisions. Rather than compressing individual events, we propose to compress an entire data set at once. We use a normalizing flow as a deep generative model to learn the probability density of the data online. The events are then represented by the generative neural network and can be inspected offline for anomalies or used for other analysis purposes. We demonstrate our new approach for a toy model and a correlation-enhanced bump hunt.
ER  -

@Article{10.21468/SciPostPhys.13.4.087,
	title={{Ephemeral Learning - Augmenting Triggers with Online-Trained Normalizing Flows}},
	author={Anja Butter and Sascha Diefenbacher and Gregor Kasieczka and Benjamin Nachman and Tilman Plehn and David Shih and Ramon Winterhalder},
	journal={SciPost Phys.},
	volume={13},
	pages={087},
	year={2022},
	publisher={SciPost},
	doi={10.21468/SciPostPhys.13.4.087},
	url={https://scipost.org/10.21468/SciPostPhys.13.4.087},
}

Cited by 10

Authors / Affiliations: mappings to Contributors and Organizations

See all Organizations.

Funders for the research work leading to this publication

Australian Research Council [ARC]
Deutsche Forschungsgemeinschaft / German Research FoundationDeutsche Forschungsgemeinschaft [DFG]
Fonds De La Recherche Scientifique - FNRS (FNRS) (through Organization: Fonds National de la Recherche Scientifique [FNRS])
United States Department of Energy [DOE]