A normalized autoencoder for LHC triggers

Dillon, Barry M.; Favaro, Luigi; Plehn, Tilman; Sorrenson, Peter; Krämer, Michael

doi:10.21468/SciPostPhysCore.6.4.074

SciPost Physics Core

A normalized autoencoder for LHC triggers

Barry M. Dillon, Luigi Favaro, Tilman Plehn, Peter Sorrenson, Michael Krämer

SciPost Phys. Core 6, 074 (2023) · published 3 November 2023

doi: 10.21468/SciPostPhysCore.6.4.074
pdf
Submissions/Reports

Abstract

Autoencoders are an effective analysis tool for the LHC, as they represent one of its main goal of finding physics beyond the Standard Model. The key challenge is that out-of-distribution anomaly searches based on the compressibility of features do not apply to the LHC, while existing density-based searches lack performance. We present the first autoencoder which identifies anomalous jets symmetrically in the directions of higher and lower complexity. The normalized autoencoder combines a standard bottleneck architecture with a well-defined probabilistic description. It works better than all available autoencoders for top vs QCD jets and reliably identifies different dark-jet signals.

TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhysCore.6.4.074
TI  - A normalized autoencoder for LHC triggers
PY  - 2023/11/03
UR  - https://www.scipost.org/SciPostPhysCore.6.4.074
JF  - SciPost Physics Core
JA  - SciPost Phys. Core
VL  - 6
IS  - 4
SP  - 074
A1  - Dillon, Barry M.
AU  - Favaro, Luigi
AU  - Plehn, Tilman
AU  - Sorrenson, Peter
AU  - Krämer, Michael
AB  - Autoencoders are an effective analysis tool for the LHC, as they represent one of its main goal of finding physics beyond the Standard Model. The key challenge is that out-of-distribution anomaly searches based on the compressibility of features do not apply to the LHC, while existing density-based searches lack performance. We present the first autoencoder which identifies anomalous jets symmetrically in the directions of higher and lower complexity. The normalized autoencoder combines a standard bottleneck architecture with a well-defined probabilistic description. It works better than all available autoencoders for top vs QCD jets and reliably identifies different dark-jet signals.
ER  -

@Article{10.21468/SciPostPhysCore.6.4.074,
	title={{A normalized autoencoder for LHC triggers}},
	author={Barry M. Dillon and Luigi Favaro and Tilman Plehn and Peter Sorrenson and Michael Krämer},
	journal={SciPost Phys. Core},
	volume={6},
	pages={074},
	year={2023},
	publisher={SciPost},
	doi={10.21468/SciPostPhysCore.6.4.074},
	url={https://scipost.org/10.21468/SciPostPhysCore.6.4.074},
}

Cited by 4

Authors / Affiliations: mappings to Contributors and Organizations

See all Organizations.

¹ Barry M. Dillon,
¹ Luigi Favaro,
¹ Tilman Plehn,
¹ Peter Sorrenson,
² Michael Krämer

Funder for the research work leading to this publication

Deutsche Forschungsgemeinschaft / German Research FoundationDeutsche Forschungsgemeinschaft [DFG]