Domain Adaptation against Background Sculpting in Anomaly Detection at the LHC

Abstract

Weakly supervised anomaly detection has been shown to be an effective tool for model-agnostic searches for new physics, especially in the context of resonance searches. However, correlations between the anomaly score and the resonant mass can distort the background distribution after selecting on the anomaly score, complicating background estimation from the sidebands. To mitigate this background sculpting, we propose a domain-adaptation-based decorrelation of the anomaly score from the resonant mass. We study this approach using the LHC Olympics R&D data set and several weakly supervised anomaly detection methods. We find that domain adaptation can substantially reduce background sculpting while largely preserving the anomaly detection performance. When correlations between the input features and the resonant mass degrade the original method's performance, domain adaptation can also recover sensitivity.

On the importance of cosmic-ray background in the Atomki anomaly
Hicham Benmansour, Gianluigi Boca, Gianluca Cavoto +8
arXiv16 Sep 2026PreprintCC BY 4.0Full textApplied physics & instrumentation High-energy & particle physicsarXiv
Anomaly detection for multijet scenarios
Gregor Kasieczka, Sung Hak Lim, Louis Moureaux +3
arXiv14 Oct 2026PreprintCC BY 4.0Full textComputational physics High-energy & particle physicsarXiv
Model-independent searches and anomaly detection at the CMS experiment
Tamas Almos Vami, for the CMS Collaboration
arXiv22 Sep 2026PreprintCC BY 4.0Full textHigh-energy & particle physicsarXiv
Predictive Maintenance at the Edge: An Embedded Anomaly Detection Pipeline Trained with Quantum Optimization
Filipe Chagas Ferraz
arXiv29 Oct 2026PreprintarXiv licenceFull textQuantum physics & quantum informationarXiv
Quantum anomaly detection in real scarce data
Emanuele Casciaro, Fabio Mascherpa, Alfonso Amendola +1
arXiv7 Oct 2026PreprintCC BY 4.0Full textQuantum physics & quantum informationarXiv

Cite

BibTeX RIS

BibTeX

@misc{benne2026domain,
  title = {{Domain Adaptation against Background Sculpting in Anomaly Detection at the LHC}},
  author = {Vincent Benne and Marie Hein and Michael Krämer and Humberto Reyes-Gonzalez and Philipp Soldin and Christopher Wiebusch},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.17659},
  eprint = {2609.17659},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.17659},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Domain Adaptation against Background Sculpting in Anomaly Detection at the LHC
AU  - Vincent Benne
AU  - Marie Hein
AU  - Michael Krämer
AU  - Humberto Reyes-Gonzalez
AU  - Philipp Soldin
AU  - Christopher Wiebusch
PY  - 2026
DA  - 2026/09/15
PB  - arXiv
DO  - 10.48550/arxiv.2609.17659
UR  - https://arxiv.org/abs/2609.17659
AB  - Weakly supervised anomaly detection has been shown to be an effective tool for model-agnostic searches for new physics, especially in the context of resonance searches. However, correlations between the anomaly score and the resonant mass can distort the background distribution after selecting on the anomaly score, complicating background estimation from the sidebands. To mitigate this background sculpting, we propose a domain-adaptation-based decorrelation of the anomaly score from the resonant mass. We study this approach using the LHC Olympics R&D data set and several weakly supervised anomaly detection methods. We find that domain adaptation can substantially reduce background sculpting while largely preserving the anomaly detection performance. When correlations between the input features and the resonant mass degrade the original method's performance, domain adaptation can also recover sensitivity.
ER  -

Abstract

Related

Cite