Trials factor for semi-supervised NN classifiers in searches for narrow resonances at the LHC
Benjamin Lieberman, Salah-Eddine Dahbi, Andreas Crivellin, Finn Stevenson, Nidhi Tripathi, Mukesh Kumar, Bruce Mellado
SciPost Phys. Core 7, 073 (2024) · published 13 November 2024
- doi: 10.21468/SciPostPhysCore.7.4.073
- Submissions/Reports
Abstract
To mitigate the model dependencies of searches for new narrow resonances at the Large Hadron Collider (LHC), semi-supervised Neural Networks (NNs) can be used. Unlike fully supervised classifiers these models introduce an additional look-elsewhere effect in the process of optimising thresholds on the response distribution. We perform a frequentist study to quantify this effect, in the form of a trials factor. As an example, we consider simulated $Z\gamma$ data to perform narrow resonance searches using semi-supervised NN classifiers. The results from this analysis provide substantiation that the look-elsewhere effect induced by the semi-supervised NN is under control.
Authors / Affiliations: mappings to Contributors and Organizations
See all Organizations.- 1 2 Benjamin Lieberman,
- 1 3 Salah-Eddine Dahbi,
- 4 5 Andreas Crivellin,
- 1 2 Finn Stevenson,
- 1 2 Nidhi Tripathi,
- 1 Mukesh Kumar,
- 1 2 Bruce Mellado
- 1 University of the Witwatersrand
- 2 National Research Foundation
- 3 中央研究院物理研究所 / Institute of Physics, Academia Sinica
- 4 Paul Scherrer Institute [PSI]
- 5 Universität Zürich / University of Zurich [UZH]