GAN-AE: an anomaly detection algorithm for New Physics search in LHC data
Abstract In recent years, interest has grown in alternative strategies for the search for New Physics beyond the Standard Model. One envisaged solution lies in the development of anomaly detection algorithms based on unsupervised machine learning techniques. In this paper, we propose a new Generativ...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-11-01
|
| Series: | European Physical Journal C: Particles and Fields |
| Online Access: | https://doi.org/10.1140/epjc/s10052-023-12169-4 |
| _version_ | 1797233359210938368 |
|---|---|
| author | Louis Vaslin Vincent Barra Julien Donini |
| author_facet | Louis Vaslin Vincent Barra Julien Donini |
| author_sort | Louis Vaslin |
| collection | DOAJ |
| description | Abstract In recent years, interest has grown in alternative strategies for the search for New Physics beyond the Standard Model. One envisaged solution lies in the development of anomaly detection algorithms based on unsupervised machine learning techniques. In this paper, we propose a new Generative Adversarial Network-based auto-encoder model that allows both anomaly detection and model-independent background modeling. This algorithm can be integrated with other model-independent tools in a complete heavy resonance search strategy. The proposed strategy has been tested on the LHC Olympics 2020 dataset with promising results. |
| first_indexed | 2024-03-11T11:01:42Z |
| format | Article |
| id | doaj.art-ec575b6f34944a99b38a681447954518 |
| institution | Directory Open Access Journal |
| issn | 1434-6052 |
| language | English |
| last_indexed | 2024-04-24T16:14:55Z |
| publishDate | 2023-11-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Physical Journal C: Particles and Fields |
| spelling | doaj.art-ec575b6f34944a99b38a6814479545182024-03-31T11:30:45ZengSpringerOpenEuropean Physical Journal C: Particles and Fields1434-60522023-11-0183111810.1140/epjc/s10052-023-12169-4GAN-AE: an anomaly detection algorithm for New Physics search in LHC dataLouis Vaslin0Vincent Barra1Julien Donini2Université Clermont-Auvergne, CNRS, LPCUniversité Clermont-Auvergne, CNRS, Mines de Saint-Étienne, Clermont-Auvergne-INP, LIMOSUniversité Clermont-Auvergne, CNRS, LPCAbstract In recent years, interest has grown in alternative strategies for the search for New Physics beyond the Standard Model. One envisaged solution lies in the development of anomaly detection algorithms based on unsupervised machine learning techniques. In this paper, we propose a new Generative Adversarial Network-based auto-encoder model that allows both anomaly detection and model-independent background modeling. This algorithm can be integrated with other model-independent tools in a complete heavy resonance search strategy. The proposed strategy has been tested on the LHC Olympics 2020 dataset with promising results.https://doi.org/10.1140/epjc/s10052-023-12169-4 |
| spellingShingle | Louis Vaslin Vincent Barra Julien Donini GAN-AE: an anomaly detection algorithm for New Physics search in LHC data European Physical Journal C: Particles and Fields |
| title | GAN-AE: an anomaly detection algorithm for New Physics search in LHC data |
| title_full | GAN-AE: an anomaly detection algorithm for New Physics search in LHC data |
| title_fullStr | GAN-AE: an anomaly detection algorithm for New Physics search in LHC data |
| title_full_unstemmed | GAN-AE: an anomaly detection algorithm for New Physics search in LHC data |
| title_short | GAN-AE: an anomaly detection algorithm for New Physics search in LHC data |
| title_sort | gan ae an anomaly detection algorithm for new physics search in lhc data |
| url | https://doi.org/10.1140/epjc/s10052-023-12169-4 |
| work_keys_str_mv | AT louisvaslin ganaeananomalydetectionalgorithmfornewphysicssearchinlhcdata AT vincentbarra ganaeananomalydetectionalgorithmfornewphysicssearchinlhcdata AT juliendonini ganaeananomalydetectionalgorithmfornewphysicssearchinlhcdata |