Event-Based Anomaly Detection for Searches for New Physics
This paper discusses model-agnostic searches for new physics at the Large Hadron Collider using anomaly-detection techniques for the identification of event signatures that deviate from the Standard Model (SM). We investigate anomaly detection in the context of a machine-learning approach based on a...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Universe |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-1997/8/10/494 |
| _version_ | 1827647859971850240 |
|---|---|
| author | Sergei Chekanov Walter Hopkins |
| author_facet | Sergei Chekanov Walter Hopkins |
| author_sort | Sergei Chekanov |
| collection | DOAJ |
| description | This paper discusses model-agnostic searches for new physics at the Large Hadron Collider using anomaly-detection techniques for the identification of event signatures that deviate from the Standard Model (SM). We investigate anomaly detection in the context of a machine-learning approach based on autoencoders. The analysis uses Monte Carlo simulations for the SM background and several selected exotic models. We also investigate the input space for the event-based anomaly detection and illustrate the shapes of invariant masses in the outlier region which will be used to perform searches for resonant phenomena beyond the SM. Challenges and conceptual limitations of this approach are discussed. |
| first_indexed | 2024-03-09T19:25:27Z |
| format | Article |
| id | doaj.art-f9bb0645a58c4a35a703403e3014a995 |
| institution | Directory Open Access Journal |
| issn | 2218-1997 |
| language | English |
| last_indexed | 2024-03-09T19:25:27Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Universe |
| spelling | doaj.art-f9bb0645a58c4a35a703403e3014a9952023-11-24T03:01:11ZengMDPI AGUniverse2218-19972022-09-0181049410.3390/universe8100494Event-Based Anomaly Detection for Searches for New PhysicsSergei Chekanov0Walter Hopkins1Argonne National Laboratory, HEP Division, 9700 S. Cass Avenue, Lemont, IL 60439, USAArgonne National Laboratory, HEP Division, 9700 S. Cass Avenue, Lemont, IL 60439, USAThis paper discusses model-agnostic searches for new physics at the Large Hadron Collider using anomaly-detection techniques for the identification of event signatures that deviate from the Standard Model (SM). We investigate anomaly detection in the context of a machine-learning approach based on autoencoders. The analysis uses Monte Carlo simulations for the SM background and several selected exotic models. We also investigate the input space for the event-based anomaly detection and illustrate the shapes of invariant masses in the outlier region which will be used to perform searches for resonant phenomena beyond the SM. Challenges and conceptual limitations of this approach are discussed.https://www.mdpi.com/2218-1997/8/10/494anomaly detectionRMMdeep learningautoencodermachine learning |
| spellingShingle | Sergei Chekanov Walter Hopkins Event-Based Anomaly Detection for Searches for New Physics Universe anomaly detection RMM deep learning autoencoder machine learning |
| title | Event-Based Anomaly Detection for Searches for New Physics |
| title_full | Event-Based Anomaly Detection for Searches for New Physics |
| title_fullStr | Event-Based Anomaly Detection for Searches for New Physics |
| title_full_unstemmed | Event-Based Anomaly Detection for Searches for New Physics |
| title_short | Event-Based Anomaly Detection for Searches for New Physics |
| title_sort | event based anomaly detection for searches for new physics |
| topic | anomaly detection RMM deep learning autoencoder machine learning |
| url | https://www.mdpi.com/2218-1997/8/10/494 |
| work_keys_str_mv | AT sergeichekanov eventbasedanomalydetectionforsearchesfornewphysics AT walterhopkins eventbasedanomalydetectionforsearchesfornewphysics |