Search for New Phenomena in Two-Body Invariant Mass Distributions Using Unsupervised Machine Learning for Anomaly Detection at √s = 13 TeV with the ATLAS Detector
Research output: Contribution to journal › Research article › Contributed › peer-review
Contributors
- Aix-Marseille Université
- University of Oklahoma
- University of Massachusetts
- University of Göttingen
- Royal Holloway University of London
- Tel Aviv University
- Technion-Israel Institute of Technology
- Argonne National Laboratory
- Pontificia Universidad Católica de Chile
- King's College London (KCL)
- Laboratoire d'Annecy-le-Vieux de Physique des Particules LAPP
- AGH University of Science and Technology
- University of Toronto
- Brandeis University
- Northern Illinois University
- Istanbul University
- University of Geneva
- Rutherford Appleton Laboratory
- University of California at Santa Cruz
- Université Paris-Saclay
- Institute for High Energy Physics
- University of Pavia
- Radboud University Nijmegen
- Alexandru Ioan Cuza University of Iaşi
- Laboratório de Instrumentação e Física Experimental de Partículas
- Universidad Autónoma de Madrid
Abstract
Searches for new resonances are performed using an unsupervised anomaly-detection technique. Events with at least one electron or muon are selected from 140 fb−1 of pp collisions at √s ¼ 13 TeV recorded by ATLAS at the Large Hadron Collider. The approach involves training an autoencoder on data, and subsequently defining anomalous regions based on the reconstruction loss of the decoder. Studies focus on nine invariant mass spectra that contain pairs of objects consisting of one light jet or b jet and either one lepton (e; μ), photon, or second light jet or b jet in the anomalous regions. No significant deviations from the background hypotheses are observed. Limits on contributions from generic Gaussian signals with various widths of the resonance mass are obtained for nine invariant masses in the anomalous regions.
Details
| Original language | English |
|---|---|
| Article number | 081801 |
| Pages (from-to) | 1-23 |
| Number of pages | 23 |
| Journal | Physical review letters |
| Volume | 132 |
| Issue number | 8 |
| Publication status | Published - 20 Feb 2024 |
| Peer-reviewed | Yes |
External IDs
| PubMed | 38457710 |
|---|