Combining resonant and tail-based anomaly detection
In many well-motivated models of the electroweak scale, cascade decays of new particles can result in highly boosted hadronic resonances (e.g., 𝑍/𝑊/ℎ). This can make these models rich and promising targets for recently developed resonant anomaly detection methods powered by modern machine learning....
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
23 May 2024
|
| In: |
Physical review
Year: 2024, Volume: 109, Issue: 9, Pages: 096031-1-096031-13 |
| ISSN: | 2470-0029 |
| DOI: | 10.1103/PhysRevD.109.096031 |
| Online Access: | Verlag, kostenfrei, Volltext: https://doi.org/10.1103/PhysRevD.109.096031 Verlag, kostenfrei, Volltext: https://link.aps.org/doi/10.1103/PhysRevD.109.096031 
|
| Author Notes: | Gerrit Bickendorf, Manuel Drees, Gregor Kasieczka, Claudius Krause, and David Shih |
| Summary: | In many well-motivated models of the electroweak scale, cascade decays of new particles can result in highly boosted hadronic resonances (e.g., 𝑍/𝑊/ℎ). This can make these models rich and promising targets for recently developed resonant anomaly detection methods powered by modern machine learning. We demonstrate this using the state-of-the-art classifying anomalies through outer density estimation (cathode) method applied to supersymmetry scenarios with gluino pair production. We show that cathode, despite being model agnostic, is nevertheless competitive with dedicated cut-based searches, while simultaneously covering a much wider region of parameter space. The gluino events also populate the tails of the missing energy and 𝐻𝑇 distributions, making this a novel combination of resonant and tail-based anomaly detection. |
|---|---|
| Item Description: | Gesehen am 25.11.2024 |
| Physical Description: | Online Resource |
| ISSN: | 2470-0029 |
| DOI: | 10.1103/PhysRevD.109.096031 |