Semi-visible jets, energy-based models, and self-supervision
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909479006633984 |
|---|---|
| author | Favaro, Luigi Krämer, Michael Modak, Tanmoy Plehn, Tilman Rüschkamp, Jan |
| author_facet | Favaro, Luigi Krämer, Michael Modak, Tanmoy Plehn, Tilman Rüschkamp, Jan |
| contents | We present DarkCLR, a novel framework for detecting semi-visible jets at the LHC. DarkCLR uses a self-supervised contrastive-learning approach to create observables that are approximately invariant under relevant transformations. We use background-enhanced data to create a sensitive representation and evaluate the representations using a CLR-inspired anomaly score and a normalized autoencoder as density estimators. Our results show a remarkable sensitivity for a wide range of semi-visible jets and are more robust than a supervised classifier trained on a specific signal. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_03067 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Semi-visible jets, energy-based models, and self-supervision Favaro, Luigi Krämer, Michael Modak, Tanmoy Plehn, Tilman Rüschkamp, Jan High Energy Physics - Phenomenology We present DarkCLR, a novel framework for detecting semi-visible jets at the LHC. DarkCLR uses a self-supervised contrastive-learning approach to create observables that are approximately invariant under relevant transformations. We use background-enhanced data to create a sensitive representation and evaluate the representations using a CLR-inspired anomaly score and a normalized autoencoder as density estimators. Our results show a remarkable sensitivity for a wide range of semi-visible jets and are more robust than a supervised classifier trained on a specific signal. |
| title | Semi-visible jets, energy-based models, and self-supervision |
| topic | High Energy Physics - Phenomenology |
| url | https://arxiv.org/abs/2312.03067 |