| Autor: |
Matthias Vigl, Nicole Hartman, Lukas Heinrich |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Machine Learning: Science and Technology, Vol 5, Iss 2, p 025075 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2632-2153 |
| DOI: |
10.1088/2632-2153/ad55a3 |
| Popis: |
In this work we demonstrate that significant gains in performance and data efficiency can be achieved in High Energy Physics (HEP) by moving beyond the standard paradigm of sequential optimization or reconstruction and analysis components. We conceptually connect HEP reconstruction and analysis to modern machine learning workflows such as pretraining, finetuning, domain adaptation and high-dimensional embedding spaces and quantify the gains in the example usecase of searches of heavy resonances decaying via an intermediate di-Higgs system to four b -jets. To our knowledge this is the first example of a low-level feature extraction network finetuned for a downstream HEP analysis objective. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
