DOAJ Open Access 2024

Finetuning foundation models for joint analysis optimization in High Energy Physics

Matthias Vigl Nicole Hartman Lukas Heinrich

Abstrak

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.

Topik & Kata Kunci

Computer engineering. Computer hardware Electronic computers. Computer science

Penulis (3)

Matthias Vigl

Nicole Hartman

Lukas Heinrich

Format Sitasi

APA MLA BibTeX

Vigl, M., Hartman, N., Heinrich, L. (2024). Finetuning foundation models for joint analysis optimization in High Energy Physics. https://doi.org/10.1088/2632-2153/ad55a3

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →

Lihat di Sumber doi.org/10.1088/2632-2153/ad55a3

Informasi Jurnal

Tahun Terbit: 2024
Sumber Database: DOAJ
DOI: 10.1088/2632-2153/ad55a3
Akses: Open Access ✓