End-to-end optimisation of HEP triggers
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915846631194624 |
|---|---|
| author | Hall, Noah Clarke Xiotidis, Ioannis Konstantinidis, Nikos Miller, David W. |
| author_facet | Hall, Noah Clarke Xiotidis, Ioannis Konstantinidis, Nikos Miller, David W. |
| contents | High-energy physics experiments face extreme data rates, requiring real-time trigger systems to reduce event throughput while preserving sensitivity to rare processes. Trigger systems are typically constructed as modular chains of sequentially optimised algorithms, including machine learning models. Each algorithm is optimised for a specific local objective with no guarantee of overall optimality. We instead formulate trigger design as a constrained end-to-end optimisation problem, treating all stages- including data encoding, denoising, clustering, and calibration- as components of a single differentiable system trained against a unified physics objective. The framework jointly optimises performance while incorporating physics and deployment constraints. We demonstrate this approach on a hardware multi-jet trigger inspired by the ATLAS High-Luminosity Large Hadron Collider design. Using Higgs boson pair production as a benchmark, we observe x2-4 improvement in true-positive rate at fixed false-positive rate, while preserving interpretable intermediate physics objects and monotonic calibration constraints. These results highlight end-to-end optimisation as a practical paradigm for next-generation real-time event selection systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_08428 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | End-to-end optimisation of HEP triggers Hall, Noah Clarke Xiotidis, Ioannis Konstantinidis, Nikos Miller, David W. High Energy Physics - Experiment High-energy physics experiments face extreme data rates, requiring real-time trigger systems to reduce event throughput while preserving sensitivity to rare processes. Trigger systems are typically constructed as modular chains of sequentially optimised algorithms, including machine learning models. Each algorithm is optimised for a specific local objective with no guarantee of overall optimality. We instead formulate trigger design as a constrained end-to-end optimisation problem, treating all stages- including data encoding, denoising, clustering, and calibration- as components of a single differentiable system trained against a unified physics objective. The framework jointly optimises performance while incorporating physics and deployment constraints. We demonstrate this approach on a hardware multi-jet trigger inspired by the ATLAS High-Luminosity Large Hadron Collider design. Using Higgs boson pair production as a benchmark, we observe x2-4 improvement in true-positive rate at fixed false-positive rate, while preserving interpretable intermediate physics objects and monotonic calibration constraints. These results highlight end-to-end optimisation as a practical paradigm for next-generation real-time event selection systems. |
| title | End-to-end optimisation of HEP triggers |
| topic | High Energy Physics - Experiment |
| url | https://arxiv.org/abs/2603.08428 |