The Pareto Frontier of Resilient Jet Tagging
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908922567196672 |
|---|---|
| author | Gambhir, Rikab LeBlanc, Matt Zhou, Yuanchen |
| author_facet | Gambhir, Rikab LeBlanc, Matt Zhou, Yuanchen |
| contents | Classifying hadronic jets using their constituents' kinematic information is a critical task in modern high-energy collider physics. Often, classifiers are designed by targeting the best performance using metrics such as accuracy, AUC, or rejection rates. However, the use of a single metric can lead to the use of architectures that are more model-dependent than competitive alternatives, leading to potential uncertainty and bias in analysis. We explore such trade-offs and demonstrate the consequences of using networks with high performance metrics but low resilience. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19431 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Pareto Frontier of Resilient Jet Tagging Gambhir, Rikab LeBlanc, Matt Zhou, Yuanchen High Energy Physics - Phenomenology Machine Learning High Energy Physics - Experiment Classifying hadronic jets using their constituents' kinematic information is a critical task in modern high-energy collider physics. Often, classifiers are designed by targeting the best performance using metrics such as accuracy, AUC, or rejection rates. However, the use of a single metric can lead to the use of architectures that are more model-dependent than competitive alternatives, leading to potential uncertainty and bias in analysis. We explore such trade-offs and demonstrate the consequences of using networks with high performance metrics but low resilience. |
| title | The Pareto Frontier of Resilient Jet Tagging |
| topic | High Energy Physics - Phenomenology Machine Learning High Energy Physics - Experiment |
| url | https://arxiv.org/abs/2509.19431 |