Learning Symmetry-Independent Jet Representations via Jet-Based Joint Embedding Predictive Architecture
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916519698497536 |
|---|---|
| author | Katel, Subash Li, Haoyang Zhao, Zihan Kansal, Raghav Mokhtar, Farouk Duarte, Javier |
| author_facet | Katel, Subash Li, Haoyang Zhao, Zihan Kansal, Raghav Mokhtar, Farouk Duarte, Javier |
| contents | In high energy physics, self-supervised learning (SSL) methods have the potential to aid in the creation of machine learning models without the need for labeled datasets for a variety of tasks, including those related to jets -- narrow sprays of particles produced by quarks and gluons in high energy particle collisions. This study introduces an approach to learning jet representations without hand-crafted augmentations using a jet-based joint embedding predictive architecture (J-JEPA), which aims to predict various physical targets from an informative context. As our method does not require hand-crafted augmentation like other common SSL techniques, J-JEPA avoids introducing biases that could harm downstream tasks. Since different tasks generally require invariance under different augmentations, this training without hand-crafted augmentation enables versatile applications, offering a pathway toward a cross-task foundation model. We finetune the representations learned by J-JEPA for jet tagging and benchmark them against task-specific representations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_05333 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Symmetry-Independent Jet Representations via Jet-Based Joint Embedding Predictive Architecture Katel, Subash Li, Haoyang Zhao, Zihan Kansal, Raghav Mokhtar, Farouk Duarte, Javier High Energy Physics - Phenomenology Machine Learning High Energy Physics - Experiment Data Analysis, Statistics and Probability In high energy physics, self-supervised learning (SSL) methods have the potential to aid in the creation of machine learning models without the need for labeled datasets for a variety of tasks, including those related to jets -- narrow sprays of particles produced by quarks and gluons in high energy particle collisions. This study introduces an approach to learning jet representations without hand-crafted augmentations using a jet-based joint embedding predictive architecture (J-JEPA), which aims to predict various physical targets from an informative context. As our method does not require hand-crafted augmentation like other common SSL techniques, J-JEPA avoids introducing biases that could harm downstream tasks. Since different tasks generally require invariance under different augmentations, this training without hand-crafted augmentation enables versatile applications, offering a pathway toward a cross-task foundation model. We finetune the representations learned by J-JEPA for jet tagging and benchmark them against task-specific representations. |
| title | Learning Symmetry-Independent Jet Representations via Jet-Based Joint Embedding Predictive Architecture |
| topic | High Energy Physics - Phenomenology Machine Learning High Energy Physics - Experiment Data Analysis, Statistics and Probability |
| url | https://arxiv.org/abs/2412.05333 |