Learning Symmetry-Independent Jet Representations via Jet-Based Joint Embedding Predictive Architecture

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Katel, Subash, Li, Haoyang, Zhao, Zihan, Kansal, Raghav, Mokhtar, Farouk, Duarte, Javier
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