J. A. Aguilar-Saavedra, E. Arganda, F. R. Joaquim, R. M. Sandá Seoane, J. F. Seabra
{"title":"Gradient boosting MUST taggers for highly-boosted jets","authors":"J. A. Aguilar-Saavedra, E. Arganda, F. R. Joaquim, R. M. Sandá Seoane, J. F. Seabra","doi":"10.1140/epjp/s13360-024-05781-0","DOIUrl":null,"url":null,"abstract":"<div><p>The Mass Unspecific Supervised Tagging (MUST) method has proven to be successful in implementing generic jet taggers capable of discriminating various signals over a wide range of jet masses. We implement the MUST concept by using eXtreme Gradient Boosting (<span>XGBoost</span>) classifiers instead of neural networks (NNs) as previously done. We build both fully-generic and specific multi-pronged taggers, to identify 2, 3, and/or 4-pronged signals from SM QCD background. We show that <span>XGBoost</span>-based taggers are not only easier to optimize and much faster than those based in NNs, but also show quite similar performance, even when testing with signals not used in training. Therefore, they provide a quite efficient alternative machine-learning implementation for generic jet taggers.</p></div>","PeriodicalId":792,"journal":{"name":"The European Physical Journal Plus","volume":"139 11","pages":""},"PeriodicalIF":2.8000,"publicationDate":"2024-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1140/epjp/s13360-024-05781-0.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"The European Physical Journal Plus","FirstCategoryId":"4","ListUrlMain":"https://link.springer.com/article/10.1140/epjp/s13360-024-05781-0","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PHYSICS, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
The Mass Unspecific Supervised Tagging (MUST) method has proven to be successful in implementing generic jet taggers capable of discriminating various signals over a wide range of jet masses. We implement the MUST concept by using eXtreme Gradient Boosting (XGBoost) classifiers instead of neural networks (NNs) as previously done. We build both fully-generic and specific multi-pronged taggers, to identify 2, 3, and/or 4-pronged signals from SM QCD background. We show that XGBoost-based taggers are not only easier to optimize and much faster than those based in NNs, but also show quite similar performance, even when testing with signals not used in training. Therefore, they provide a quite efficient alternative machine-learning implementation for generic jet taggers.
质量无特定监督标记（MUST）方法已被证明能够成功地实现通用喷流标记器，能够在广泛的喷流质量范围内分辨各种信号。我们通过使用极端梯度提升（XGBoost）分类器来实现 MUST 概念，而不是像以前那样使用神经网络（NN）。我们建立了完全通用的和特定的多管齐下标记器，以便从 SM QCD 背景中识别出 2、3 和/或 4 管齐下信号。我们的研究表明，基于 XGBoost 的标记器不仅比基于 NN 的标记器更容易优化、速度更快，而且即使在使用训练中未使用的信号进行测试时，也能表现出相当相似的性能。因此，它们为通用射流标记器提供了一种相当高效的替代机器学习实现方法。
期刊介绍：
The aims of this peer-reviewed online journal are to distribute and archive all relevant material required to document, assess, validate and reconstruct in detail the body of knowledge in the physical and related sciences.
The scope of EPJ Plus encompasses a broad landscape of fields and disciplines in the physical and related sciences - such as covered by the topical EPJ journals and with the explicit addition of geophysics, astrophysics, general relativity and cosmology, mathematical and quantum physics, classical and fluid mechanics, accelerator and medical physics, as well as physics techniques applied to any other topics, including energy, environment and cultural heritage.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
