Parton labeling without matching: unveiling emergent labelling capabilities in regression models

IF 4.2 2区 物理与天体物理 Q2 PHYSICS, PARTICLES & FIELDS
Shikai Qiu, Shuo Han, Xiangyang Ju, Benjamin Nachman, Haichen Wang
{"title":"Parton labeling without matching: unveiling emergent labelling capabilities in regression models","authors":"Shikai Qiu,&nbsp;Shuo Han,&nbsp;Xiangyang Ju,&nbsp;Benjamin Nachman,&nbsp;Haichen Wang","doi":"10.1140/epjc/s10052-023-11809-z","DOIUrl":null,"url":null,"abstract":"<div><p>Parton labeling methods are widely used when reconstructing collider events with top quarks or other massive particles. State-of-the-art techniques are based on machine learning and require training data with events that have been matched using simulations with truth information. In nature, there is no unique matching between partons and final state objects due to the properties of the strong force and due to acceptance effects. We propose a new approach to parton labeling that circumvents these challenges by recycling regression models. The final state objects that are most relevant for a regression model to predict the properties of a particular top quark are assigned to said parent particle without having any parton-matched training data. This approach is demonstrated using simulated events with top quarks and outperforms the widely-used <span>\\(\\chi ^2\\)</span> method.</p></div>","PeriodicalId":788,"journal":{"name":"The European Physical Journal C","volume":"83 7","pages":""},"PeriodicalIF":4.2000,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1140/epjc/s10052-023-11809-z.pdf","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"The European Physical Journal C","FirstCategoryId":"4","ListUrlMain":"https://link.springer.com/article/10.1140/epjc/s10052-023-11809-z","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PHYSICS, PARTICLES & FIELDS","Score":null,"Total":0}
引用次数: 2

Abstract

Parton labeling methods are widely used when reconstructing collider events with top quarks or other massive particles. State-of-the-art techniques are based on machine learning and require training data with events that have been matched using simulations with truth information. In nature, there is no unique matching between partons and final state objects due to the properties of the strong force and due to acceptance effects. We propose a new approach to parton labeling that circumvents these challenges by recycling regression models. The final state objects that are most relevant for a regression model to predict the properties of a particular top quark are assigned to said parent particle without having any parton-matched training data. This approach is demonstrated using simulated events with top quarks and outperforms the widely-used \(\chi ^2\) method.

没有匹配的Parton标记:揭示回归模型中的紧急标记能力
在用顶夸克或其他大质量粒子重建对撞机事件时,广泛使用帕顿标记方法。最先进的技术是基于机器学习的,需要训练数据与事件相匹配,使用模拟与真实信息相匹配。在自然界中,由于强作用力的性质和接受效应,部分与最终状态对象之间不存在唯一的匹配。我们提出了一种新的parton标记方法,通过循环回归模型来规避这些挑战。与回归模型预测特定顶夸克性质最相关的最终状态对象被分配给该母粒子,而无需任何部分匹配的训练数据。这种方法是用顶夸克模拟事件来证明的,并且优于广泛使用的\(\chi ^2\)方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
The European Physical Journal C
The European Physical Journal C 物理-物理:粒子与场物理
CiteScore
8.10
自引率
15.90%
发文量
1008
审稿时长
2-4 weeks
期刊介绍: Experimental Physics I: Accelerator Based High-Energy Physics Hadron and lepton collider physics Lepton-nucleon scattering High-energy nuclear reactions Standard model precision tests Search for new physics beyond the standard model Heavy flavour physics Neutrino properties Particle detector developments Computational methods and analysis tools Experimental Physics II: Astroparticle Physics Dark matter searches High-energy cosmic rays Double beta decay Long baseline neutrino experiments Neutrino astronomy Axions and other weakly interacting light particles Gravitational waves and observational cosmology Particle detector developments Computational methods and analysis tools Theoretical Physics I: Phenomenology of the Standard Model and Beyond Electroweak interactions Quantum chromo dynamics Heavy quark physics and quark flavour mixing Neutrino physics Phenomenology of astro- and cosmoparticle physics Meson spectroscopy and non-perturbative QCD Low-energy effective field theories Lattice field theory High temperature QCD and heavy ion physics Phenomenology of supersymmetric extensions of the SM Phenomenology of non-supersymmetric extensions of the SM Model building and alternative models of electroweak symmetry breaking Flavour physics beyond the SM Computational algorithms and tools...etc.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信