The Machine Learning landscape of top taggers

Author:

Kasieczka Gregor1,Plehn Tilman2,Butter Anja2,Cranmer Kyle3,Debnath Dipsikha4,Dillon Barry M.5,Fairbairn Malcolm6,Faroughy Darius A.5,Fedorko Wojtek7,Gay Christophe7,Gouskos Loukas8,Kamenik Jernej Fesel59,Komiske Patrick10,Leiss Simon1,Lister Alison7,Macaluso Sebastian34,Metodiev Eric10,Moore Liam11,Nachman Benjamin1213,Nordström Karl1415,Pearkes Jannicke7,Qu Huilin8,Rath Yannik16,Rieger Marcel16,Shih David4,Thompson Jennifer2,Varma Sreedevi6

Affiliation:

1. University of Hamburg

2. Heidelberg University

3. New York University

4. Rutgers, The State University of New Jersey

5. Jožef Stefan Institute

6. King's College London

7. University of British Columbia

8. University of California, Santa Barbara

9. University of Ljubljana

10. Massachusetts Institute of Technology

11. Université catholique de Louvain

12. Lawrence Berkeley National Laboratory

13. University of California, Berkeley

14. Laboratory of Theoretical and High Energy Physics

15. National Institute for Subatomic Physics

16. RWTH Aachen University

Abstract

Based on the established task of identifying boosted, hadronically decaying top quarks, we compare a wide range of modern machine learning approaches. Unlike most established methods they rely on low-level input, for instance calorimeter output. While their network architectures are vastly different, their performance is comparatively similar. In general, we find that these new approaches are extremely powerful and great fun.

Funder

National Science Foundation

Nvidia

United States Department of Energy

Publisher

Stichting SciPost

Subject

General Physics and Astronomy

Cited by 148 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Triggering dark showers with conditional dual auto-encoders;Machine Learning: Science and Technology;2024-09-01

2. Generative Adversarial Networks in Business and Social Science;Applied Sciences;2024-08-23

3. Anomalies, representations, and self-supervision;SciPost Physics Core;2024-08-16

4. Jet rotational metrics;Journal of High Energy Physics;2024-08-06

5. OmniJet-α: the first cross-task foundation model for particle physics;Machine Learning: Science and Technology;2024-08-02

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3