[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127683-en":3,"doc-seo-127683-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},127683,962084925782,"Ava Thompson","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Jet Substructure in the Era of Machine Learning - Dissertation Action/Completeness Phrase","Jet Substructure in the Era of Machine Learning presents methods for classifying and characterizing jets from high-energy physics using modern machine-learning architectures. The work addresses multi-prong jet classification with high-level and low-level models, compares dense networks, convolutional networks, transformers, and physics-inspired networks, and studies topology dependence and multi-class to binary strategies. It further introduces jet rotational metrics with symmetry-oriented similarity measures. Finally, it treats systematic uncertainties in LHC data using Gaussian process regression and Bayesian experimental design to estimate efficiencies.","UC Irvine  \nUC Irvine Electronic Theses and Dissertations  \nTitle  \nJet Substructure in the Era of Machine Learning  \nPermalink  \n[https://escholarship.org/uc/item/65d6n1bq](https://escholarship.org/uc/item/65d6n1bq)  \nAuthor  \nRomero, Alexis  \nPublication Date 2023  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA,  \nIRVINE  \nJet Substructure in the Era of Machine Learning  \nDISSERTATION  \nsubmitted in partial satisfaction of the requirements  \nfor the degree of  \nDOCTOR OF PHILOSOPHY  \nin Physics  \nby  \nAlexis Romero  \nDissertation Committee: Professor Daniel Whiteson, Chair Professor Michael Ratz  \nProfessor Arvind Rajaraman  \n© 2023 Alexis Romero  \nDEDICATION  \nTo Freja.  \nTABLE OF CONTENTS  \nPage  \nLIST OF FIGURES vi  \nLIST OF TABLES xi  \nLIST OF ALGORITHMS xii  \nACKNOWLEDGMENTS xiii  \nVITA xiv  \nABSTRACT OF THE DISSERTATION xvi  \n1 Introduction 1  \n2 Deep Learning and High-Energy Physics 4  \n2.1 Jets at the LHC .................................. 6  \n2.1.1 High-Level Variables ........................... 8  \n2.1.2 Current High-Level Techniques: Dense Neural Networks (DNNs) ... 11  \n2.1.3 Low-Level Data .............................. 13  \n2.1.4 Convolutional Neural Networks (CNNs) ................ 14  \n2.1.5 Transformers ............................... 15  \n2.1.6 Physics-Inspired Networks ........................ 19  \n2.2 IRC-Safety ..................................... 20  \n3 Multi-Prong Jet Classification 23  \n3.1 Introduction .................................... 23  \n3.2 Dataset ...................................... 25  \n3.3 High-Level Models ................................ 28  \n3.4 Low-Level Models ................................. 30  \n3.4.1 Particle-Flow Network .......................... 30  \n3.4.2 Transformer ................................ 31  \n3.5 Performance .................................... 31  \n3.6 Closing the Performance Gap .......................... 34  \n3.6.1 Adding Energy-Flow Polynomials .................... 34  \n3.6.2 Feature Selection ............................. 35  \n3.7 Topology Dependence ............................... 42  \n3.8 Multi-Class to Binary Classification ....................... 47  \n3.9 Discussion ..................................... 49  \n4 Jet Rotational Metrics 52  \n4.1 Introduction .................................... 52  \n4.2 Similarity Measure ................................ 55  \n4.3 Gauging Cn Rotational Symmetry ........................ 57  \n4.4 Multi-Prong Jet Classification .......................... 59  \n4.4.1 Feature Selection ............................. 63  \n4.5 Discussion ..................................... 65  \n5 Systematic Uncertainties in LHC data 67  \n5.1 Introduction .................................... 67  \n5.2 Systematic Uncertainties ............................. 69  \n5.3 Gaussian Process Regression ........................... 71  \n5.3.1 Including Derivative Information .................... 75  \n5.3.2 Efficient Gaussian Process Regression with Approximated Gradients . 77  \n5.4 Bayesian Experimental Design .......................... 78  \n5.4.1 Utility ................................... 79  \n5.4.2 Choice of Utility Input .......................... 80  \n5.4.3 Updating the Beliefs About the Model ................. 81  \n5.5 Simple 1D Toy Model ............................... 82  \n5.5.1 Gaussian Process Regression ....................... 82  \n5.5.2 Bayesian Experimental Design ...................... 83  \n5.6 High-Energy Physics: 2D Efficiency Estimation ................ 85  \n5.6.1 Gaussian Process Regression ....................... 89  \n5.6.2 Bayesian Experimental Design ...................... 90  \n5.7 High-Energy Physics: 4D Efficiency Estimation ................ 94  \n5.7.1 Gaussian Process Regression ....................... 97  \n5.7.2 Bayesian Experimental Design ...................... 98  \n5.8 Discussion ..................................","cbCailqHk8dgawoP","https://ap.wps.com/l/cbCailqHk8dgawoP","pdf",8107797,3,1,144,"English","en",105,"# Table of Contents\n## 1 Introduction\n## 2 Deep Learning and High-Energy Physics\n## 3 Multi-Prong Jet Classification\n## 4 Jet Rotational Metrics\n## 5 Systematic Uncertainties in LHC data\n## 6 Conclusion\n## Appendix A Multi-Prong Jet Classification\n## Appendix B Jet Rotational Metrics\n## Appendix C Sampling Strategies","[{\"question\":\"What is the main focus of the dissertation?\",\"answer\":\"The dissertation focuses on applying machine learning to jet substructure, including classification and physics-motivated jet characterization.\"},{\"question\":\"How does the work approach multi-prong jet classification?\",\"answer\":\"It combines high-level and low-level modeling, evaluating dense neural networks and architectures such as CNNs, transformers, particle-flow networks, and physics-inspired networks, while studying performance gaps and topology dependence.\"},{\"question\":\"What techniques are used to handle systematic uncertainties in LHC data?\",\"answer\":\"Systematic uncertainties are treated using Gaussian process regression, including derivative information, and Bayesian experimental design to select utility inputs and update beliefs about the model.\"}]","Jet Substructure in the Era of Machine Learning - Dissertation Action/Completeness Phrase | PDF",1785940814,363,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"jet-substructure-in-the-era-of-machine-learning-dissertation-actioncompleteness-phrase","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/jet-substructure-in-the-era-of-machine-learning-dissertation-actioncompleteness-phrase/127683/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is the main focus of the dissertation?","Question",{"text":76,"@type":77},"The dissertation focuses on applying machine learning to jet substructure, including classification and physics-motivated jet characterization.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the work approach multi-prong jet classification?",{"text":81,"@type":77},"It combines high-level and low-level modeling, evaluating dense neural networks and architectures such as CNNs, transformers, particle-flow networks, and physics-inspired networks, while studying performance gaps and topology dependence.",{"name":83,"@type":74,"acceptedAnswer":84},"What techniques are used to handle systematic uncertainties in LHC data?",{"text":85,"@type":77},"Systematic uncertainties are treated using Gaussian process regression, including derivative information, and Bayesian experimental design to select utility inputs and update beliefs about the model.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]