[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128277-en":3,"doc-seo-128277-105":30,"detail-sidebar-cat-0-en-105":89},{"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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},128277,962085570644,"Evangeline","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Application of Machine Learning to Supersymmetric Models at Collider Experiments - Dissertation","This dissertation applies modern machine learning to searches for supersymmetric models of physics beyond the Standard Model, focusing on collider experiments. It studies resonant anomaly detection approaches such as CATHODE, emphasizing weakly supervised, signal-model agnostic construction to broaden coverage of parameter space beyond localized feature signals. The work investigates sensitivity limitations in realistic SUSY scenarios and demonstrates comparative performance against multiple dedicated searches. It also explores image-based jet classification using transformer and MaxViT variants to improve predictions and set exclusion reach in mock analyses.","Application of Machine Learning to Supersymmetric Models at Collider Experiments  \nDissertation  \nzur  \nErlangung des Doktorgrades (Dr. rer. nat.)  \nder  \nMathematisch-Naturwissenschaftlichen Fakultät  \nder  \nRheinischen Friedrich-Wilhelms-Universität Bonn  \nvon  \nLars Gerrit Bickendorf  \naus  \nKöln  \nBonn, Juli 2024  \nAngefertigt mit Genehmigung der Mathematisch-Naturwissenschaftlichen Fakultät der Rheinischen Friedrich-Wilhelms-Universität Bonn  \nGutachter / Betreuer: Prof. Dr. Manuel Drees  \nGutachter: Prof. Dr. Herbert Dreiner  \nTag der Promotion: 04.09.2024  \nErscheinungsjahr: 2024  \nAcknowledgements  \nFirst, I would like to express my gratitude to my advisor, Manuel Drees, for his invaluable insights and kind, hands-off attitude, which inspired my pursuit of particle physics as presented in this thesis.  \nI extend my thanks to Herbi Dreiner for becoming the second referee and for his enjoyable, light-hearted approach to teaching physics. I also thank Prof. Desch and Prof. Klein for serving on my committee as the experimentalist and computer science member, respectively.  \nI am grateful to various administrative members of the institute, particularly Petra Weiss, Patricia Zündorf, Christa Börsch, Andreas Wißkirchen, and Dominik Köhler. Dominik, despite being a doctoral student, was essential in keeping the BCTP running smoothly, contributing to a productive period.  \nFor the collaboration on resonant anomaly detection, I thank David Shih, Claudius Krause, and Gregor Kasieczka. Though the project took time to complete, it was both fun and fascinating.  \nI appreciate Bardia Najjari Farizhendi and Rahul Mehra for encouraging me to join the research group, which turned out to be a great decision. Being in the same group as Lina and meeting her in the corridor or at Christmas parties has always been a joy.  \nMoritz Wolter, Julian ([et. al](et. al).) Günther, and Marc Vaisband kindly reviewed various chapters of my thesis, helping to improve the text.  \nI am thankful for my parents, Magdalene and Ralph,(and their cats) for their unwavering support in my studies of physics.  \nLastly, I would like to thank Sophie for her steadfast support since the beginning of this journey. She stood by me, especially during my long-standing disagreement with an event generator, encouraging me to persevere.  \nAbstract  \nIn this thesis, we study the application of modern machine learning methods to searches for supersymmetric models of physics beyond the Standard Model.  \nIn recent years, resonant anomaly detection methods, such as CATHODE, have gained much attention. Using weakly supervised learning, these methods are built to be signal-model agnostic. The main advantage is that they are not only sensitive to a specific signal model, the analysis is tailored to, but cover a potentially much larger region of the parameter space. These methods are most often demonstrated on signal models that contain purely localized features.  \nHowever, the well-motivated R-parity conserving minimally supersymmetric Standard Model is often found at the tails of distributions of features such as 􀀿 iss or 􀀝􀀩 . Pair produced gluinos with the  \ndecay chain  → 􀁀 02(02 → 􀀭01) with 􀀭 either the 􀀯 or Higgs boson, light 01 and small mass  \nsplitting between and 02 will be used to demonstrate CATHODEs sensitivity. We, for the first time,  \ndemonstrate that CATHODE is only slightly less sensitive than multiple dedicated searches while covering multiple signal models simultaneously.  \nThis˜ method can not uncover all signal models. For examp˜le the R-parity violating scalar top quark  \ndecaincnnayrov􀁃eliati1ec(1et􀁀der􀁀􀁀tovi.s)wiFoionrt, htswhiuceshaskigasscnaCallo1deaetnla,d swndube bM-TuiaxeVldViailupthsaetto prviapprodsedly tuchcelaessfesielafif-tuearrtteWesnttheiatuonCAtilimezTecHrhaOecniDesEntm  \nto images. We represent calorimeter towers and tracks of jets as 2D images and show that the transformer-based classifiers outperform more classical convolutional neural network","cbCaijIZDxlM9WT5","https://ap.wps.com/l/cbCaijIZDxlM9WT5","pdf",4226891,1,138,"English","en",105,"# Contents\n## Introduction\n## Theoretical Overview\n## Machine Learning","[{\"question\":\"What problem does this dissertation address in collider physics?\",\"answer\":\"\"},{\"question\":\"How do resonant anomaly detection methods like CATHODE help in supersymmetric searches?\",\"answer\":\"\"},{\"question\":\"What machine learning architectures are evaluated for jet classification?\",\"answer\":\"\"}]","Application of Machine Learning to Supersymmetric Models at Collider Experiments - Dissertation | PDF",1785946487,348,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":28},"application-of-machine-learning-to-supersymmetric-models-at-collider-experiments-dissertation","",{"@graph":36,"@context":83},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/application-of-machine-learning-to-supersymmetric-models-at-collider-experiments-dissertation/128277/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"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",[72,77,80],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does this dissertation address in collider physics?","Question",{"text":34,"@type":76},"Answer",{"name":78,"@type":74,"acceptedAnswer":79},"How do resonant anomaly detection methods like CATHODE help in supersymmetric searches?",{"text":34,"@type":76},{"name":81,"@type":74,"acceptedAnswer":82},"What machine learning architectures are evaluated for jet classification?",{"text":34,"@type":76},"https://schema.org",{"og:url":52,"og:type":85,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":87,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":46,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":46,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":46,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]