[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125539-en":3,"doc-seo-125539-105":30,"detail-sidebar-cat-0-en-105":91},{"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},125539,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Unbinned multivariate observables for global SMEFT analyses from machine learning","Global SMEFT interpretations of collider measurements require inferring many Wilson coefficients from large datasets while choosing observables that carry maximal sensitivity to theory parameters. This work presents ML4EFT, an open-source framework integrating unbinned multivariate observables into global SMEFT fits. Compared with binned measurements, it avoids information loss from binning subsets of final-state kinematics. The approach uses machine learning regression and classification to parameterize high-dimensional likelihood ratios, with Monte Carlo replicas to estimate and propagate methodological uncertainties.","arXiv :2211 .02058v1 [hep-ph] 3 Nov 2022  \nNikhef-2022-015  \nUnbinned multivariate observables for global SMEFT analyses  \nfrom machine learning  \nRaquel Gomez Ambrosio, 1 Jaco ter Hoeve,2 ;3 Maeve Madigan,4 Juan Rojo,2 ;3 and Veronica Sanz5 ;6  \n1 Dipartimento di Fisica \\G. Occhialini\", Universita degli Studi di Milano-Bicocca, and INFN, Sezione di Milano Bicocca, Piazza della Scienza 3, I { 20126 Milano, Italy  \n2 Department of Physics and Astronomy, VU Amsterdam, 1081HV Amsterdam, The Netherlands  \n3 Nikhef Theory Group, Science Park 105, 1098 XG Amsterdam, The Netherlands  \n4 DAMTP, University of Cambridge, Wilberforce Road, Cambridge CB3 0WA, UK  \n5 Instituto de F􀀓􀀐sica Corpuscular (IFIC), Universidad de Valencia-CSIC, E-46980 Valencia, Spain  \n6 Department of Physics and Astronomy, University of Sussex, Brighton BN1 9QH, UK  \nAbstract  \nTheoretical interpretations of particle physics data, such as the determination of the Wilson coe􀀎cients of the Standard Model E􀀋ective Field Theory (SMEFT), often involve the inference of multiple parameters from a global dataset. Optimizing such interpretations requires the identi􀀌cation of observables that exhibit the highest possible sensitivity to the underlying theory parameters. In this work we develop a 􀀍exible open source framework, ML4EFT, enabling the integration of unbinned multivariate observables into global SMEFT 􀀌ts. As compared to traditional measurements, such observables enhance the sensitivity to the theory parameters by preventing the information loss incurred when binning in a subset of 􀀌nalstate kinematic variables. Our strategy combines machine learning regression and classi􀀌cation techniques to parameterize high-dimensional likelihood ratios, using the Monte Carlo replica method to estimate and propagate methodological uncertainties. As a proof of concept we construct unbinned multivariate observables for top-quark pair and Higgs+Z production at the LHC, demonstrate their impact on the SMEFT parameter space as compared to binned measurements, and study the improved constraints associated to multivariate inputs. Since the number of neural networks to be trained scales quadratically with the number of parameters and can be fully parallelized, the ML4EFT framework is well-suited to construct unbinned multivariate observables which depend on up to tens of EFT coe􀀎cients, as required in global 􀀌ts.  \nContents  \n1 Introduction 2  \n2 From binned to unbinned likelihoods 3  \n2.1 Binned likelihoods .......................................... 4  \n2.2 Unbinned likelihood ......................................... 6  \n3 Unbinned observables from machine learning 8  \n3.1 Di􀀋erential cross-sections ...................................... 8  \n3.2 Cross-section parametrization .................................... 9  \n3.3 Neural network training ....................................... 12  \n4 Theoretical modeling 16  \n4.1 Benchmark processes and simulation pipeline ........................... 16  \n4.2 Top-quark pair production: parton level .............................. 19  \n4.3 Top-quark pair production: particle level .............................. 20  \n4.4 Higgs associated production with a Z-boson ............................ 21  \n4.5 Inputs to the neural network training ................................ 22  \n5 EFT constraints from unbinned multivariate observables 27  \n5.1 EFT parameter inference ...................................... 27  \n5.2 Top-quark pair production: parton level results .......................... 28  \n5.3 Top-quark pair production: particle level results ......................... 28  \n5.4 Higgs associated production with vector bosons .......................... 35  \n5.5 Methodological uncertainties .................................... 40  \n6 Summary and outlook 40  \nA The ML4EFT framework 44  \nB The unbinned Asimov data set 44  \n1 Introduction  \nThe extensive characterization of the Higgs boson properties achieved at the LHC [1{3] following the tenth  \nannive","cbCaiuXZBSlZ82EF","https://ap.wps.com/l/cbCaiuXZBSlZ82EF","pdf",6312646,1,53,"English","en",105,"# Introduction\n# From binned to unbinned likelihoods\n## Binned likelihoods\n## Unbinned likelihood\n# Unbinned observables from machine learning\n## Di­fferential cross-sections\n## Cross-section parametrization\n## Neural network training\n# Theoretical modeling\n## Benchmark processes and simulation pipeline\n## Top-quark pair production: parton level\n## Top-quark pair production: particle level\n## Higgs associated production with a Z-boson\n## Inputs to the neural network training\n# EFT constraints from unbinned multivariate observables\n## EFT parameter inference\n## Methodological uncertainties\n# Summary and outlook","[{\"question\":\"What problem does ML4EFT address in global SMEFT analyses?\",\"answer\":\"It addresses the need to choose observables with high sensitivity to SMEFT parameters while avoiding information loss from binning in global fits.\"},{\"question\":\"How does ML4EFT incorporate unbinned multivariate observables?\",\"answer\":\"It combines machine learning regression and classification to parameterize high-dimensional likelihood ratios and integrates them into global SMEFT fitting workflows.\"},{\"question\":\"What method is used to estimate and propagate uncertainties?\",\"answer\":\"The framework uses the Monte Carlo replica method to estimate and propagate methodological uncertainties.\"}]","Unbinned multivariate observables for global SMEFT analyses from machine learning | PDF",1785899737,134,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"unbinned-multivariate-observables-for-global-smeft-analyses-from-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@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/unbinned-multivariate-observables-for-global-smeft-analyses-from-machine-learning/125539/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does ML4EFT address in global SMEFT analyses?","Question",{"text":75,"@type":76},"It addresses the need to choose observables with high sensitivity to SMEFT parameters while avoiding information loss from binning in global fits.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does ML4EFT incorporate unbinned multivariate observables?",{"text":80,"@type":76},"It combines machine learning regression and classification to parameterize high-dimensional likelihood ratios and integrates them into global SMEFT fitting workflows.",{"name":82,"@type":73,"acceptedAnswer":83},"What method is used to estimate and propagate uncertainties?",{"text":84,"@type":76},"The framework uses the Monte Carlo replica method to estimate and propagate methodological uncertainties.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]