[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120141-en":3,"doc-seo-120141-105":30,"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":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},120141,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Calibrating Bayesian generative machine learning for Bayesiamplification","Recently, combinations of generative and Bayesian deep learning have been introduced in particle physics to enable fast detector simulation and inference under limited training statistics. The distribution-wide meaning of uncertainty, however, remains unclear. This work presents a concrete calibration scheme for Bayesian generative machine-learning models. Using a Continuous Normalizing Flow on a low-dimensional toy problem, it evaluates calibration from either mean-field Gaussian weight posteriors or Monte Carlo sampling of network weights, including behavior on unsteady distribution edges.","Lawrence Berkeley National Laboratory LBL Publications  \nTitle  \nCalibrating Bayesian generative machine learning for Bayesiamplification  \nPermalink  \n[https://escholarship.org/uc/item/34q6w12d](https://escholarship.org/uc/item/34q6w12d)  \nJournal  \nMachine Learning: Science and Technology, 5(4)  \nISSN  \n2632-2153  \nAuthors  \nBieringer, S  \nDiefenbacher, SKasieczka, Get al.  \nPublication Date  \n2024-12-01  \nDOI  \n10.1088/2632-2153/ad9136  \nCopyright Information  \nThis work is made available under the terms of a Creative Commons Attribution License, available at [https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nPAPER • OPEN ACCESS  \nCalibrating Bayesian generative machine learning for Bayesiamplification  \nTo cite this article: S Bieringer et al 2024 Mach. Learn. : Sci. Technol. 5 045044  \nView the article online for updates and enhancements.  \nYou may also like  \n-Physics-inspired machine learning detects‘unknown unknowns’ in networks: discovering network boundaries from observable dynamics  \nMoshir Harsh, Leonhard Götz Vulpius and Peter Sollich  \n-Detection of 19 lt-yr Long Bipolar Jets from Interacting Binary KX And  \nStefan Ziegenbalg  \n-qCMOS Detectors and the Case of Hypothetical Primordial Black Holes in the Solar System, near Earth Objects, Transients, and Other High-cadence Observations  \nMartin M. Roth  \nThis content was downloaded from IP address [108.75.79.166](108.75.79.166) on 10/12/2024 at 18:38  \n Mach. Learn.: Sci. Technol. 5 (2024) 045044 [https://doi.org/10.1088/2632-2153/ad9136](https://doi.org/10.1088/2632-2153/ad9136)  \nPAPER  \nCalibrating Bayesian generative machine learning for  \nOPEN ACCESS  \nBayesiamplification  \nRECEIVED  \n5 August 2024 S Bieringer1, ∗􀁂, S Diefenbacher2􀁂, G Kasieczka1􀁂 and M Trabs3􀁂  \nREVISED29 October 2024 1 Institut für Experimentalphysik, Universität Hamburg, Luruper Chaussee 149, 22761 Hamburg, Germany  \n2 Physics Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, United States of America  \nA1CEPTED FORNovembePrU2BLICA024TION  Department of Mathematics, Karlsruhe Institute of Technology, Englerstr. 2, 76131 Karlsruhe, Germany Author to whom any correspondence should be addressed.  \nPUBLISHED  \n20 November 2024 E-mail: [sebastian.guido.bieringer@uni-hamburg.de](sebastian.guido.bieringer@uni-hamburg.de)  \n   Keywords: Bayesian neural networks, generative neural networks, data amplification, fast detector simulation  \nOriginal Content from this work may be used under the terms of the  \nCreative Commons Attribution 4 .0 licence.  \nAny further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.  \nAbstract  \nRecently, combinations of generative and Bayesian deep learning have been introduced in particle physics for both fast detector simulation and inference tasks. These neural networks aim to quantify the uncertainty on the generated distribution originating from limited training statistics. The interpretation of a distribution-wide uncertainty however remains ill-defined. We show a clear scheme for quantifying the calibration of Bayesian generative machine learning models. For a Continuous Normalizing Flow applied to a low-dimensional toy example, we evaluate the calibration of Bayesian uncertainties from either a mean-field Gaussian weight posterior, or Monte Carlo sampling network weights, to gauge their behaviour on unsteady distribution edges. Well calibrated uncertainties can then be used to roughly estimate the number of uncorrelated truth samples that are equivalent to the generated sample and clearly indicate data amplification for smooth features of the distribution.  \n1. Introduction  \nThe upcoming high-luminosity runs of the LHC will push the quantitative frontier of data taking to over 25-times its current rates. To ens","cbCainm4FiM011uB","https://ap.wps.com/l/cbCainm4FiM011uB","pdf",1169231,1,14,"English","en",105,"# Introduction\n## Data-taking and simulation scaling\n## Generative machine learning and amplification\n## Bayesian generative models and uncertainty calibration","[{\"question\":\"What problem does the paper address regarding Bayesian generative machine learning uncertainty?\",\"answer\":\"It targets the ill-defined interpretation of uncertainty across the entire generated distribution when Bayesian generative models are trained with limited statistics.\"},{\"question\":\"How does the proposed method evaluate calibration in the paper?\",\"answer\":\"It evaluates uncertainty calibration for a Continuous Normalizing Flow toy example using either a mean-field Gaussian weight posterior or Monte Carlo sampling of network weights.\"},{\"question\":\"How can calibrated Bayesian uncertainties help in practice?\",\"answer\":\"Well calibrated uncertainties can estimate the effective number of uncorrelated truth samples equivalent to the generated sample and indicate data amplification for smooth distribution features.\"}]","Calibrating Bayesian generative machine learning for Bayesiamplification | PDF",1785728411,35,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"calibrating-bayesian-generative-machine-learning-for-bayesiamplification","",{"@graph":36,"@context":86},[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/calibrating-bayesian-generative-machine-learning-for-bayesiamplification/120141/",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","2026-08-06","2026-08-03",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 problem does the paper address regarding Bayesian generative machine learning uncertainty?","Question",{"text":76,"@type":77},"It targets the ill-defined interpretation of uncertainty across the entire generated distribution when Bayesian generative models are trained with limited statistics.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed method evaluate calibration in the paper?",{"text":81,"@type":77},"It evaluates uncertainty calibration for a Continuous Normalizing Flow toy example using either a mean-field Gaussian weight posterior or Monte Carlo sampling of network weights.",{"name":83,"@type":74,"acceptedAnswer":84},"How can calibrated Bayesian uncertainties help in practice?",{"text":85,"@type":77},"Well calibrated uncertainties can estimate the effective number of uncorrelated truth samples equivalent to the generated sample and indicate data amplification for smooth distribution features.","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":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]