{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T04:42:45Z","timestamp":1780461765916,"version":"3.54.1"},"reference-count":35,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Helmholtz Information and Data Science School","award":["DASHH - HIDSS-0002"],"award-info":[{"award-number":["DASHH - HIDSS-0002"]}]},{"DOI":"10.13039\/100006235","name":"Lawrence Berkeley National Laboratory","doi-asserted-by":"crossref","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}],"id":[{"id":"10.13039\/100006235","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"crossref","award":["KISS consortium - 05D23GU4"],"award-info":[{"award-number":["KISS consortium - 05D23GU4"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"crossref","award":["EXC 2121 Quantum Universe \u2013 390833306"],"award-info":[{"award-number":["EXC 2121 Quantum Universe \u2013 390833306"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Recently, 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.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad9136","type":"journal-article","created":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T22:59:03Z","timestamp":1731365943000},"page":"045044","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Calibrating Bayesian generative machine learning for Bayesiamplification"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2615-5639","authenticated-orcid":true,"given":"S","family":"Bieringer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4308-6804","authenticated-orcid":true,"given":"S","family":"Diefenbacher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3457-2755","authenticated-orcid":false,"given":"G","family":"Kasieczka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8104-4467","authenticated-orcid":false,"given":"M","family":"Trabs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"key":"mlstad9136bib1","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/s41781-018-0018-8","article-title":"A roadmap for HEP software and computing R&D for the 2020s","volume":"3","author":"HEP Software Foundation","year":"2019","journal-title":"Comput. Softw. Big Sci."},{"key":"mlstad9136bib2","article-title":"HL-LHC software and computing review panel","author":"Boehnlein","year":"2022"},{"key":"mlstad9136bib3","doi-asserted-by":"publisher","first-page":"079","DOI":"10.21468\/SciPostPhys.14.4.079","article-title":"Machine learning and LHC event generation","volume":"14","author":"Butter","year":"2023","journal-title":"SciPost Phys."},{"key":"mlstad9136bib4","doi-asserted-by":"publisher","DOI":"10.1016\/j.revip.2024.100092","article-title":"Deep generative models for detector signature simulation: an analytical taxonomy","volume":"12","author":"Hashemi","year":"2024","journal-title":"Rev. Phys."},{"key":"mlstad9136bib5","doi-asserted-by":"publisher","first-page":"139","DOI":"10.21468\/SciPostPhys.10.6.139","article-title":"GANplifying event samples","volume":"10","author":"Butter","year":"2021","journal-title":"SciPost Phys."},{"key":"mlstad9136bib6","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/17\/09\/P09028","article-title":"Calomplification\u2014the power of generative calorimeter models","volume":"17","author":"Bieringer","year":"2022","journal-title":"J. Instrum."},{"key":"mlstad9136bib7","article-title":"Jet diffusion versus JetGPT\u2013Modern networks for the LHC","author":"Butter","year":"2023"},{"key":"mlstad9136bib8","doi-asserted-by":"publisher","DOI":"10.2172\/1886020","article-title":"Interpretable uncertainty quantification in AI for HEP","author":"Chen","year":"2022"},{"key":"mlstad9136bib9","doi-asserted-by":"publisher","DOI":"10.1016\/j.physletb.2020.136041","article-title":"Bayesian neural networks for fast SUSY predictions","volume":"813","author":"Kronheim","year":"2021","journal-title":"Phys. Lett. B"},{"key":"mlstad9136bib10","doi-asserted-by":"publisher","first-page":"006","DOI":"10.21468\/SciPostPhys.8.1.006","article-title":"Deep-learning jets with uncertainties and more","volume":"8","author":"Bollweg","year":"2020","journal-title":"SciPost Phys."},{"key":"mlstad9136bib11","doi-asserted-by":"publisher","first-page":"JHEP04(2021)296","DOI":"10.1007\/JHEP04(2021)296","article-title":"Combine and conquer: event reconstruction with Bayesian ensemble neural networks","author":"Araz","year":"2021","journal-title":"J. High Energy Phys."},{"key":"mlstad9136bib12","doi-asserted-by":"publisher","first-page":"003","DOI":"10.21468\/SciPostPhys.13.1.003","article-title":"Understanding event-generation networks via uncertainties","volume":"13","author":"Bellagente","year":"2022","journal-title":"SciPost Phys."},{"key":"mlstad9136bib13","doi-asserted-by":"publisher","first-page":"031","DOI":"10.21468\/SciPostPhys.16.1.031","article-title":"How to understand limitations of generative networks","volume":"16","author":"Das","year":"2024","journal-title":"SciPost Phys."},{"key":"mlstad9136bib14","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/MCI.2022.3155327","article-title":"Hands-on bayesian neural networks\u2014A tutorial for deep learning users","volume":"17","author":"Jospin","year":"2022","journal-title":"IEEE Comput. Intell. Mag."},{"key":"mlstad9136bib15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3477140","article-title":"A survey on uncertainty estimation in deep learning classification systems from a bayesian perspective","volume":"54","author":"Mena","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"mlstad9136bib16","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/978-3-030-42553-1_3","article-title":"Bayesian neural networks: an introduction and survey","volume":"vol 2259)","author":"Goan","year":"2020"},{"key":"mlstad9136bib17","first-page":"1613","article-title":"Weight uncertainty in neural networks","author":"Blundell","year":"2015"},{"key":"mlstad9136bib18","first-page":"4629","article-title":"What are bayesian neural network posteriors really like?","author":"Izmailov","year":"2021"},{"key":"mlstad9136bib19","first-page":"1683","article-title":"Stochastic gradient hamiltonian monte carlo","author":"Chen","year":"2014"},{"key":"mlstad9136bib20","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1140\/epjc\/s10052-024-13353-w","article-title":"Classifier surrogates: sharing AI-based searches with the world","volume":"84","author":"Bieringer","year":"2024","journal-title":"Eur. Phys. J. C"},{"key":"mlstad9136bib21","article-title":"AdamMCMC: combining Metropolis adjusted Langevin with momentum-based optimization","author":"Bieringer","year":"2023"},{"key":"mlstad9136bib22","first-page":"1530","article-title":"Variational inference with normalizing flows","author":"Rezende","year":"2015"},{"key":"mlstad9136bib23","first-page":"6572","article-title":"Neural ordinary differential equations","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"mlstad9136bib24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.108.036025","article-title":"Fast point cloud generation with diffusion models in high energy physics","volume":"108","author":"Mikuni","year":"2023","journal-title":"Phys. Rev. D"},{"key":"mlstad9136bib25","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/19\/02\/P02001","article-title":"CaloScore v2: single-shot calorimeter shower simulation with diffusion models","volume":"19","author":"Mikuni","year":"2024","journal-title":"J. Instrum."},{"key":"mlstad9136bib26","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.109.012010","article-title":"Faster diffusion model with improved quality for particle cloud generation","volume":"109","author":"Leigh","year":"2024","journal-title":"Phys. Rev. D"},{"key":"mlstad9136bib27","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/19\/04\/P04020","article-title":"CaloClouds II: ultra-fast geometry-independent highly-granular calorimeter simulation","volume":"19","author":"Buhmann","year":"2024","journal-title":"J. Instrum."},{"key":"mlstad9136bib28","article-title":"EPiC-ly fast particle cloud generation with flow-matching and diffusion","author":"Buhmann","year":"2023"},{"key":"mlstad9136bib29","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.110.072003","article-title":"Graph-based diffusion model for fast shower generation in calorimeters with irregular geometry","volume":"110","author":"Kobylianskii","year":"2024","journal-title":"Phys. Rev. D"},{"key":"mlstad9136bib30","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2023"},{"key":"mlstad9136bib31","first-page":"4477","article-title":"Specifying weight priors in bayesian deep neural networks with empirical bayes","author":"Krishnan","year":"2020"},{"key":"mlstad9136bib32","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"mlstad9136bib33","article-title":"Latent space refinement for deep generative models","author":"Winterhalder","year":"2021"},{"key":"mlstad9136bib34","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.106.055006","article-title":"Classifying anomalies through outer density estimation","volume":"106","author":"Hallin","year":"2022","journal-title":"Phys. Rev. D"},{"key":"mlstad9136bib35","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1140\/epjc\/s10052-024-12607-x","article-title":"The interplay of machine learning-based resonant anomaly detection methods","volume":"84","author":"Golling","year":"2024","journal-title":"Eur. Phys. J. C"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad9136","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad9136\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad9136","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad9136\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad9136\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad9136\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad9136\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad9136\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T12:28:34Z","timestamp":1732105714000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad9136"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"references-count":35,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,11,20]]},"published-print":{"date-parts":[[2024,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad9136","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,20]]},"assertion":[{"value":"Calibrating Bayesian generative machine learning for Bayesiamplification","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-08-05","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-11-11","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-11-20","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}