{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T06:56:27Z","timestamp":1769756187737,"version":"3.49.0"},"reference-count":27,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100006208","name":"High Energy Physics","doi-asserted-by":"crossref","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}],"id":[{"id":"10.13039\/100006208","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":[[2025,9,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Most of the fundamental, emergent, and phenomenological parameters of particle and nuclear physics are determined through parametric template fits. Simulations are used to populate histograms which are then matched to data. This approach is inherently lossy, since histograms are binned and low-dimensional. Deep learning has enabled unbinned and high-dimensional parameter estimation through neural likelihood(-ratio) estimation. We compare two approaches for neural simulation-based inference (NSBI): one based on discriminative learning (classification) and one based on generative modeling. These two approaches are directly evaluated on the same datasets, with a similar level of hyperparameter optimization in both cases. In addition to a Gaussian dataset, we study NSBI using a Higgs boson dataset from the FAIR Universe Challenge. We find that both the direct likelihood and likelihood ratio estimation are able to effectively extract parameters with reasonable uncertainties. For the numerical examples and within the set of hyperparameters studied, we found that the likelihood ratio method is more accurate and\/or precise. Both methods have a significant spread from the network training and would require ensembling or other mitigation strategies in practice.<\/jats:p>","DOI":"10.1088\/2632-2153\/adf68b","type":"journal-article","created":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T22:52:48Z","timestamp":1754002368000},"page":"030503","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Discriminative versus generative approaches to simulation-based inference"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6830-9016","authenticated-orcid":true,"given":"Benjamin","family":"Sluijter","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4308-6804","authenticated-orcid":true,"given":"Sascha","family":"Diefenbacher","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6213-8617","authenticated-orcid":false,"given":"Wahid","family":"Bhimji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1024-0932","authenticated-orcid":false,"given":"Benjamin","family":"Nachman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,8,19]]},"reference":[{"key":"mlstadf68bbib1","doi-asserted-by":"publisher","first-page":"30055","DOI":"10.1073\/pnas.1912789117","article-title":"The frontier of simulation-based inference","volume":"117","author":"Cranmer","year":"2020","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstadf68bbib2","article-title":"Presenting unbinned differential cross section results","author":"Arratia","year":"2021"},{"key":"mlstadf68bbib3","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":"mlstadf68bbib4","article-title":"The landscape of unfolding with machine learning","author":"Huetsch","year":"2024"},{"key":"mlstadf68bbib5","article-title":"Measurement of off-shell Higgs boson production in the H\u2217\u2192ZZ\u21924\u2113 decay channel using a neural simulation-based inference technique in 13 TeV pp collisions with the ATLAS detector","author":"ATLAS Collaboration","year":"2024"},{"key":"mlstadf68bbib6","article-title":"An implementation of neural simulation-based inference for parameter estimation in ATLAS","author":"ATLAS Collaboration","year":"2024"},{"key":"mlstadf68bbib7","article-title":"Constraints on standard model effective field theory for a Higgs boson produced in association with W or Z bosons in the H \u2192bb\u00af decay channel in proton-proton collisions at s = 13 TeV","author":"CMS Collaboration","year":"2024"},{"key":"mlstadf68bbib8","doi-asserted-by":"publisher","first-page":"1999","DOI":"10.1093\/mnras\/stab2181","article-title":"Towards constraining warm dark matter with stellar streams through neural simulation-based inference","volume":"507","author":"Hermans","year":"2021","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstadf68bbib9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.130.171403","article-title":"Neural importance sampling for rapid and reliable gravitational-wave inference","volume":"130","author":"Dax","year":"2023","journal-title":"Phys. Rev. Lett."},{"key":"mlstadf68bbib10","article-title":"Exploring the BSM parameter space with neural network aided simulation-based inference","author":"Chatterjee","year":"2025"},{"key":"mlstadf68bbib11","article-title":"FAIR universe HiggsML uncertainty challenge competition","author":"Bhimji","year":"2024"},{"key":"mlstadf68bbib12","first-page":"pp 19","article-title":"The Higgs boson machine learning challenge","author":"Adam-Bourdarios","year":"2015"},{"key":"mlstadf68bbib13","article-title":"Normalizing flows for probabilistic modeling and inference","author":"Papamakarios","year":"2021"},{"key":"mlstadf68bbib14","article-title":"Approximating likelihood ratios with calibrated discriminative classifiers","author":"Cranmer","year":"2015"},{"key":"mlstadf68bbib15","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1140\/epjc\/s10052-016-4099-4","article-title":"Parameterized neural networks for high-energy physics","volume":"C76","author":"Baldi","year":"2016","journal-title":"Eur. Phys. J."},{"key":"mlstadf68bbib16","first-page":"pp 8024","article-title":"Pytorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"mlstadf68bbib17","article-title":"Neural spline flows","volume":"vol 32","author":"Durkan","year":"2019"},{"key":"mlstadf68bbib18","article-title":"CURTAINs for your sliding window: constructing unobserved regions by transforming adjacent intervals","author":"Raine","year":"2022"},{"key":"mlstadf68bbib19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.103.116013","article-title":"Learning from many collider events at once","volume":"103","author":"Nachman","year":"2021","journal-title":"Phys. Rev. D"},{"key":"mlstadf68bbib20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.104.056026","article-title":"Uncertainty-aware machine learning for high energy physics","volume":"104","author":"Ghosh","year":"2021","journal-title":"Phys. Rev. D"},{"key":"mlstadf68bbib21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.physletb.2012.08.020","article-title":"Observation of a new particle in the search for the standard model Higgs boson with the ATLAS detector at the LHC","volume":"716","author":"ATLAS Collaboration","year":"2012","journal-title":"Phys. Lett. B"},{"key":"mlstadf68bbib22","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.physletb.2012.08.021","article-title":"Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC","volume":"716","author":"CMS Collaboration","year":"2012","journal-title":"Phys. Lett. B"},{"key":"mlstadf68bbib23","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.cpc.2015.01.024","article-title":"An introduction to PYTHIA 8.2","volume":"191","author":"Sj\u00f6strand","year":"2015","journal-title":"Comput. Phys. Commun."},{"key":"mlstadf68bbib24","doi-asserted-by":"publisher","first-page":"JHEP02(2014)057","DOI":"10.1007\/JHEP02(2014)057","article-title":"A modular framework for fast simulation of a generic collider experiment","author":"DELPHES 3 Collaboration DELPHES 3","year":"2014","journal-title":"J. High Energy Phys."},{"key":"mlstadf68bbib25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1214\/aos\/1176344552","article-title":"Bootstrap methods: another look at the jackknife","volume":"7","author":"Efron","year":"1979","journal-title":"Ann. Stat."},{"key":"mlstadf68bbib26","article-title":"Optimizers for stabilizing likelihood-free inference","author":"De Luca","year":"2025"},{"key":"mlstadf68bbib27","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1214\/ss\/1177013815","article-title":"Bootstrap methods for standard errors, confidence intervals and other measures of statistical accuracy","volume":"1","author":"Efron","year":"1986","journal-title":"Stat. Sci."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf68b","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf68b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf68b","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf68b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf68b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf68b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf68b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf68b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T09:40:34Z","timestamp":1755596434000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf68b"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,19]]},"references-count":27,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,8,19]]},"published-print":{"date-parts":[[2025,9,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/adf68b","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,19]]},"assertion":[{"value":"Discriminative versus generative approaches to simulation-based inference","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 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-03-24","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-07-31","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-08-19","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}