{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T02:51:17Z","timestamp":1761101477167,"version":"3.37.3"},"reference-count":26,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T00:00:00Z","timestamp":1664928000000},"content-version":"vor","delay-in-days":34,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T00:00:00Z","timestamp":1664928000000},"content-version":"tdm","delay-in-days":34,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2022,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Signal-background classification is a central problem in high-energy physics, that plays a major role for the discovery of new fundamental particles. A recent method\u2014the parametric neural network (pNN)\u2014leverages multiple signal mass hypotheses as an additional input feature to effectively replace a whole set of individual classifiers, each providing (in principle) the best response for the corresponding mass hypothesis. In this work we aim at deepening the understanding of pNNs in light of real-world usage. We discovered several peculiarities of parametric networks, providing intuition, metrics, and guidelines to them. We further propose an alternative parametrization scheme, resulting in a new parametrized neural network architecture: the AffinePNN; along with many other generally applicable improvements, like the <jats:italic>balanced training<\/jats:italic> procedure. Finally, we extensively and empirically evaluate our models on the <jats:monospace>HEPMASS<\/jats:monospace> dataset, along its <jats:italic>imbalanced<\/jats:italic> version (called <jats:monospace>HEPMASS-IMB<\/jats:monospace>) we provide here for the first time, to further validate our approach. Provided results are in terms of the impact of the proposed design decisions, classification performance, and interpolation capability, as well.<\/jats:p>","DOI":"10.1088\/2632-2153\/ac917c","type":"journal-article","created":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T10:54:43Z","timestamp":1664967283000},"page":"035017","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Improving parametric neural networks for high-energy physics (and beyond)"],"prefix":"10.1088","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0399-8836","authenticated-orcid":true,"given":"Luca","family":"Anzalone","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0780-8785","authenticated-orcid":false,"given":"Tommaso","family":"Diotalevi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0835-9574","authenticated-orcid":false,"given":"Daniele","family":"Bonacorsi","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2022,10,5]]},"reference":[{"year":"2016","author":"Goodfellow","key":"mlstac917cbib1"},{"year":"2001","author":"Friedman","key":"mlstac917cbib2"},{"key":"mlstac917cbib3","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":"Chatrchyan","year":"2012","journal-title":"Phys. Lett. B"},{"key":"mlstac917cbib4","doi-asserted-by":"publisher","first-page":"4308","DOI":"10.1038\/ncomms5308","article-title":"Searching for exotic particles in high-energy physics with deep learning","volume":"5","author":"Baldi","year":"2014","journal-title":"Nat. Commun."},{"key":"mlstac917cbib5","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/3\/08\/S08001","article-title":"LHC machine","volume":"3","author":"Evans","year":"2008","journal-title":"J. Instrum."},{"key":"mlstac917cbib6","doi-asserted-by":"publisher","first-page":"096","DOI":"10.1007\/JHEP01(2020)096","article-title":"Search for a charged Higgs boson decaying into top and bottom quarks in events with electrons or muons in proton-proton collisions at s = 13 TeV","volume":"01","author":"Sirunyan","year":"2020","journal-title":"J. High Energy Phys."},{"key":"mlstac917cbib7","doi-asserted-by":"publisher","first-page":"054","DOI":"10.1007\/JHEP01(2018)054","article-title":"Search for resonant and nonresonant Higgs boson pair production in the bb\u203e\u2113\u03bd\u2113\u03bd final state in proton-proton collisions at s=13 TeV","volume":"01","author":"Sirunyan","year":"2018","journal-title":"J. High Energy Phys."},{"key":"mlstac917cbib8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1140\/epjc\/s10052-016-4099-4","article-title":"Parameterized neural networks for high-energy physics","volume":"76","author":"Baldi","year":"2016","journal-title":"Eur. Phys. J. C"},{"key":"mlstac917cbib9","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.6453048","article-title":"HEPMASS-IMB","author":"Anzalone","year":"2022"},{"article-title":"HEPMASS dataset\u2014UCI machine learning repository","year":"2015","author":"Baldi","key":"mlstac917cbib10"},{"key":"mlstac917cbib11","first-page":"pp 1","article-title":"End-to-end driving via conditional imitation learning","author":"Codevilla","year":"2018"},{"key":"mlstac917cbib12","first-page":"pp 1126","article-title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","volume":"vol 70","author":"Finn","year":"2017"},{"article-title":"Diversity is all you need: learning skills without a reward function","year":"2019","author":"Eysenbach","key":"mlstac917cbib13"},{"article-title":"Conditional generative adversarial nets","year":"2014","author":"Mirza","key":"mlstac917cbib14"},{"key":"mlstac917cbib15","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00011","article-title":"Feature-wise transformations","author":"Dumoulin","year":"2018"},{"key":"mlstac917cbib16","first-page":"pp 448","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","volume":"vol 37","author":"Ioffe","year":"2015"},{"key":"mlstac917cbib17","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/JHEP06(2021)145","article-title":"Search for charged Higgs bosons decaying into a top quark and a bottom quark at s = 13 TeV with the ATLAS detector","volume":"06","author":"Aad","year":"2021","journal-title":"J. High Energy Phys."},{"key":"mlstac917cbib18","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"mlstac917cbib19","first-page":"11","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"mlstac917cbib20","doi-asserted-by":"publisher","first-page":"e2","DOI":"10.23915\/distill.00002","article-title":"How to use t-SNE effectively","volume":"1","author":"Wattenberg","year":"2016","journal-title":"Distill"},{"key":"mlstac917cbib21","first-page":"pp 19","article-title":"The Higgs Boson Machine Learning Challenge","author":"Adam-Bourdarios","year":"2015"},{"key":"mlstac917cbib22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1140\/epjc\/s10052-011-1554-0","article-title":"Asymptotic formulae for likelihood-based tests of new physics","volume":"71","author":"Cowan","year":"2011","journal-title":"Eur. Phys. J. C"},{"key":"mlstac917cbib23","first-page":"pp 265","article-title":"TensorFlow: a system for large-scale machine learning","author":"Abadi","year":"2016"},{"article-title":"Keras: Deep Learning for Humans","year":"2015","author":"Chollet","key":"mlstac917cbib24"},{"article-title":"Adam: a method for stochastic optimization","year":"2015","author":"Kingma","key":"mlstac917cbib25"},{"key":"mlstac917cbib26","first-page":"pp 249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"vol 9","author":"Glorot","year":"2010"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac917c","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac917c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac917c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac917c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T10:54:49Z","timestamp":1664967289000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac917c"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,1]]},"references-count":26,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2022,10,5]]},"published-print":{"date-parts":[[2022,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ac917c","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2022,9,1]]},"assertion":[{"value":"Improving parametric neural networks for high-energy physics (and beyond)","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 2022 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-04-27","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-09-12","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-10-05","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}