{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T10:17:22Z","timestamp":1772187442180,"version":"3.50.1"},"reference-count":59,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T00:00:00Z","timestamp":1772150400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T00:00:00Z","timestamp":1772150400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T00:00:00Z","timestamp":1772150400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"},{"start":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T00:00:00Z","timestamp":1772150400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"}],"funder":[{"name":"Korean Local Governments -Gyeongsangbuk-do Province and Pohang City"},{"name":"Science and Technology Promotion Fund and Lottery Fund of the Korean Government"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2026,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Neural scaling laws-power-law relationships between generalization errors and characteristics of deep learning models-are vital tools for developing reliable models while managing limited resources. Although the success of large language models highlights the importance of these laws, their application to deep regression models remains largely unexplored. Here, we empirically investigate neural scaling laws in deep regression using a parameter estimation model for twisted van der Waals magnets. We observe power-law relationships between the loss and both training dataset size and model capacity across a wide range of values, employing various architectures-including fully connected networks, residual networks, and vision transformers. Furthermore, the scaling exponents governing these relationships range from 1 to 2, with specific values depending on the regressed parameters and model details. The consistent scaling behaviors and their large scaling exponents suggest that the performance of deep regression models can improve substantially with increasing data size.<\/jats:p>","DOI":"10.1088\/2632-2153\/ae484c","type":"journal-article","created":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T22:53:18Z","timestamp":1771541598000},"page":"025011","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Neural scaling laws for deep regression on domain image data of twisted magnets"],"prefix":"10.1088","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5343-4086","authenticated-orcid":false,"given":"Tilen","family":"\u010cade\u017e","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2468-3152","authenticated-orcid":true,"given":"Kyoung-Min","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2026,2,27]]},"reference":[{"key":"mlstae484cbib1","doi-asserted-by":"publisher","first-page":"2065","DOI":"10.1109\/TPAMI.2019.2910523","type":"journal-article","article-title":"A comprehensive analysis of deep regression","volume":"42","author":"Lathuili\u00e9re","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstae484cbib2","article-title":"The effectiveness of data augmentation in image classification using deep learning","author":"Wang","type":"preprint"},{"key":"mlstae484cbib3","article-title":"How to train your vit? data, augmentation, and regularization in vision transformers","author":"Steiner","year":"2022","type":"preprint"},{"key":"mlstae484cbib4","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/0893-6080(93)90013-M","type":"journal-article","article-title":"A universal theorem on learning curves","volume":"6","author":"Amari","year":"1993","journal-title":"Neural Netw."},{"key":"mlstae484cbib5","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1162\/neco.1992.4.4.605","type":"journal-article","article-title":"Four types of learning curves","volume":"4","author":"Amari","year":"1992","journal-title":"Neural Comput."},{"key":"mlstae484cbib6","article-title":"A solvable model of neural scaling laws","author":"Maloney","year":"2022","type":"preprint"},{"key":"mlstae484cbib7","article-title":"Dimension-free deterministic equivalents and scaling laws for random feature regression","author":"Leonardo","year":"2023","type":"preprint"},{"key":"mlstae484cbib8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0526)","type":"conference-proceedings","article-title":"4+3 phases of compute-optimal neural scaling laws","author":"Paquette","year":"2024"},{"key":"mlstae484cbib9","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2311878121","type":"journal-article","article-title":"Explaining neural scaling laws","volume":"121","author":"Bahri","year":"2024","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"mlstae484cbib10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106504","type":"journal-article","article-title":"Effects of dataset size and interactions on the prediction performance of logistic regression and deep learning models","volume":"213","author":"Bailly","year":"2022","journal-title":"Comput. Methods Programs Biomed."},{"key":"mlstae484cbib11","article-title":"Deep 288 learning scaling is predictable, empirically","author":"Hestness","year":"2017","type":"preprint"},{"key":"mlstae484cbib12","article-title":"A constructive prediction of the generalization error across scales","author":"Rosenfeld","year":"2020","type":"conference-proceedings"},{"key":"mlstae484cbib13","article-title":"Scaling laws for autoregressive generative modeling","author":"Henighan","year":"2020","type":"preprint"},{"key":"mlstae484cbib14","article-title":"How much data do you need? part 2: predicting DL class specific training dataset sizes","author":"M\u00fchlenst\u00e4dt","year":"2024","type":"preprint"},{"key":"mlstae484cbib15","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-76764-1","type":"journal-article","article-title":"Power-law scaling to assist with key challenges in artificial intelligence","volume":"10","author":"Meir","year":"2020","journal-title":"Sci. Rep."},{"key":"mlstae484cbib16","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/1472-6947-12-8","type":"journal-article","article-title":"Predicting sample size required for classification performance","volume":"12","author":"Figueroa","year":"2012","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"mlstae484cbib17","article-title":"How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?","author":"Cho","year":"2016","type":"preprint"},{"key":"mlstae484cbib18","doi-asserted-by":"publisher","first-page":"pp 843","DOI":"10.1109\/ICCV.2017.97)","type":"conference-proceedings","article-title":"Revisiting unreasonable effectiveness of data in deep learning era","author":"Sun","year":"2017"},{"key":"mlstae484cbib19","article-title":"Scaling laws from the data manifold dimension","author":"Sharma","year":"2022","type":"conference-proceedings"},{"key":"mlstae484cbib20","first-page":"pp 22300","type":"conference-proceedings","article-title":"Revisiting neural scaling laws in language and vision","volume":"vol 35","author":"Alabdulmohsin","year":"2022"},{"key":"mlstae484cbib21","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","type":"preprint"},{"key":"mlstae484cbib22","type":"conference-proceedings","article-title":"Training compute-optimal large language models","volume":"vol 35","author":"Hoffmann","year":"2022"},{"key":"mlstae484cbib23","article-title":"Learning curve theory","author":"Hutter","year":"2021","type":"preprint"},{"key":"mlstae484cbib24","article-title":"Scaling laws in linear regression: compute, parameters, and data","author":"Lin","year":"2024","type":"preprint"},{"key":"mlstae484cbib25","doi-asserted-by":"publisher","first-page":"6088","DOI":"10.1021\/acs.nanolett.3c01529","type":"journal-article","article-title":"Ab initio spin hamiltonian and topological noncentrosymmetric magnetism in twisted bilayer CrI3","volume":"23","author":"Kim","year":"2023","journal-title":"Nano Lett."},{"key":"mlstae484cbib26","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.108.L100401","type":"journal-article","article-title":"Controllable magnetic domains in twisted trilayer magnets","volume":"108","author":"Kim","year":"2023","journal-title":"Phys. Rev. B"},{"key":"mlstae484cbib27","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1021\/acs.nanolett.3c03246","type":"journal-article","article-title":"Emergence of stable meron quartets in twisted magnets","volume":"24","author":"Kim","year":"2024","journal-title":"Nano Lett."},{"key":"mlstae484cbib28","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad56fa","type":"journal-article","article-title":"Deep learning methods for Hamiltonian parameter estimation and magnetic domain image generation in twisted van der Waals magnets","volume":"5","author":"Lee","year":"2024","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstae484cbib29","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1038\/s41535-025-00789-w","type":"journal-article","article-title":"Emergence of Meron Kekul\u00e9 lattices in twisted N\u00e9el antiferromagnets","volume":"10","author":"Kim","year":"2025","journal-title":"npj Quantum Mater."},{"key":"mlstae484cbib30","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.3.013027","type":"journal-article","article-title":"Magnetization textures in twisted bilayer CrX3 (X = Br, I)","volume":"3","author":"Xiao","year":"2021","journal-title":"Phys. Rev. Res."},{"key":"mlstae484cbib31","doi-asserted-by":"publisher","DOI":"10.1002\/adfm.202206923","type":"journal-article","article-title":"Magnetic skyrmion lattices in a novel 2D-twisted bilayer magnet","volume":"33","author":"Zheng","year":"2023","journal-title":"Adv. Funct. Mater."},{"key":"mlstae484cbib32","doi-asserted-by":"publisher","first-page":"pp 770","DOI":"10.1109\/CVPR.2016.90)","type":"conference-proceedings","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"mlstae484cbib33","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","type":"conference-proceedings"},{"key":"mlstae484cbib34","author":"Mitchell","year":"1997","type":"book"},{"key":"mlstae484cbib35","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6633\/aab406","type":"journal-article","article-title":"Machine learning & artificial intelligence in the quantum domain","volume":"81","author":"Dunjko","year":"2018","journal-title":"Rep. Prog. Phys."},{"key":"mlstae484cbib36","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.91.045002","type":"journal-article","article-title":"Machine learning and the physical sciences","volume":"91","author":"Carleo","year":"2019","journal-title":"Rev. Mod. Phys."},{"key":"mlstae484cbib37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.physrep.2019.03.001","type":"journal-article","article-title":"A high-bias, low-variance introduction to machine learning for physicists","volume":"810","author":"Mehta","year":"2019","journal-title":"Phys. Rep."},{"key":"mlstae484cbib38","doi-asserted-by":"publisher","DOI":"10.7566\/JPSJ.85.123706","type":"journal-article","article-title":"Deep learning the quantum phase transitions in random two-dimensional electron systems","volume":"85","author":"Ohtsuki","year":"2016","journal-title":"J. Phys. Soc. Jpn."},{"key":"mlstae484cbib39","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1038\/nphys4035","type":"journal-article","article-title":"Machine learning phases of matter","volume":"13","author":"Carrasquilla","year":"2017","journal-title":"Nat. Phys."},{"key":"mlstae484cbib40","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.95.062122","type":"journal-article","article-title":"Discovering phases, phase transitions and crossovers through unsupervised machine learning: a critical examination","volume":"95","author":"Hu","year":"2017","journal-title":"Phys. Rev. E"},{"key":"mlstae484cbib41","doi-asserted-by":"publisher","DOI":"10.7566\/JPSJ.89.022001","type":"journal-article","article-title":"Drawing phase diagrams of random quantum systems by deep learning the wave functions","volume":"89","author":"Ohtsuki","year":"2020","journal-title":"J. Phys. Soc. Jpn."},{"key":"mlstae484cbib42","doi-asserted-by":"publisher","DOI":"10.1088\/1361-648X\/abb895","type":"journal-article","article-title":"Machine learning for condensed matter physics","volume":"33","author":"Bedolla","year":"2020","journal-title":"J. Condens. Matter Phys."},{"key":"mlstae484cbib43","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-38335-y","type":"journal-article","article-title":"Super-resolution of magnetic systems using deep learning","volume":"13","author":"Lee","year":"2023","journal-title":"Sci. Rep."},{"key":"mlstae484cbib44","doi-asserted-by":"publisher","first-page":"eabb0872","DOI":"10.1126\/sciadv.abb0872","type":"journal-article","article-title":"Magnetic hamiltonian parameter estimation using deep learning techniques","volume":"6","author":"Kwon","year":"2020","journal-title":"Sci. Adv."},{"key":"mlstae484cbib45","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202004795","type":"journal-article","article-title":"Magnetic state generation using hamiltonian guided variational autoencoder with spin structure stabilization","volume":"8","author":"Kwon","year":"2021","journal-title":"Adv. Sci."},{"key":"mlstae484cbib46","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-02374-0","type":"journal-article","article-title":"Estimating the effective fields of spin configurations using a deep learning technique","volume":"11","author":"Lee","year":"2021","journal-title":"Sci. Rep."},{"key":"mlstae484cbib47","doi-asserted-by":"publisher","DOI":"10.1021\/acsami.2c12848","type":"journal-article","article-title":"Understanding the magnetic microstructure through experiments and machine learning algorithms","volume":"14","author":"Talapatra","year":"2022","journal-title":"ACS Appl. Mater. Interfaces"},{"key":"mlstae484cbib48","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.108.184202","type":"journal-article","article-title":"Machine learning wave functions to identify fractal phases","volume":"108","author":"\u010cade\u017e","year":"2023","journal-title":"Phys. Rev. B"},{"key":"mlstae484cbib49","doi-asserted-by":"publisher","DOI":"10.7566\/JPSJ.94.031002","type":"journal-article","article-title":"Machine learning of phases and structures for model systems in physics","volume":"94","author":"Bayo","year":"2025","journal-title":"J. Phys. Soc. Jpn."},{"key":"mlstae484cbib50","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41586-018-0361-2","type":"journal-article","article-title":"Machine learning at the energy and intensity frontiers of particle physics","volume":"560","author":"Radovic","year":"2018","journal-title":"Nature"},{"key":"mlstae484cbib51","doi-asserted-by":"crossref","DOI":"10.1088\/1742-6596\/1085\/2\/022008","type":"preprint","article-title":"Machine learning in high energy physics community white paper","author":"Albertsson","year":"2018"},{"key":"mlstae484cbib52","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1146\/annurev-nucl-101917-021019","type":"journal-article","article-title":"Deep learning and its application to LHC physics","volume":"68","author":"Guest","year":"2018","journal-title":"Annu. Rev. Nucl. Part. Sci."},{"key":"mlstae484cbib53","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/nature23463","type":"journal-article","article-title":"Fast automated analysis of strong gravitational lenses with convolutional neural networks","volume":"548","author":"Hezaveh","year":"2017","journal-title":"Nature"},{"key":"mlstae484cbib54","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1904859116","type":"journal-article","article-title":"Machine learning and cosmology: opportunities and challenges","volume":"116","author":"Ntampaka","year":"2019","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"mlstae484cbib55","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.abj7478","type":"journal-article","article-title":"Direct visualization of magnetic domains and moir\u00e9 magnetism in twisted 2D magnets","volume":"374","author":"Song","year":"2021","journal-title":"Science"},{"key":"mlstae484cbib56","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.8.041028","type":"journal-article","article-title":"Topological spin excitations in honeycomb ferromagnet CrI3","volume":"8","author":"Chen","year":"2018","journal-title":"Phys. Rev. X"},{"key":"mlstae484cbib57","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1021\/ci0342472","type":"journal-article","article-title":"The problem of overfitting","volume":"44","author":"Hawkins","year":"2004","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"mlstae484cbib58","first-page":"pp 8024","type":"conference-proceedings","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"mlstae484cbib59","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.17200754","type":"web-resource","article-title":"Data for \u201cNeural Scaling Laws for Deep Regression\u201d (arXiv:2509.10000)","author":"Cadez","year":"2025"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae484c","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae484c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae484c","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae484c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae484c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae484c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae484c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae484c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T09:14:11Z","timestamp":1772183651000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae484c"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,27]]},"references-count":59,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2,27]]},"published-print":{"date-parts":[[2026,4,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ae484c","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,27]]},"assertion":[{"value":"Neural scaling laws for deep regression on domain image data of twisted magnets","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 2026 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-09-25","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-02-19","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-02-27","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}