{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T06:25:55Z","timestamp":1768890355491,"version":"3.49.0"},"reference-count":75,"publisher":"MIT Press","issue":"6","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Small data learning problems are characterized by a significant discrepancy between the limited number of response variable observations and the large feature space dimension. In this setting, the common learning tools struggle to identify the features important for the classification task from those that bear no relevant information and cannot derive an appropriate learning rule that allows discriminating among different classes. As a potential solution to this problem, here we exploit the idea of reducing and rotating the feature space in a lower-dimensional gauge and propose the gauge-optimal approximate learning (GOAL) algorithm, which provides an analytically tractable joint solution to the dimension reduction, feature segmentation, and classification problems for small data learning problems. We prove that the optimal solution of the GOAL algorithm consists in piecewise-linear functions in the Euclidean space and that it can be approximated through a monotonically convergent algorithm that presents\u2014under the assumption of a discrete segmentation of the feature space\u2014a closed-form solution for each optimization substep and an overall linear iteration cost scaling. The GOAL algorithm has been compared to other state-of-the-art machine learning tools on both synthetic data and challenging real-world applications from climate science and bioinformatics (i.e., prediction of the El Ni\u00f1o Southern Oscillation and inference of epigenetically induced gene-activity networks from limited experimental data). The experimental results show that the proposed algorithm outperforms the reported best competitors for these problems in both learning performance and computational cost.<\/jats:p>","DOI":"10.1162\/neco_a_01664","type":"journal-article","created":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T21:19:51Z","timestamp":1714166391000},"page":"1198-1227","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":4,"title":["Gauge-Optimal Approximate Learning for Small Data Classification"],"prefix":"10.1162","volume":"36","author":[{"given":"Edoardo","family":"Vecchi","sequence":"first","affiliation":[{"name":"Universit\u00e0 della Svizzera Italiana, Faculty of Informatics, Institute of Computing, 6962 Lugano, Switzerland edoardo.vecchi@usi.ch"}]},{"given":"Davide","family":"Bassetti","sequence":"additional","affiliation":[{"name":"Technical University of Kaiserslautern, Faculty of Mathematics, Group of Mathematics of AI, 67663 Kaiserslautern, Germany bassetti@mathematik.uni-kl.de"}]},{"given":"Fabio","family":"Graziato","sequence":"additional","affiliation":[{"name":"Independent researcher, 22070 Valmorea, Italy fabio.graziato94@gmail.com"}]},{"given":"Luk\u00e1\u0161","family":"Posp\u00ed\u0161il","sequence":"additional","affiliation":[{"name":"VSB Ostrava, Department of Mathematics, Ludvika Podeste 1875\/17 708 33 Ostrava, Czech Republic lukas.pospisil@vsb.cz"}]},{"given":"Illia","family":"Horenko","sequence":"additional","affiliation":[{"name":"Technical University of Kaiserslautern, Faculty of Mathematics, Group of Mathematics of AI, 67663 Kaiserslautern, Germany horenko@rptu.de"}]}],"member":"281","published-online":{"date-parts":[[2024,5,10]]},"reference":[{"issue":"1","key":"2024082215382178200_bib1","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-020-73449-7","article-title":"Fokker\u2013Planck dynamics of the El Ni\u00f1o-southern oscillation","volume":"10","author":"An","year":"2020","journal-title":"Scientific Reports"},{"key":"2024082215382178200_bib2","article-title":"On learning rotations","volume-title":"Advances in neural information processing systems","author":"Arora","year":"2009"},{"key":"2024082215382178200_bib3","first-page":"1027","article-title":"K-means++ the advantages of careful seeding","volume-title":"Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms","author":"Arthur","year":"2007"},{"issue":"1","key":"2024082215382178200_bib4","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1049\/trit.2019.0028","article-title":"Deep learning approach for microarray cancer data classification","volume":"5","author":"Basavegowda","year":"2020","journal-title":"CAAI Transactions on Intelligence Technology"},{"issue":"1","key":"2024082215382178200_bib5","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine Learning"},{"key":"2024082215382178200_bib6","volume-title":"Classification and regression trees","author":"Breiman","year":"1984"},{"issue":"3","key":"2024082215382178200_bib7","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1016\/j.bpsc.2017.11.007","article-title":"Machine learning for precision psychiatry: Opportunities and challenges","volume":"3","author":"Bzdok","year":"2018","journal-title":"Biological Psychiatry: Cognitive Neuroscience and Neuroimaging"},{"key":"2024082215382178200_bib8","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"9","key":"2024082215382178200_bib9","doi-asserted-by":"publisher","first-page":"2455","DOI":"10.1175\/JAMC-D-16-0249.1","article-title":"The impact of El Ni\u00f1o\u2013Southern Oscillation (ENSO) on winter and early spring us tornado outbreaks","volume":"56","author":"Cook","year":"2017","journal-title":"Journal of Applied Meteorology and Climatology"},{"key":"2024082215382178200_bib10","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511801389","volume-title":"An introduction to support vector machines and other kernel-based learning methods","author":"Cristianini","year":"2000"},{"issue":"D1","key":"2024082215382178200_bib11","doi-asserted-by":"publisher","first-page":"D794","DOI":"10.1093\/nar\/gkx1081","article-title":"The encyclopedia of DNA elements (encode), data portal update","volume":"46","author":"Davis","year":"2018","journal-title":"Nucleic Acids Research"},{"key":"2024082215382178200_bib12","doi-asserted-by":"publisher","DOI":"10.3389\/fphy.2019.00153","article-title":"The application of machine learning techniques to improve El Ni\u00f1o prediction skill","volume":"7","author":"Dijkstra","year":"2019","journal-title":"Frontiers in Physics"},{"issue":"3","key":"2024082215382178200_bib13","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1109\/18.382009","article-title":"De-noising by soft-thresholding","volume":"41","author":"Donoho","year":"1995","journal-title":"IEEE Transactions on Information Theory"},{"issue":"13","key":"2024082215382178200_bib14","doi-asserted-by":"publisher","first-page":"8736","DOI":"10.1021\/acs.chemrev.3c00189","article-title":"Machine learning methods for small data challenges in molecular science","volume":"123","author":"Dou","year":"2023","journal-title":"Chemical Reviews"},{"key":"2024082215382178200_bib15","first-page":"1","article-title":"C4.5, class imbalance, and cost sensitivity: Why under-sampling beats over-sampling","volume-title":"Workshop on Learning from Imbalanced Datasets II","author":"Drummond","year":"2003"},{"issue":"1","key":"2024082215382178200_bib16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-020-57866-2","article-title":"Structural analysis and optimization of convolutional neural networks with a small sample size","volume":"10","author":"D\u2019Souza","year":"2020","journal-title":"Scientific Reports"},{"issue":"1","key":"2024082215382178200_bib17","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1016\/j.csda.2007.02.001","article-title":"Improving implementation of linear discriminant analysis for the high dimension\/small sample size problem","volume":"52","author":"Duintjer Tebbens","year":"2007","journal-title":"Computational Statistics and Data Analysis"},{"key":"2024082215382178200_bib18","article-title":"Using deep learning to enhance cancer diagnosis and classification","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Fakoor","year":"2013"},{"issue":"2","key":"2024082215382178200_bib19","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1093\/nsr\/nwt032","article-title":"Challenges of big data analysis","volume":"1","author":"Fan","year":"2014","journal-title":"National Science Review"},{"key":"2024082215382178200_bib20","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-98074-4","volume-title":"Learning from imbalanced data sets","author":"Fern\u00e1ndez","year":"2018"},{"key":"2024082215382178200_bib21","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-05318-5_1","article-title":"Hyperparameter optimization","volume-title":"Automated machine learning","author":"Feurer","year":"2019"},{"issue":"2","key":"2024082215382178200_bib22","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1111\/j.1469-1809.1936.tb02137.x","article-title":"The use of multiple measurements in taxonomic problems","volume":"7","author":"Fisher","year":"1936","journal-title":"Annals of Eugenics"},{"issue":"5","key":"2024082215382178200_bib23","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aaw0961","article-title":"Low-cost scalable discretization, prediction, and feature selection for complex systems","volume":"6","author":"Gerber","year":"2020","journal-title":"Science Advances"},{"issue":"6316","key":"2024082215382178200_bib24","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1038\/350324a0","article-title":"Interdecadal oscillations and the warming trend in global temperature time series","volume":"350","author":"Ghil","year":"1991","journal-title":"Nature"},{"key":"2024082215382178200_bib25","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","author":"Glorot","year":"2010"},{"key":"2024082215382178200_bib26","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1137\/0702016","article-title":"Singular value decomposition and principal component analysis","volume":"2","author":"Golub","year":"1965","journal-title":"Journal of the Society for Industrial and Applied Mathematics, Series B Numerical Analysis"},{"issue":"1","key":"2024082215382178200_bib27","doi-asserted-by":"crossref","DOI":"10.1061\/(ASCE)HE.1943-5584.0001872","article-title":"Impact of ENSO, global warming, and land surface elevation on extreme precipitation in India","volume":"25","author":"Gupta","year":"2020","journal-title":"Journal of Hydrologic Engineering"},{"issue":"7775","key":"2024082215382178200_bib28","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1038\/s41586-019-1559-7","article-title":"Deep learning for multi-year ENSO forecasts","volume":"573","author":"Ham","year":"2019","journal-title":"Nature"},{"key":"2024082215382178200_bib29","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The elements of statistical learning: Data mining, inference, and prediction","author":"Hastie","year":"2009"},{"key":"2024082215382178200_bib30","first-page":"12","article-title":"DLENSO: A deep learning ENSO forecasting model","volume-title":"Proceedings of the Pacific Rim International Conference on Artificial Intelligence","author":"He","year":"2019"},{"issue":"4","key":"2024082215382178200_bib31","doi-asserted-by":"publisher","first-page":"576","DOI":"10.1016\/j.molcel.2010.05.004","article-title":"Simple combinations of lineage-determining transcription factors prime cis-regulatory elements required for macrophage and B cell identities","volume":"38","author":"Heinz","year":"2010","journal-title":"Molecular Cell"},{"issue":"8","key":"2024082215382178200_bib32","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"issue":"8","key":"2024082215382178200_bib33","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1162\/neco_a_01296","article-title":"On a scalable entropic breaching of the overfitting barrier for small data problems in machine learning","volume":"32","author":"Horenko","year":"2020","journal-title":"Neural Computation"},{"issue":"6","key":"2024082215382178200_bib34","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging8060156","article-title":"Low-cost probabilistic 3D denoising with applications for ultra-low-radiation computed tomography","volume":"8","author":"Horenko","year":"2022","journal-title":"Journal of Imaging"},{"issue":"1","key":"2024082215382178200_bib35","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2214972120","article-title":"On cheap entropy-sparsified regression learning","volume":"120","author":"Horenko","year":"2023","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2024082215382178200_bib36","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1016\/j.neubiorev.2020.09.036","article-title":"I tried a bunch of things: The dangers of unexpected overfitting in classification of brain data","volume":"119","author":"Hosseini","year":"2020","journal-title":"Neuroscience and Biobehavioral Reviews"},{"issue":"4","key":"2024082215382178200_bib37","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1007\/s13218-015-0381-0","article-title":"Beyond manual tuning of hyperparameters","volume":"29","author":"Hutter","year":"2015","journal-title":"KI-K\u00fcnstliche Intelligenz"},{"key":"2024082215382178200_bib38","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.3624052","article-title":"Can machines \u201clearn\u201d finance?","author":"Israel","year":"2020"},{"key":"2024082215382178200_bib39","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/BF02418571","article-title":"Sur les fonctions convexes et les in\u00e9galit\u00e9s entre les valeurs moyennes","volume":"30","author":"Jensen","year":"1906","journal-title":"Acta Mathematica"},{"key":"2024082215382178200_bib40","first-page":"1","article-title":"Deep learning for underwater image recognition in small sample size situations","volume-title":"Proceedings","author":"Jin","year":"2017"},{"issue":"3","key":"2024082215382178200_bib41","article-title":"Principal component analysis","volume":"45","author":"Jolliffe","year":"2003","journal-title":"Technometrics"},{"issue":"11","key":"2024082215382178200_bib42","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1002\/pro.3715","article-title":"Toward understanding the origin and evolution of cellular organisms","volume":"28","author":"Kanehisa","year":"2019","journal-title":"Protein Science"},{"issue":"D1","key":"2024082215382178200_bib43","doi-asserted-by":"publisher","first-page":"D545","DOI":"10.1093\/nar\/gkaa970","article-title":"KEGG: Integrating viruses and cellular organisms","volume":"49","author":"Kanehisa","year":"2021","journal-title":"Nucleic Acids Research"},{"key":"2024082215382178200_bib44","doi-asserted-by":"crossref","DOI":"10.1016\/j.epsr.2022.108613","article-title":"BELTISTOS: A robust interior point method for large-scale optimal power flow problems","volume":"212","author":"Kardo\u0161","year":"2022","journal-title":"Electric Power Systems Research"},{"key":"2024082215382178200_bib45","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/978-981-10-6602-3_3","article-title":"Comparing the behavior of oversampling and undersampling approach of class imbalance learning by combining class imbalance problem with noise","volume-title":"ICT based innovations","author":"Kaur","year":"2018"},{"key":"2024082215382178200_bib46","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1109\/BigMM50055.2020.00028","article-title":"Unravelling small sample size problems in the deep learning world","volume-title":"Proceedings of the 2020 IEEE Sixth International Conference on Multimedia Big Data","author":"Keshari","year":"2020"},{"key":"2024082215382178200_bib47","author":"Kingma","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"issue":"3","key":"2024082215382178200_bib48","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1038\/s41558-019-0404-1","article-title":"Applying big data beyond small problems in climate research","volume":"9","author":"Knusel","year":"2019","journal-title":"Nature Climate Change"},{"key":"2024082215382178200_bib49","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1016\/B978-1-55860-377-6.50045-1","article-title":"Automatic parameter selection by minimizing estimated error","volume-title":"Machine Learning Proceedings 1995","author":"Kohavi","year":"1995"},{"issue":"1","key":"2024082215382178200_bib50","doi-asserted-by":"publisher","DOI":"10.1177\/00368504211029777","article-title":"Machine learning on small size samples: A synthetic knowledge synthesis","volume":"105","author":"Kokol","year":"2022","journal-title":"Science Progress"},{"issue":"3","key":"2024082215382178200_bib51","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1177\/0962280220970228","article-title":"Small sample sizes: A big data problem in high-dimensional data analysis","volume":"30","author":"Konietschke","year":"2021","journal-title":"Statistical Methods in Medical Research"},{"issue":"1","key":"2024082215382178200_bib52","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1038\/s41386-020-0767-z","article-title":"Deep learning for small and big data in psychiatry","volume":"46","author":"Koppe","year":"2021","journal-title":"Neuropsychopharmacology"},{"issue":"1","key":"2024082215382178200_bib53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13721-016-0125-6","article-title":"A review of automatic selection methods for machine learning algorithms and hyper-parameter values","volume":"5","author":"Luo","year":"2016","journal-title":"Network Modeling Analysis in Health Informatics and Bioinformatics"},{"key":"2024082215382178200_bib54","first-page":"105","article-title":"Conditional logit analysis of qualitative choice behavior","volume-title":"Frontiers in econometrics","author":"McFadden","year":"1973"},{"key":"2024082215382178200_bib55","first-page":"243","article-title":"Machine learning with oversampling and undersampling techniques: Overview study and experimental results","volume-title":"Proceedings of the 11th International Conference on Information and Communication Systems","author":"Mohammed","year":"2020"},{"key":"2024082215382178200_bib56","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-89010-0_4","volume-title":"Overfitting, model tuning, and evaluation of prediction performance","author":"Montesinos L\u00f3pez","year":"2022"},{"key":"2024082215382178200_bib57","volume-title":"Numerical optimization","author":"Nocedal","year":"2006","edition":"2nd"},{"issue":"1","key":"2024082215382178200_bib58","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/27.1.29","article-title":"KEGG: Kyoto encyclopedia of genes and genomes","volume":"27","author":"Ogata","year":"1999","journal-title":"Nucleic Acids Research"},{"issue":"8","key":"2024082215382178200_bib59","doi-asserted-by":"publisher","first-page":"2688","DOI":"10.1109\/TMI.2020.2993291","article-title":"Deep learning covid-19 features on CXR using limited training data sets","volume":"39","author":"Oh","year":"2020","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"2024082215382178200_bib60","volume-title":"Finite mixture models.","author":"Peel","year":"2000"},{"key":"2024082215382178200_bib61","volume-title":"The matrix cookbook","author":"Petersen","year":"2008"},{"key":"2024082215382178200_bib62","article-title":"Small data challenges in big data era: A survey of recent progress on unsupervised and semi-supervised methods","volume-title":"Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence","author":"Qi","year":"2020"},{"key":"2024082215382178200_bib63","first-page":"8093","article-title":"Overfitting in adversarially robust deep learning","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Rice","year":"2020"},{"key":"2024082215382178200_bib64","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/CTS.2013.6567202","article-title":"Big data: A review","volume-title":"Proceedings of the 2013 International Conference on Collaboration Technologies and Systems","author":"Sagiroglu","year":"2013"},{"key":"2024082215382178200_bib65","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.procs.2015.04.060","article-title":"Feature selection of gene expression data for cancer classification: A review","volume":"50","author":"Singh","year":"2015","journal-title":"Procedia Computer Science"},{"issue":"18","key":"2024082215382178200_bib66","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph17186933","article-title":"Unveiling covid-19 from chest x-ray with deep learning: A hurdles race with small data","volume":"17","author":"Tartaglione","year":"2020","journal-title":"International Journal of Environmental Research and Public Health"},{"issue":"11","key":"2024082215382178200_bib67","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0224365","article-title":"Machine learning algorithm validation with a limited sample size","volume":"14","author":"Vabalas","year":"2019","journal-title":"PLOS One"},{"issue":"11","key":"2024082215382178200_bib68","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"2024082215382178200_bib69","doi-asserted-by":"publisher","DOI":"10.1016\/j.ribaf.2023.101958","article-title":"Entropic approximate learning for financial decision-making in the small data regime","volume":"65","author":"Vecchi","year":"2023","journal-title":"Research in International Business and Finance"},{"issue":"5","key":"2024082215382178200_bib70","doi-asserted-by":"publisher","first-page":"1220","DOI":"10.1162\/neco_a_01490","article-title":"eSPA+: Scalable entropy-optimal machine learning classification for small data problems","volume":"34","author":"Vecchi","year":"2022","journal-title":"Neural Computation"},{"issue":"1","key":"2024082215382178200_bib71","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1007\/s10107-004-0559-y","article-title":"On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming","volume":"106","author":"W\u00e4chter","year":"2005","journal-title":"Mathematical Programming"},{"issue":"10","key":"2024082215382178200_bib72","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1038\/s41592-021-01205-4","article-title":"DOME: Recommendations for supervised machine learning validation in biology","volume":"18","author":"Walsh","year":"2021","journal-title":"Nature Methods"},{"key":"2024082215382178200_bib73","first-page":"13","article-title":"An application of oversampling, undersampling, bagging and boosting in handling imbalanced datasets","volume-title":"Proceedings of the First International Conference on Advanced Data and Information Engineering","author":"Yap","year":"2014"},{"key":"2024082215382178200_bib74","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.110121","article-title":"Deep learning methods for forecasting covid-19 time-series data: A comparative study","volume":"140","author":"Zeroual","year":"2020","journal-title":"Chaos, Solitons and Fractals"},{"key":"2024082215382178200_bib75","author":"Zhang","year":"2019","journal-title":"A survey on deep learning of small sample in biomedical image analysis."}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/36\/6\/1198\/2467115\/neco_a_01664.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/36\/6\/1198\/2467115\/neco_a_01664.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T16:07:43Z","timestamp":1724342863000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/36\/6\/1198\/120667\/Gauge-Optimal-Approximate-Learning-for-Small-Data"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,10]]},"references-count":75,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,5,10]]},"published-print":{"date-parts":[[2024,5,10]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01664","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,6]]},"published":{"date-parts":[[2024,5,10]]}}}