{"id":"https://openalex.org/W7118064601","doi":"https://doi.org/10.1016/j.patrec.2026.01.003","title":"Generalization performance distributions along learning curves","display_name":"Generalization performance distributions along learning curves","publication_year":2026,"publication_date":"2026-01-03","ids":{"openalex":"https://openalex.org/W7118064601","doi":"https://doi.org/10.1016/j.patrec.2026.01.003"},"language":"en","primary_location":{"id":"doi:10.1016/j.patrec.2026.01.003","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patrec.2026.01.003","pdf_url":null,"source":{"id":"https://openalex.org/S151820558","display_name":"Pattern Recognition Letters","issn_l":"0167-8655","issn":["0167-8655","1872-7344"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.patrec.2026.01.003","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002562774","display_name":"O. Taylan Turan","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"O. Taylan Turan","raw_affiliation_strings":["Pattern Recognition and Bioinformatics Laboratory, Delft University of Technology, Van Mourik Broekmanweg 6, Delft, 2628 XE, The Netherlands"],"raw_orcid":"https://orcid.org/0009-0004-1022-6334","affiliations":[{"raw_affiliation_string":"Pattern Recognition and Bioinformatics Laboratory, Delft University of Technology, Van Mourik Broekmanweg 6, Delft, 2628 XE, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121850513","display_name":"Marco Loog","orcid":null},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marco Loog","raw_affiliation_strings":["Institute for Computing and Information Sciences, Radboud University, Toernooiveld 212, Nijmegen, 6525 EC, The Netherlands","Pattern Recognition and Bioinformatics Laboratory, Delft University of Technology, Van Mourik Broekmanweg 6, Delft, 2628 XE, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-1298-8461","affiliations":[{"raw_affiliation_string":"Institute for Computing and Information Sciences, Radboud University, Toernooiveld 212, Nijmegen, 6525 EC, The Netherlands","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Pattern Recognition and Bioinformatics Laboratory, Delft University of Technology, Van Mourik Broekmanweg 6, Delft, 2628 XE, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114334927","display_name":"David M. J. Tax","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"David M.J. Tax","raw_affiliation_strings":["Pattern Recognition and Bioinformatics Laboratory, Delft University of Technology, Van Mourik Broekmanweg 6, Delft, 2628 XE, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-5153-9087","affiliations":[{"raw_affiliation_string":"Pattern Recognition and Bioinformatics Laboratory, Delft University of Technology, Van Mourik Broekmanweg 6, Delft, 2628 XE, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002562774"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":{"value":2500,"currency":"USD","value_usd":2500},"apc_paid":{"value":2500,"currency":"USD","value_usd":2500},"fwci":33.414,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98208147,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"201","issue":null,"first_page":"29","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.3012999892234802,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.3012999892234802,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.21969999372959137,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.12359999865293503,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7134000062942505},{"id":"https://openalex.org/keywords/learning-curve","display_name":"Learning curve","score":0.6848000288009644},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.6208999752998352},{"id":"https://openalex.org/keywords/quantile","display_name":"Quantile","score":0.5845999717712402},{"id":"https://openalex.org/keywords/standard-deviation","display_name":"Standard deviation","score":0.5250999927520752},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.48339998722076416},{"id":"https://openalex.org/keywords/statistical-learning","display_name":"Statistical learning","score":0.44859999418258667},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44190001487731934},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4291999936103821}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7134000062942505},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.6848000288009644},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.6208999752998352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5956000089645386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5885999798774719},{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.5845999717712402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5412999987602234},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48339998722076416},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4449999928474426},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4075999855995178},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.34310001134872437},{"id":"https://openalex.org/C2779915298","wikidata":"https://www.wikidata.org/wiki/Q7604400","display_name":"Statistical learning theory","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.33309999108314514},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.31200000643730164},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C102094743","wikidata":"https://www.wikidata.org/wiki/Q133871","display_name":"Normal distribution","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.2572999894618988}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.patrec.2026.01.003","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patrec.2026.01.003","pdf_url":null,"source":{"id":"https://openalex.org/S151820558","display_name":"Pattern Recognition Letters","issn_l":"0167-8655","issn":["0167-8655","1872-7344"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition Letters","raw_type":"journal-article"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/328324","is_oa":false,"landing_page_url":"https://hdl.handle.net/2066/328324","pdf_url":null,"source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article / Letter to editor"}],"best_oa_location":{"id":"doi:10.1016/j.patrec.2026.01.003","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patrec.2026.01.003","pdf_url":null,"source":{"id":"https://openalex.org/S151820558","display_name":"Pattern Recognition Letters","issn_l":"0167-8655","issn":["0167-8655","1872-7344"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1975107026","https://openalex.org/W2000280933","https://openalex.org/W2001710797","https://openalex.org/W2167277498","https://openalex.org/W2168745915","https://openalex.org/W2895205778","https://openalex.org/W4312203799","https://openalex.org/W4412002212"],"related_works":[],"abstract_inverted_index":{"\u2022":[0,4,12,18,28,38],"Research":[1],"Highlights":[2],"(Required)":[3],"A":[5],"high-fidelity":[6,124],"learning":[7,22,47,93,119,125,172,213,216],"curve":[8,126],"database":[9],"is":[10,62,77,105],"created.":[11],"Classifier":[13],"performance":[14,31,54,88,116,151],"distributions":[15,20,113],"are":[16,89],"investigated.":[17],"Performance":[19],"along":[21,46,171],"curves":[23,50],"often":[24,63],"deviate":[25,34],"from":[26,35],"normality.":[27],"Differences":[29],"in":[30],"between":[32],"models":[33,214],"normal":[36],"distributions.":[37],"Using":[39],"alternative":[40],"statistical":[41,181,201],"measures":[42,185,202],"alter":[43],"model":[44,191],"rankings":[45],"curves.":[48,94,120,173,217],"Learning":[49],"show":[51,176],"the":[52,84,112,118,138,178,189,196],"expected":[53],"with":[55,99,129,215],"respect":[56,130],"to":[57,65,131],"training":[58,132,143],"set":[59,133,144],"size.":[60,145],"This":[61],"used":[64],"evaluate":[66],"and":[67,72,135,203,210],"compare":[68],"models,":[69],"tune":[70],"hyper-parameters":[71],"determine":[73],"how":[74],"much":[75],"data":[76],"needed":[78],"for":[79,140,157],"a":[80,123,141,154],"specific":[81],"performance.":[82],"However,":[83],"distributional":[85],"properties":[86],"of":[87,114,137,161,180,198,205],"frequently":[90],"overlooked":[91],"on":[92,117],"Generally,":[95],"only":[96],"an":[97],"average":[98],"standard":[100,103],"error":[101],"or":[102,168],"deviation":[104],"used.":[106],"In":[107],"this":[108],"paper,":[109],"we":[110,175],"analyze":[111],"generalization":[115,150],"We":[121],"compile":[122],"database,":[127],"both":[128],"size":[134],"repetitions":[136],"sampling":[139,166],"fixed":[142],"Our":[146,193],"investigation":[147],"reveals":[148],"that":[149,177],"rarely":[152],"follows":[153],"Gaussian":[155],"distribution":[156],"classical":[158],"classifiers,":[159],"regardless":[160],"dataset":[162],"balance,":[163],"loss":[164],"function,":[165],"method,":[167],"hyper-parameter":[169],"tuning":[170],"Furthermore,":[174],"choice":[179],"summary,":[182],"mean":[183],"versus":[184],"like":[186],"quantiles":[187],"affect":[188],"top":[190],"rankings.":[192],"findings":[194],"highlight":[195],"importance":[197],"considering":[199],"different":[200],"use":[204],"non-parametric":[206],"approaches":[207],"when":[208],"evaluating":[209],"selecting":[211],"machine":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-30T09:15:22.047038","created_date":"2026-01-03T00:00:00"}