{"id":"https://openalex.org/W30208763","doi":null,"title":"The paradox of overfitting","display_name":"The paradox of overfitting","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W30208763","mag":"30208763"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.4231","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.4231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://volker.nannen.com/pdf/the_paradox_of_overfitting.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033479793","display_name":"Volker Nannen","orcid":"https://orcid.org/0000-0002-5767-0190","observed_orcids":["https://orcid.org/0000-0002-5767-0190"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Volker Nannen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5767-0190","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5033479793"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.00377776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.8978999853134155,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.8978999853134155,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10136","display_name":"Statistical Methods and Inference","score":0.02370000071823597,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.015399999916553497,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.8650000095367432},{"id":"https://openalex.org/keywords/model-selection","display_name":"model selection","score":0.9980000257492065},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"minimum description length","score":0.8420000076293945},{"id":"https://openalex.org/keywords/kolmogorov-complexity","display_name":"Kolmogorov complexity","score":0.9660000205039978},{"id":"https://openalex.org/keywords/generalization-error","display_name":"generalization error","score":0.9629999995231628},{"id":"https://openalex.org/keywords/polynomial-regression","display_name":"polynomial regression","score":0.8679999709129333},{"id":"https://openalex.org/keywords/interactive-visualization","display_name":"interactive visualization","score":0.5889999866485596}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9185287952423096},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.8480004668235779},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7772088646888733},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.7518925070762634},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.6316837072372437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6154171824455261},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6010404825210571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5629821419715881},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5156034827232361},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4848364591598511},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4588537812232971},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3478100895881653},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15348100662231445},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12155535817146301},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.4231","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.4231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://volker.nannen.com/pdf/the_paradox_of_overfitting.pdf","raw_type":"text"},{"id":"mag:30208763","doi":null,"is_oa":false,"landing_page_url":"https://volker.nannen.com/pdf/the_paradox_of_overfitting.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W158727920","https://openalex.org/W572135912","https://openalex.org/W1588146227","https://openalex.org/W1638203394","https://openalex.org/W1969678783","https://openalex.org/W1995875735","https://openalex.org/W2005097301","https://openalex.org/W2053565514","https://openalex.org/W2054658115","https://openalex.org/W2058815839","https://openalex.org/W2082397409","https://openalex.org/W2099111195","https://openalex.org/W2114804254","https://openalex.org/W2117388928","https://openalex.org/W2120078031","https://openalex.org/W2126160338","https://openalex.org/W2136064961","https://openalex.org/W2141394518","https://openalex.org/W2154462988","https://openalex.org/W2170052858","https://openalex.org/W2296087697","https://openalex.org/W2328418989","https://openalex.org/W2333976070","https://openalex.org/W2947000318"],"related_works":["https://openalex.org/W2130372067","https://openalex.org/W2240452364","https://openalex.org/W7099218209","https://openalex.org/W7098154580","https://openalex.org/W1840091437","https://openalex.org/W2925920795","https://openalex.org/W6941534426","https://openalex.org/W7099091421","https://openalex.org/W2489956408","https://openalex.org/W2038730462"],"abstract_inverted_index":{"Model":[0],"selection":[1,20,143,209],"plays":[2],"an":[3,164],"important":[4],"part":[5],"in":[6,10,13,63,96],"machine":[7],"learning":[8],"and":[9,52,78,115,178,188,195,198,220],"artificial":[11],"intelligence":[12],"general.":[14],"A":[15],"central":[16],"problem":[17,213],"to":[18,72,170,172,176],"model":[19,102,107,114,183,208],"is":[21,38,88,167],"overfitting.":[22],"It":[23,93,122],"can":[24,83],"be":[25,84],"measured":[26],"as":[27,118,140,146],"the":[28,35,40,49,66,80,97,110,119,135,159,180,204,221,228],"generalization":[29,36,81,229],"error":[30,37,82,230],"on":[31,139],"test":[32],"samples.":[33,234],"Minimizing":[34],"not":[39,61],"only":[41],"definition":[42],"of":[43,48,65,99,113,137,144,182,200,207,216],"a":[44,89,106,142,193],"good":[45],"model.":[46],"Resemblance":[47],"original":[50,67],"function":[51,68],"minimum":[53,75],"randomness":[54,76,129],"deficiency":[55,77,130],"are":[56,60,210,223],"others.":[57],"While":[58,156],"we":[59,69,148,231],"interested":[62],"resemblance":[64],"do":[70],"want":[71],"know":[73],"if":[74],"minimizing":[79],"combined.":[85],"Kolmogorov":[86],"complexity":[87,112],"powerful":[90],"mathematical":[91],"tool.":[92],"has":[94,123,163],"resulted":[95],"theory":[98],"MDL":[100,104,127,138],"for":[101,158,192],"selection.":[103,184],"selects":[105],"that":[108,126,166],"minimizes":[109,128],"combined":[111],"data,":[116],"known":[117],"two-part":[120],"code.":[121],"been":[124],"proven":[125],"[VV02].":[131],"To":[132,225],"efficiently":[133],"map":[134],"performance":[136],"broad":[141],"problems":[145,181,219],"possible":[147],"introduced":[149],"our":[150],"own":[151],"application,\r\nthe":[152],"Statistical":[153],"Data":[154],"Viewer.":[155],"intended":[157],"advanced":[160],"scientist,":[161],"it":[162],"interface":[165],"easy":[168],"enough":[169],"use":[171,232],"allow":[173,191],"uninitiated":[174],"students":[175],"explore":[177],"comprehend":[179],"Its":[185],"interactive":[186],"plots":[187],"sophisticated":[189],"editor":[190],"fast":[194],"efficient":[196],"setup":[197],"execution":[199],"controlled":[201],"experiments.":[202],"All":[203],"relevant":[205],"aspects":[206],"implemented.":[211],"The":[212],"space":[214],"consists":[215],"two-dimensional":[217],"regression":[218],"models":[222],"polynomials.":[224],"objectively":[226],"measure":[227],"i.i.d.test":[233]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}