{"id":"https://openalex.org/W7225186608","doi":"https://doi.org/10.48550/arxiv.2611.02856","title":"Kolmogorov-Arnold Networks vs. Multi-Layer Perceptrons: A Rigorous Statistical Benchmark on Clinical Tabular Data","display_name":"Kolmogorov-Arnold Networks vs. Multi-Layer Perceptrons: A Rigorous Statistical Benchmark on Clinical Tabular Data","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225186608","doi":"https://doi.org/10.48550/arxiv.2611.02856"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.02856","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02856","pdf_url":"https://arxiv.org/pdf/2611.02856","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.02856","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160431440","display_name":"Rafa\u0142 Wodzi\u0144ski","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24881138","display_name":"Cracow University of Technology","ror":"https://ror.org/00pdej676","country_code":"PL","type":"education","lineage":["https://openalex.org/I24881138"]},{"id":"https://openalex.org/I4405252653","display_name":"Sano \u2013 Centre for Computational Personalised Medicine International Research Foundation","ror":"https://ror.org/04h58p752","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4405252653"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Wodzi\u0144ski, Rafa\u0142","raw_affiliation_strings":["Department of Computer Science , Faculty of Computer Science and Mathematics , Cracow University of Technology , Krak\u00f3w , Poland","Sano Centre for Computational Medicine , Krak\u00f3w , Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Faculty of Computer Science and Mathematics , Cracow University of Technology , Krak\u00f3w , Poland","institution_ids":["https://openalex.org/I24881138"]},{"raw_affiliation_string":"Sano Centre for Computational Medicine , Krak\u00f3w , Poland","institution_ids":["https://openalex.org/I4405252653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040782719","display_name":"Pawe\u0142 Szczerbiak","orcid":"https://orcid.org/0000-0002-7487-6545","observed_orcids":["https://orcid.org/0000-0002-7487-6545"]},"institutions":[{"id":"https://openalex.org/I4405252653","display_name":"Sano \u2013 Centre for Computational Personalised Medicine International Research Foundation","ror":"https://ror.org/04h58p752","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4405252653"]},{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Szczerbiak, Pawe\u0142","raw_affiliation_strings":["Faculty of Computer Science , AGH University of Krakow , Krak\u00f3w , Poland","Sano Centre for Computational Medicine , Krak\u00f3w , Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science , AGH University of Krakow , Krak\u00f3w , Poland","institution_ids":["https://openalex.org/I686019"]},{"raw_affiliation_string":"Sano Centre for Computational Medicine , Krak\u00f3w , Poland","institution_ids":["https://openalex.org/I4405252653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10320","display_name":"Neural Networks and Applications","score":0.3393999934196472,"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/T10320","display_name":"Neural Networks and Applications","score":0.3393999934196472,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.32670000195503235,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.10980000346899033,"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/kolmogorov-arnold-networks","display_name":"Kolmogorov-Arnold networks","score":0.9919999837875366},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"multilayer perceptron","score":0.9919999837875366},{"id":"https://openalex.org/keywords/tabular-clinical-data","display_name":"tabular clinical data","score":0.6119999885559082},{"id":"https://openalex.org/keywords/benchmark-comparison","display_name":"benchmark comparison","score":0.5049999952316284},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.9490000009536743},{"id":"https://openalex.org/keywords/precision-recall-curve","display_name":"precision-recall curve","score":0.7009999752044678},{"id":"https://openalex.org/keywords/brier-score","display_name":"Brier score","score":0.9430000185966492},{"id":"https://openalex.org/keywords/region-of-practical-equivalence","display_name":"region of practical equivalence","score":0.9449999928474426},{"id":"https://openalex.org/keywords/inference-latency","display_name":"inference latency","score":0.6370000243186951}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6676999926567078},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5849999785423279},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5788999795913696},{"id":"https://openalex.org/C35405484","wikidata":"https://www.wikidata.org/wiki/Q4967066","display_name":"Brier score","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5267000198364258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4754999876022339},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4383000135421753},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4025000035762787},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.375},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.3619999885559082},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3612000048160553},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.32030001282691956},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C162040801","wikidata":"https://www.wikidata.org/wiki/Q799897","display_name":"Bootstrap aggregating","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.27900001406669617},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C2776493592","wikidata":"https://www.wikidata.org/wiki/Q5158717","display_name":"Succinctness","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.26420000195503235},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2603999972343445}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.02856","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02856","pdf_url":"https://arxiv.org/pdf/2611.02856","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2611.02856","doi":"https://doi.org/10.48550/arxiv.2611.02856","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.02856","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.02856","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02856","pdf_url":"https://arxiv.org/pdf/2611.02856","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5683000087738037,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225186608.pdf","grobid_xml":"https://content.openalex.org/works/W7225186608.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7169113550","https://openalex.org/W4404102102","https://openalex.org/W7225035482","https://openalex.org/W7154612135","https://openalex.org/W4403702901","https://openalex.org/W4412743805","https://openalex.org/W7154845627","https://openalex.org/W7150153381","https://openalex.org/W7132910470","https://openalex.org/W4404389467"],"abstract_inverted_index":{"Kolmogorov-Arnold":[0],"Networks":[1],"(KANs)":[2],"have":[3],"recently":[4],"been":[5],"proposed":[6],"as":[7],"a":[8,45,65,69,92,133,183,206,218],"promising":[9],"alternative":[10,220],"to":[11,189,198],"Multi-Layer":[12],"Perceptrons":[13],"(MLPs).":[14],"However,":[15],"empirical":[16],"evaluations":[17],"on":[18,36,146,209,223],"structured":[19],"medical":[20,77],"datasets":[21,79,147],"remain":[22],"scarce,":[23],"and":[24,63,68,86,104,119,157,163,196],"commonly":[25],"reported":[26],"metrics":[27],"like":[28],"AUROC":[29],"can":[30,159],"yield":[31],"overly":[32],"optimistic":[33],"performance":[34],"estimates":[35],"imbalanced":[37],"clinical":[38,230],"cohorts.":[39],"In":[40],"this":[41],"study,":[42],"we":[43],"present":[44],"standardized":[46],"benchmark":[47],"comparing":[48],"eleven":[49],"architectures":[50,154],"-":[51,73],"nine":[52],"KAN":[53,153,174,215],"variants":[54,175,216],"(FastKAN,":[55],"WavKAN,":[56],"ReLUKAN,":[57],"ChebyKAN,":[58],"TaylorKAN,":[59],"GramKAN,":[60],"JacobiKAN,":[61],"LegendreKAN,":[62],"TabKAN),":[64],"tuned":[66],"StandardMLP,":[67],"Random":[70],"Forest":[71],"baseline":[72,208],"across":[74,171],"seven":[75],"heterogeneous":[76],"tabular":[78],"spanning":[80],"oncology,":[81],"cardiology,":[82],"nephrology,":[83],"neurology,":[84],"endocrinology,":[85],"obstetrics.":[87],"Our":[88],"experimental":[89],"protocol":[90],"employs":[91],"3x5":[93],"Repeated":[94],"Stratified":[95],"K-Fold":[96],"cross-validation":[97],"scheme":[98],"with":[99,132,148],"nested":[100],"Bayesian":[101,129],"hyperparameter":[102],"optimization":[103],"evaluates":[105],"discrimination":[106,180],"via":[107],"Area":[108],"Under":[109],"the":[110,116,128,210,228,236],"Precision-Recall":[111],"Curve":[112],"(AUPRC),":[113],"calibration":[114],"through":[115],"Brier":[117],"Score,":[118],"computational":[120],"efficiency.":[121],"Formal":[122],"equivalence":[123],"testing":[124],"is":[125,227,238],"conducted":[126],"using":[127],"Correlated":[130],"t-Test":[131],"Region":[134],"of":[135],"Practical":[136],"Equivalence":[137],"(ROPE)":[138],"at":[139,240],"+/-":[140],"0.01.":[141],"The":[142,232],"results":[143,237],"indicate":[144],"that":[145],"severe":[149],"class":[150],"imbalance,":[151],"dedicated":[152],"(particularly":[155],"TabKAN":[156],"ReLUKAN)":[158],"improve":[160],"minority-class":[161],"detection":[162],"achieve":[164],"higher":[165],"AUPRC":[166],"than":[167,182],"standard":[168],"MLPs.":[169],"Nevertheless,":[170],"pooled":[172],"datasets,":[173],"demonstrate":[176],"comparable":[177],"overall":[178],"predictive":[179],"rather":[181],"systematic":[184],"advantage,":[185],"while":[186,214],"requiring":[187],"1.20x":[188],"1.48x":[190],"longer":[191],"inference":[192],"latency":[193],"per":[194],"sample":[195],"up":[197],"12.5x":[199],"more":[200],"trainable":[201],"parameters.":[202],"Consequently,":[203],"StandardMLP":[204],"remains":[205],"strong":[207],"efficiency":[211],"Pareto":[212],"frontier,":[213],"provide":[217],"viable":[219],"when":[221],"precision":[222],"rare":[224],"positive":[225],"cases":[226],"primary":[229],"objective.":[231],"code":[233],"for":[234],"reproducing":[235],"available":[239],"https://github.com/rafalwodzinski/kan_mlp_comparison.":[241]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-04T00:00:00"}