{"id":"https://openalex.org/W7118765613","doi":"https://doi.org/10.48550/arxiv.2601.01927","title":"Theoretical Convergence of SMOTE-Generated Samples","display_name":"Theoretical Convergence of SMOTE-Generated Samples","publication_year":2026,"publication_date":"2026-01-05","ids":{"openalex":"https://openalex.org/W7118765613","doi":"https://doi.org/10.48550/arxiv.2601.01927"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.01927","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.01927","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2601.01927","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122265766","display_name":"Firuz Kamalov","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kamalov, Firuz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066909407","display_name":"Hana Sulieman","orcid":"https://orcid.org/0000-0003-4952-8298"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sulieman, Hana","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113355433","display_name":"Witold Pedrycz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedrycz, Witold","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5122265766"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9225999712944031,"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":0.9225999712944031,"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":0.008899999782443047,"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":0.00860000029206276,"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/convergence","display_name":"Convergence (economics)","score":0.8101000189781189},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5604000091552734},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.49230000376701355},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.47290000319480896},{"id":"https://openalex.org/keywords/convergence-of-random-variables","display_name":"Convergence of random variables","score":0.44699999690055847},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.40220001339912415},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.4009000062942505}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.8101000189781189},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5110999941825867},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.49230000376701355},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46399998664855957},{"id":"https://openalex.org/C95763700","wikidata":"https://www.wikidata.org/wiki/Q578985","display_name":"Convergence of random variables","level":3,"score":0.44699999690055847},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38909998536109924},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.365200012922287},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.361299991607666},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29660001397132874},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C538505008","wikidata":"https://www.wikidata.org/wiki/Q3979448","display_name":"Convergence tests","level":4,"score":0.2669999897480011},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26489999890327454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.01927","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.01927","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2601.01927","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.01927","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Imbalanced":[0],"data":[1,125,130],"affects":[2],"a":[3,45,74,120],"wide":[4],"range":[5],"of":[6,19,49,89],"machine":[7],"learning":[8],"applications,":[9],"from":[10],"healthcare":[11],"to":[12,24,31,65,95,101],"network":[13],"security.":[14],"As":[15],"SMOTE":[16],"is":[17,29,81],"one":[18],"the":[20,57,66,90],"most":[21],"popular":[22],"approaches":[23],"addressing":[25],"this":[26,41],"issue,":[27],"it":[28,33],"imperative":[30],"validate":[32],"not":[34],"only":[35],"empirically":[36],"but":[37],"also":[38],"theoretically.":[39],"In":[40],"paper,":[42],"we":[43,54,84],"provide":[44],"rigorous":[46],"theoretical":[47,104],"analysis":[48],"SMOTE's":[50],"convergence":[51,76,97],"properties.":[52],"Concretely,":[53],"prove":[55,73],"that":[56,86,123],"synthetic":[58,115],"random":[59,68],"variable":[60,69],"Z":[61],"converges":[62],"in":[63,77],"probability":[64],"underlying":[67],"X.":[70],"We":[71],"further":[72],"stronger":[75],"mean":[78],"when":[79],"X":[80],"compact.":[82],"Finally,":[83],"show":[85],"lower":[87],"values":[88],"nearest":[91],"neighbor":[92],"rank":[93],"lead":[94],"faster":[96],"offering":[98],"actionable":[99],"guidance":[100],"practitioners.":[102],"The":[103],"results":[105],"are":[106],"supported":[107],"by":[108],"numerical":[109],"experiments":[110],"using":[111],"both":[112],"real-life":[113],"and":[114],"data.":[116],"Our":[117],"work":[118],"provides":[119],"foundational":[121],"understanding":[122],"enhances":[124],"augmentation":[126],"techniques":[127],"beyond":[128],"imbalanced":[129],"scenarios.":[131]},"counts_by_year":[],"updated_date":"2026-01-08T20:10:11.968330","created_date":"2026-01-08T00:00:00"}