{"id":"https://openalex.org/W7221537540","doi":"https://doi.org/10.48550/arxiv.2610.12946","title":"From Imbalance to Evidence: Deep Nonparametric Testing for Complex Data under Severe Sample Imbalance","display_name":"From Imbalance to Evidence: Deep Nonparametric Testing for Complex Data under Severe Sample Imbalance","publication_year":2026,"publication_date":"2026-10-09","ids":{"openalex":"https://openalex.org/W7221537540","doi":"https://doi.org/10.48550/arxiv.2610.12946"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.12946","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.12946","pdf_url":"https://arxiv.org/pdf/2610.12946","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/2610.12946","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111217721","display_name":"Guanhao Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Guanhao","raw_affiliation_strings":["Department of Applied and Computational Mathematics and Statistics University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied and Computational Mathematics and Statistics University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5158477037","display_name":"Xiufan Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu, Xiufan","raw_affiliation_strings":["Department of Applied and Computational Mathematics and Statistics University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied and Computational Mathematics and Statistics University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I107639228"],"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.888700008392334,"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":0.888700008392334,"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/T10136","display_name":"Statistical Methods and Inference","score":0.026599999517202377,"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/T13500","display_name":"Probability and Statistical Research","score":0.013100000098347664,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sample-imbalance","display_name":"sample imbalance","score":0.8119999766349792},{"id":"https://openalex.org/keywords/nonparametric-tests","display_name":"nonparametric tests","score":0.8450000286102295},{"id":"https://openalex.org/keywords/non-euclidean-data","display_name":"non-Euclidean data","score":0.8399999737739563},{"id":"https://openalex.org/keywords/graphs","display_name":"graphs","score":0.7680000066757202},{"id":"https://openalex.org/keywords/blockchain-forensics","display_name":"blockchain forensics","score":0.7960000038146973},{"id":"https://openalex.org/keywords/distribution-comparison","display_name":"distribution comparison","score":0.34599998593330383}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6424000263214111},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.6284000277519226},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.597100019454956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5394999980926514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5166000127792358},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.5012000203132629},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3887999951839447},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C96608239","wikidata":"https://www.wikidata.org/wiki/Q1199823","display_name":"Statistical power","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.29019999504089355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.2669000029563904}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.12946","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.12946","pdf_url":"https://arxiv.org/pdf/2610.12946","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.2610.12946","doi":"https://doi.org/10.48550/arxiv.2610.12946","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.12946","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.12946","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.12946","pdf_url":"https://arxiv.org/pdf/2610.12946","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7307999730110168}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221537540.pdf","grobid_xml":"https://content.openalex.org/works/W7221537540.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4285409009","https://openalex.org/W2147594372","https://openalex.org/W7164083049","https://openalex.org/W4414878008","https://openalex.org/W3168912818","https://openalex.org/W7211873576","https://openalex.org/W3000324184","https://openalex.org/W4411924658","https://openalex.org/W2585770658","https://openalex.org/W7064863690"],"abstract_inverted_index":{"Comparing":[0],"distributions":[1],"under":[2],"severe":[3,74],"sample":[4,75,90,128],"imbalance":[5,76,91,129,170],"requires":[6],"effectively":[7],"using":[8,179],"abundant":[9],"majority":[10],"observations":[11],"while":[12],"retaining":[13],"sensitivity":[14],"to":[15,138,172,184],"differences":[16],"involving":[17],"the":[18,169,176,191],"smaller":[19],"sample.":[20],"This":[21],"challenge":[22],"is":[23],"particularly":[24],"relevant":[25],"for":[26,37,54,96,127,165,208],"complex,":[27],"non-Euclidean":[28],"data,":[29],"such":[30,46],"as":[31,93],"graphs,":[32],"whose":[33],"structural":[34],"characteristics":[35],"call":[36],"flexible":[38],"testing":[39,80,107],"procedures.":[40],"Classifier":[41,119],"two-sample":[42],"tests":[43],"(C2STs)":[44],"provide":[45],"flexibility,":[47],"but":[48],"existing":[49],"procedures":[50],"are":[51],"primarily":[52],"designed":[53,126],"balanced":[55],"or":[56],"comparably":[57],"sized":[58],"samples.":[59],"In":[60],"this":[61,111],"paper,":[62],"we":[63,99,113,146,155],"study":[64],"C2STs":[65],"in":[66],"a":[67,94,103,123,149],"highly":[68],"imbalanced":[69,85],"regime,":[70],"and":[71,162,181],"show":[72],"that":[73,88,130,190],"may":[77],"substantially":[78],"degrade":[79],"performance.":[81],"Different":[82],"from":[83],"conventional":[84],"learning":[86],"approaches":[87],"treat":[89],"merely":[92],"nuisance":[95],"classifier":[97],"training,":[98],"turn":[100],"it":[101],"into":[102,200],"source":[104],"of":[105],"repeated":[106],"evidence.":[108],"Building":[109],"on":[110,159],"insight,":[112],"propose":[114],"an":[115,182,206],"Enhanced":[116],"Imbalance-Aware":[117],"Deep":[118],"Two-Sample":[120],"Test":[121],"(EIAD-C2ST),":[122],"classifier-agnostic":[124],"framework":[125],"accommodates":[131],"diverse":[132],"data":[133,139],"modalities":[134],"by":[135],"tailoring":[136],"classifiers":[137],"structure.":[140],"For":[141],"computationally":[142],"expensive":[143],"deep":[144],"classifiers,":[145],"further":[147],"develop":[148],"scalable":[150],"representation-amortized":[151],"implementation":[152],"strategy.":[153],"Theoretically,":[154],"establish":[156],"rigorous":[157],"guarantees":[158],"asymptotic":[160],"size":[161],"characterize":[163],"conditions":[164],"power":[166],"consistency,":[167],"allowing":[168],"ratio":[171],"diverge.":[173],"We":[174],"demonstrate":[175],"empirical":[177],"gains":[178],"simulations":[180],"application":[183],"blockchain":[185],"forensics.":[186],"The":[187],"results":[188],"reveal":[189],"majority-sample":[192],"surplus,":[193],"when":[194],"properly":[195],"leveraged,":[196],"can":[197],"be":[198],"organized":[199],"useful":[201],"statistical":[202],"evidence,":[203],"rather":[204],"than":[205],"obstacle,":[207],"distributional":[209],"comparisons":[210],"with":[211],"complex":[212],"data.":[213]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-13T00:00:00"}