{"id":"https://openalex.org/W7129474564","doi":"https://doi.org/10.48550/arxiv.2602.14682","title":"Exposing Diversity Bias in Deep Generative Models: Statistical Origins and Correction of Diversity Error","display_name":"Exposing Diversity Bias in Deep Generative Models: Statistical Origins and Correction of Diversity Error","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129474564","doi":"https://doi.org/10.48550/arxiv.2602.14682"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.14682","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","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":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126270606","display_name":"Farzan Farnia","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Farnia, Farzan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126269871","display_name":"Mohammad Jalali","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jalali, Mohammad","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114188122","display_name":"Azim Ospanov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ospanov, Azim","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5126270606"],"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8741999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8741999864578247,"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"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.019099999219179153,"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"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.013399999588727951,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7303000092506409},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.6567999720573425},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5393000245094299},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5325999855995178},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.48579999804496765},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4771000146865845},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.44929999113082886},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.40470001101493835}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7303000092506409},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.6567999720573425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5813000202178955},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5393000245094299},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5325999855995178},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5278000235557556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5012999773025513},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4771000146865845},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.44929999113082886},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.424699991941452},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.3939000070095062},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3353999853134155},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C96608239","wikidata":"https://www.wikidata.org/wiki/Q1199823","display_name":"Statistical power","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2808000147342682},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.14682","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.14682","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.14682","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.14682","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"generative":[1,33,113],"models":[2,34,61],"have":[3],"achieved":[4],"great":[5],"success":[6],"in":[7,111],"producing":[8],"high-quality":[9],"samples,":[10,104],"making":[11],"them":[12],"a":[13,106,159,173],"central":[14],"tool":[15],"across":[16],"machine":[17],"learning":[18],"applications.":[19],"Beyond":[20],"sample":[21,139],"quality,":[22],"an":[23],"important":[24],"yet":[25],"less":[26],"systematically":[27],"studied":[28],"question":[29,50],"is":[30],"whether":[31],"trained":[32],"faithfully":[35],"capture":[36],"the":[37,40,54,69,102,117,124,152,155,162,207],"diversity":[38,55,78,99,109,129,143,153],"of":[39,56,64,119,127,154,175],"underlying":[41],"data":[42,71,91,169],"distribution.":[43,157],"In":[44],"this":[45,49,120,196],"work,":[46],"we":[47,87,122,178],"address":[48],"by":[51,59],"directly":[52],"comparing":[53],"samples":[57,66],"generated":[58,103],"state-of-the-art":[60],"with":[62,138],"that":[63,89,133,142],"test":[65,90],"drawn":[67],"from":[68,145],"target":[70],"distribution,":[72],"using":[73],"recently":[74],"proposed":[75],"reference-free":[76],"entropy-based":[77,128],"scores,":[79],"Vendi":[80,96,188],"and":[81,97,131,183,189,198],"RKE.":[82],"Across":[83],"multiple":[84],"benchmark":[85],"datasets,":[86],"find":[88],"consistently":[92],"attains":[93],"substantially":[94],"higher":[95],"RKE":[98,190],"scores":[100,130],"than":[101],"suggesting":[105,202],"systematic":[107],"downward":[108],"bias":[110],"modern":[112],"models.":[114],"To":[115],"understand":[116],"origin":[118],"bias,":[121,197],"analyze":[123],"finite-sample":[125],"behavior":[126],"show":[132],"their":[134,203],"expected":[135],"values":[136],"increase":[137],"size,":[140],"implying":[141],"estimated":[144],"finite":[146],"training":[147],"sets":[148],"could":[149],"inherently":[150],"underestimate":[151],"true":[156],"As":[158],"result,":[160],"optimizing":[161],"generators":[163],"to":[164,167,205],"minimize":[165],"divergence":[166],"empirical":[168,200],"distributions":[170],"would":[171],"induce":[172],"loss":[174],"diversity.":[176],"Finally,":[177],"discuss":[179],"potential":[180,204],"diversity-aware":[181],"regularization":[182],"guidance":[184],"strategies":[185],"based":[186],"on":[187],"as":[191],"principled":[192],"directions":[193],"for":[194],"mitigating":[195],"provide":[199],"evidence":[201],"improve":[206],"results.":[208]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-18T00:00:00"}