{"id":"https://openalex.org/W7220997372","doi":"https://doi.org/10.48550/arxiv.2610.07114","title":"Sample-Optimal Estimation of the Fr\u00e9chet Inception Distance","display_name":"Sample-Optimal Estimation of the Fr\u00e9chet Inception Distance","publication_year":2026,"publication_date":"2026-10-05","ids":{"openalex":"https://openalex.org/W7220997372","doi":"https://doi.org/10.48550/arxiv.2610.07114"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.07114","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07114","pdf_url":"https://arxiv.org/pdf/2610.07114","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.07114","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157894233","display_name":"Ziyun Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Ziyun","raw_affiliation_strings":["University of Washington ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington ,","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101439736","display_name":"Jerry Zheng Li","orcid":"https://orcid.org/0009-0003-5035-3728","observed_orcids":["https://orcid.org/0009-0003-5035-3728"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Jerry","raw_affiliation_strings":["University of Washington ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington ,","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101553599","display_name":"Kevin Tian","orcid":"https://orcid.org/0000-0003-0109-9201","observed_orcids":["https://orcid.org/0000-0003-0109-9201","https://orcid.org/0000-0002-9876-3991"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian, Kevin","raw_affiliation_strings":["University of Texas at Austin ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin ,","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127785416","display_name":"Yusong Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhu, Yusong","raw_affiliation_strings":["University of Texas at Austin ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin ,","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7666000127792358,"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":0.7666000127792358,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.06870000064373016,"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/T13141","display_name":"Statistical Methods and Applications","score":0.019899999722838402,"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/frechet-inception-distance","display_name":"Fr\u00e9chet Inception Distance","score":0.9829999804496765},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.8610000014305115},{"id":"https://openalex.org/keywords/finite-sample-bias","display_name":"finite-sample bias","score":0.7960000038146973},{"id":"https://openalex.org/keywords/variance-bounds","display_name":"variance bounds","score":0.7070000171661377},{"id":"https://openalex.org/keywords/debiased-estimation","display_name":"debiased estimation","score":0.5809999704360962},{"id":"https://openalex.org/keywords/u-statistics","display_name":"U-statistics","score":0.9120000004768372},{"id":"https://openalex.org/keywords/generative-model-evaluation","display_name":"generative model evaluation","score":0.8610000014305115},{"id":"https://openalex.org/keywords/multivariate-normal-distribution","display_name":"multivariate normal distribution","score":0.6309999823570251}],"concepts":[{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.8414999842643738},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7800999879837036},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.7487000226974487},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6610000133514404},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5300999879837036},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4828000068664551},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44839999079704285},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.44670000672340393},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3296999931335449},{"id":"https://openalex.org/C181243257","wikidata":"https://www.wikidata.org/wiki/Q1693522","display_name":"Sample mean and sample covariance","level":3,"score":0.31869998574256897},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C44082924","wikidata":"https://www.wikidata.org/wiki/Q1767128","display_name":"Order statistic","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C158946198","wikidata":"https://www.wikidata.org/wiki/Q131187","display_name":"Taylor series","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C2993021520","wikidata":"https://www.wikidata.org/wiki/Q175199","display_name":"Sample variance","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2648000121116638},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C18747219","wikidata":"https://www.wikidata.org/wiki/Q620994","display_name":"Standard error","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2526000142097473},{"id":"https://openalex.org/C156458928","wikidata":"https://www.wikidata.org/wiki/Q661953","display_name":"Decantation","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.07114","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07114","pdf_url":"https://arxiv.org/pdf/2610.07114","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.2610.07114","doi":"https://doi.org/10.48550/arxiv.2610.07114","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.07114","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.07114","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07114","pdf_url":"https://arxiv.org/pdf/2610.07114","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":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220997372.pdf","grobid_xml":"https://content.openalex.org/works/W7220997372.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3154909524","https://openalex.org/W2985516053","https://openalex.org/W3089783180","https://openalex.org/W7160879804","https://openalex.org/W7162778045","https://openalex.org/W7028456113","https://openalex.org/W4415798177","https://openalex.org/W4415330138","https://openalex.org/W7159602839","https://openalex.org/W7220707910"],"abstract_inverted_index":{"The":[0],"Fr\u00e9chet":[1],"Inception":[2,195],"Distance":[3],"(FID)":[4],"is":[5,47,163],"widely":[6],"used":[7],"to":[8,32,94,221,225],"evaluate":[9],"generative":[10],"models,":[11],"but":[12],"its":[13],"empirical":[14,70,83,169],"plug-in":[15,71,84],"estimator":[16,91,215],"suffers":[17],"from":[18],"finite-sample":[19,57],"bias":[20,59,105,184],"[BSAG18,":[21],"CF20].":[22],"We":[23,54,101,129,148,165],"study":[24],"the":[25,69,82,88,181,187,199,205],"sample":[26,77,157,208],"complexity":[27],"$n$":[28],"of":[29,92,97,109,171,189],"estimating":[30],"FID":[31,139],"error":[33,203],"$\u03b5$":[34],"between":[35],"$d$-dimensional":[36],"Gaussians":[37,179],"with":[38,194],"bounded":[39],"mean":[40,201],"distance":[41],"and":[42,60,106,115,159,185],"covariances,":[43],"when":[44],"one":[45],"distribution":[46],"known.":[48],"Our":[49,175],"contributions":[50],"are":[51],"threefold.":[52],"(1)":[53],"establish":[55],"tight":[56,104],"$\u0398(\\frac{d^2}{n})$":[58],"$\u0398(\\frac{d}{n}":[61],"+":[62,111,113,119],"\\frac":[63],"{d^2}":[64],"{n^2})$":[65],"variance":[66,107],"bounds":[67,108],"for":[68,121],"estimator,":[72,85],"establishing":[73],"a":[74,135,167],"$\\gtrsim":[75],"d^2$":[76],"complexity.":[78],"(2)":[79],"To":[80],"debias":[81],"we":[86],"generalize":[87],"${\\rm":[89],"FID}_\\infty$":[90],"[CF20]":[93],"extrapolation":[95,124,214],"methods":[96],"arbitrary":[98],"order":[99],"$k$.":[100],"further":[102],"prove":[103,160],"$\u0398(\\frac{d^{k":[110],"2}}{n^{k":[112],"1}})$":[114],"$\u0398(\\frac":[116],"d":[117,155],"n":[118],"\\frac{d^2}{n^2})$":[120],"any":[122],"order-$k$":[123],"under":[125],"our":[126,172,190,211],"framework.":[127],"(3)":[128],"introduce":[130],"Relative":[131],"Taylor":[132],"Debiasing":[133],"(RTD),":[134],"new,":[136],"computationally":[137],"efficient":[138],"estimation":[140,202],"algorithm":[141],"using":[142],"debiasing":[143],"techniques":[144],"inspired":[145],"by":[146],"U-statistics.":[147],"show":[149],"that":[150,161],"RTD":[151,197],"achieves":[152,198],"an":[153],"$O(\\frac":[154],"{\u03b5^2})$":[156],"complexity,":[158],"this":[162],"optimal.":[164],"provide":[166],"complementary":[168],"evaluation":[170],"new":[173],"estimators.":[174],"experiments":[176],"on":[177],"synthetic":[178],"validate":[180],"predicted":[182],"residual":[183],"support":[186],"tightness":[188],"bounds.":[191],"On":[192],"ImageNet":[193],"embeddings,":[196],"lowest":[200],"at":[204,227],"standard":[206],"50K":[207,228],"budget,":[209],"while":[210],"second-order":[212],"variance-aware":[213],"(VALE$_2$)":[216],"uses":[217],"only":[218],"10K":[219],"samples":[220],"achieve":[222],"accuracy":[223],"comparable":[224],"FID$_\\infty$":[226],"samples.":[229]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-09T00:00:00"}