{"id":"https://openalex.org/W7223827353","doi":"https://doi.org/10.48550/arxiv.2610.33610","title":"On the Error Analysis of Triangular Transport Maps for Conditional Generation via MMD-based Objectives","display_name":"On the Error Analysis of Triangular Transport Maps for Conditional Generation via MMD-based Objectives","publication_year":2026,"publication_date":"2026-10-24","ids":{"openalex":"https://openalex.org/W7223827353","doi":"https://doi.org/10.48550/arxiv.2610.33610"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.33610","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.33610","pdf_url":"https://arxiv.org/pdf/2610.33610","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/2610.33610","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133041937","display_name":"Michele Martino","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":"Martino, Michele","raw_affiliation_strings":["Department of Applied Mathematics , University of Washington , Seattle , WA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics , University of Washington , Seattle , WA , USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012461935","display_name":"Bamdad Hosseini","orcid":"https://orcid.org/0000-0001-5053-6223","observed_orcids":["https://orcid.org/0000-0001-5053-6223"]},"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":"Hosseini, Bamdad","raw_affiliation_strings":["Department of Applied Mathematics , University of Washington , Seattle , WA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics , University of Washington , Seattle , WA , USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031661439","display_name":"Amir Sagiv","orcid":"https://orcid.org/0000-0002-0831-216X","observed_orcids":["https://orcid.org/0000-0002-0831-216X"]},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sagiv, Amir","raw_affiliation_strings":["Department of Mathematical Sciences , New Jersey Institute of Technology , Newark , NJ , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematical Sciences , New Jersey Institute of Technology , Newark , NJ , USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035589000","display_name":"Amirhossein Taghvaei","orcid":"https://orcid.org/0000-0002-1536-892X","observed_orcids":["https://orcid.org/0000-0002-1536-892X"]},"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":"Taghvaei, Amirhossein","raw_affiliation_strings":["Department of Aeronautics and Astronautics , University of Washington , Seattle , WA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics , University of Washington , Seattle , WA , USA","institution_ids":["https://openalex.org/I201448701"]}]}],"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":0.33889999985694885,"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":0.33889999985694885,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.319599986076355,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.06199999898672104,"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/conditional-generative-models","display_name":"conditional generative models","score":0.9100000262260437},{"id":"https://openalex.org/keywords/conditional-sampling","display_name":"conditional sampling","score":0.6230000257492065},{"id":"https://openalex.org/keywords/minimum-divergence-estimation","display_name":"minimum divergence estimation","score":0.8029999732971191},{"id":"https://openalex.org/keywords/maximum-mean-discrepancy","display_name":"maximum mean discrepancy","score":0.9070000052452087},{"id":"https://openalex.org/keywords/non-asymptotic-error-bounds","display_name":"non-asymptotic error bounds","score":0.8289999961853027},{"id":"https://openalex.org/keywords/model-misspecification","display_name":"model misspecification","score":0.675000011920929},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"curse of dimensionality","score":0.7879999876022339},{"id":"https://openalex.org/keywords/surrogate-loss","display_name":"surrogate loss","score":0.5609999895095825},{"id":"https://openalex.org/keywords/parameter-estimation","display_name":"parameter estimation","score":0.3790000081062317}],"concepts":[{"id":"https://openalex.org/C21430997","wikidata":"https://www.wikidata.org/wiki/Q5159279","display_name":"Conditional variance","level":4,"score":0.7458999752998352},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6805999875068665},{"id":"https://openalex.org/C103982235","wikidata":"https://www.wikidata.org/wiki/Q7309594","display_name":"Regular conditional probability","level":4,"score":0.6646000146865845},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6618000268936157},{"id":"https://openalex.org/C186215838","wikidata":"https://www.wikidata.org/wiki/Q772232","display_name":"Conditional expectation","level":2,"score":0.5764999985694885},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.35030001401901245},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34279999136924744},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C174920663","wikidata":"https://www.wikidata.org/wiki/Q5159256","display_name":"Conditional dependence","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30889999866485596},{"id":"https://openalex.org/C55974624","wikidata":"https://www.wikidata.org/wiki/Q1188504","display_name":"Exponential family","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C124805900","wikidata":"https://www.wikidata.org/wiki/Q5159269","display_name":"Conditional mutual information","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.2718999981880188}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.33610","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.33610","pdf_url":"https://arxiv.org/pdf/2610.33610","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.2610.33610","doi":"https://doi.org/10.48550/arxiv.2610.33610","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.33610","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:2610.33610","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.33610","pdf_url":"https://arxiv.org/pdf/2610.33610","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":[{"id":"https://openalex.org/G2055485564","display_name":"A Dynamical Theory of Floquet Materials","funder_award_id":"2508811","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7620772523","display_name":"CAREER: Gaussian Processes for Scientific Machine Learning: Theoretical Analysis and Computational Algorithms","funder_award_id":"2337678","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223827353.pdf","grobid_xml":"https://content.openalex.org/works/W7223827353.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W603636824","https://openalex.org/W1565176583","https://openalex.org/W1959608418","https://openalex.org/W1988115241","https://openalex.org/W1993288992","https://openalex.org/W1995565517","https://openalex.org/W1998037613","https://openalex.org/W2023103251","https://openalex.org/W2041944459","https://openalex.org/W2056709476","https://openalex.org/W2077161011","https://openalex.org/W2099973661","https://openalex.org/W2115986460","https://openalex.org/W2124331852","https://openalex.org/W2125389028","https://openalex.org/W2146641075","https://openalex.org/W2401440373","https://openalex.org/W2418306335","https://openalex.org/W2767757834","https://openalex.org/W2786449553","https://openalex.org/W2951338616","https://openalex.org/W2963090522","https://openalex.org/W2979712029","https://openalex.org/W2991001610","https://openalex.org/W2992005611","https://openalex.org/W2992035660","https://openalex.org/W3004450693","https://openalex.org/W3004574756","https://openalex.org/W3034727712","https://openalex.org/W3036167779","https://openalex.org/W3096831136","https://openalex.org/W3120877973","https://openalex.org/W3141455185","https://openalex.org/W3155072588","https://openalex.org/W3157752112","https://openalex.org/W3217132494","https://openalex.org/W4206803153","https://openalex.org/W4221165958","https://openalex.org/W4226034460","https://openalex.org/W4245232001","https://openalex.org/W4281651681","https://openalex.org/W4286751013","https://openalex.org/W4303647933","https://openalex.org/W4323322764","https://openalex.org/W4361249119","https://openalex.org/W4378718194","https://openalex.org/W4378771535","https://openalex.org/W4383960153","https://openalex.org/W4387195417","https://openalex.org/W4401455382","https://openalex.org/W4402217122","https://openalex.org/W4402426960","https://openalex.org/W4404391923","https://openalex.org/W4407980702","https://openalex.org/W4411707478","https://openalex.org/W4412474039","https://openalex.org/W4413156798","https://openalex.org/W4415796499","https://openalex.org/W4417092149","https://openalex.org/W7080306732","https://openalex.org/W7213522152","https://openalex.org/W7214907663","https://openalex.org/W7219155329"],"related_works":["https://openalex.org/W4383987973","https://openalex.org/W4401455382","https://openalex.org/W4415338104","https://openalex.org/W4226297177","https://openalex.org/W2921924902","https://openalex.org/W4415796499","https://openalex.org/W7221508438","https://openalex.org/W4403815026","https://openalex.org/W4404391923","https://openalex.org/W7023686039"],"abstract_inverted_index":{"Conditional":[0],"generative":[1,252],"models":[2,253],"parameterized":[3],"by":[4],"triangular":[5,37],"transport":[6],"maps":[7],"are":[8,133],"widely":[9],"used":[10],"for":[11,32,128,196,228,250],"conditional":[12,22,54,67,113,121,149,173,220,251,257],"sampling,":[13],"yet":[14],"theoretical":[15],"guarantees":[16],"on":[17,204],"the":[18,21,49,65,72,79,82,87,94,106,109,112,119,137,148,171,188,192,205,211,219,229,241,256,260],"quality":[19],"of":[20,36,97,118,187,218,238],"measures":[23],"they":[24],"produce":[25],"remain":[26],"scarce.":[27],"We":[28,39,90,140,163],"address":[29],"this":[30],"question":[31],"minimum":[33],"divergence":[34],"estimators":[35],"maps.":[38],"use":[40],"MMD-based":[41],"objectives":[42],"as":[43,71,115],"a":[44,99,152,165,215,236,263],"tractable":[45],"setting":[46],"in":[47,136,191,240],"which":[48],"gap":[50],"between":[51,78],"joint":[52,100,110,131,157,197,212,230,261],"and":[53,60,81,111,160,179,222,270],"errors":[55],"can":[56],"be":[57],"analyzed":[58],"precisely,":[59],"we":[61,125,208,223],"measure":[62],"performance":[63],"through":[64,151],"average":[66,172],"estimation":[68,174],"error,":[69,262],"defined":[70],"squared":[73],"maximum":[74],"mean":[75,122],"discrepancy":[76],"(MMD)":[77],"estimated":[80],"true":[83],"conditionals,":[84],"averaged":[85],"over":[86],"conditioning":[88,206,242],"variable.":[89,243],"first":[91],"show":[92,209],"that":[93,145,169,210,247,265],"common":[95],"practice":[96],"minimizing":[98],"MMD":[101],"may":[102],"fail":[103],"to":[104,267,271],"recover":[105],"conditionals:":[107],"writing":[108],"criteria":[114,249],"quadratic":[116],"energies":[117],"same":[120],"embedding":[123],"residual,":[124],"prove":[126,164],"that,":[127],"parametric":[129,193],"classes,":[130],"minimizers":[132],"generically":[134],"inconsistent":[135],"misspecified":[138],"setting.":[139,194],"then":[141],"analyze":[142],"an":[143,225],"estimator":[144],"directly":[146],"minimizes":[147],"criterion":[150,213],"surrogate":[153],"loss":[154],"computable":[155],"from":[156,200,235],"target":[158,255],"samples":[159],"reference":[161,180],"samples.":[162],"non-asymptotic":[166],"error":[167,175,226],"bound":[168,227],"decomposes":[170],"into":[176],"approximation,":[177],"estimation,":[178],"sampling":[181],"errors,":[182],"with":[183],"fast":[184],"rates":[185],"independent":[186],"ambient":[189],"dimension":[190],"Finally,":[195],"MMDs":[198],"built":[199],"concentrating":[201],"Gaussian":[202],"kernels":[203],"variable,":[207],"approximates":[214],"density-reweighted":[216],"version":[217],"one,":[221],"derive":[224],"minimizer":[231],"whose":[232],"rate":[233],"suffers":[234],"curse":[237],"dimensionality":[239],"Our":[244],"results":[245],"suggest":[246],"training":[248],"should":[254],"rather":[258],"than":[259],"principle":[264],"extends":[266],"other":[268],"divergences":[269],"dynamic":[272],"transport.":[273]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-28T00:00:00"}