{"id":"https://openalex.org/W7224003291","doi":"https://doi.org/10.48550/arxiv.2610.35652","title":"Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel","display_name":"Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel","publication_year":2026,"publication_date":"2026-10-26","ids":{"openalex":"https://openalex.org/W7224003291","doi":"https://doi.org/10.48550/arxiv.2610.35652"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.35652","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.35652","pdf_url":"https://arxiv.org/pdf/2610.35652","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":"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/2610.35652","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159874183","display_name":"Jayoung Ryu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryu, Jayoung","raw_affiliation_strings":["Department of Computer Science , Courant Institute School of Mathematics ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Courant Institute School of Mathematics ,","institution_ids":["https://openalex.org/I36672615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159865326","display_name":"Kyunghyun Cho","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cho, Kyunghyun","raw_affiliation_strings":["Computing, and Data Science , New York University","Department of Computer Science , Courant Institute School of Mathematics ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing, and Data Science , New York University","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Department of Computer Science , Courant Institute School of Mathematics ,","institution_ids":["https://openalex.org/I36672615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021527800","display_name":"Romain Lopez","orcid":"https://orcid.org/0000-0003-0495-738X","observed_orcids":["https://orcid.org/0000-0003-0495-738X"]},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lopez, Romain","raw_affiliation_strings":["Department of Biology , New York University","Department of Computer Science , Courant Institute School of Mathematics ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology , New York University","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Department of Computer Science , Courant Institute School of Mathematics ,","institution_ids":["https://openalex.org/I36672615"]}]}],"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.850600004196167,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.850600004196167,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.1306000053882599,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.003700000001117587,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.9589999914169312},{"id":"https://openalex.org/keywords/conditional-generative-models","display_name":"conditional generative models","score":0.9800000190734863},{"id":"https://openalex.org/keywords/gaussian-processes","display_name":"Gaussian processes","score":0.6169999837875366},{"id":"https://openalex.org/keywords/conditional-flow-matching","display_name":"conditional flow matching","score":0.6259999871253967}],"concepts":[{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.5094000101089478},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.48559999465942383},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47279998660087585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4620000123977661},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45249998569488525},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4311000108718872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4296000003814697},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42080000042915344},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3765000104904175},{"id":"https://openalex.org/C186215838","wikidata":"https://www.wikidata.org/wiki/Q772232","display_name":"Conditional expectation","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C21430997","wikidata":"https://www.wikidata.org/wiki/Q5159279","display_name":"Conditional variance","level":4,"score":0.3402000069618225},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.336899995803833},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C138187205","wikidata":"https://www.wikidata.org/wiki/Q131251","display_name":"Tangent","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.31029999256134033},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.35652","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.35652","pdf_url":"https://arxiv.org/pdf/2610.35652","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.35652","doi":"https://doi.org/10.48550/arxiv.2610.35652","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.35652","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.35652","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.35652","pdf_url":"https://arxiv.org/pdf/2610.35652","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G341312323","display_name":null,"funder_award_id":"CG016","funder_id":"https://openalex.org/F4320313203","funder_display_name":"New York University Abu Dhabi"}],"funders":[{"id":"https://openalex.org/F4320313203","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320330069","display_name":"Tamkeen","ror":"https://ror.org/00bqpz325"},{"id":"https://openalex.org/F4320332193","display_name":"Genentech","ror":"https://ror.org/04gndp242"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224003291.pdf","grobid_xml":"https://content.openalex.org/works/W7224003291.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4399421337","https://openalex.org/W3174720337","https://openalex.org/W4386081100","https://openalex.org/W4226297177","https://openalex.org/W3118197842","https://openalex.org/W4415796499","https://openalex.org/W2899107858","https://openalex.org/W6980728440","https://openalex.org/W7167614931","https://openalex.org/W2428952132"],"abstract_inverted_index":{"Many":[0],"high-throughput":[1],"scientific":[2],"experiments":[3],"produce":[4],"distributional":[5,93],"outputs,":[6],"requiring":[7],"conditional":[8,73,201,205,209,233],"generative":[9,74,114,202],"models":[10],"to":[11,16,92,121],"interpret":[12],"the":[13,42,67,100,127,131,136,141,163,166,179,185,224,227,232,236],"data,":[14],"and":[15,81,134,156,208,217],"predict":[17],"outcomes":[18],"at":[19,25],"new":[20,26,31,35],"inputs.":[21],"Acquiring":[22],"experimental":[23,46],"data":[24],"conditions":[27],"(e.g.,":[28],"for":[29,44,152,242],"a":[30,34,72,78,82,106,113,149,170,188],"antigen":[32],"or":[33,60],"cell":[36],"type)":[37],"is":[38,90,118],"often":[39],"expensive,":[40],"motivating":[41],"need":[43],"automated":[45],"design":[47],"methods.":[48],"However,":[49],"existing":[50],"active":[51,88,190,240],"learning":[52,89,191,241],"frameworks":[53],"are":[54],"limited":[55],"as":[56,165],"they":[57],"assume":[58],"scalar":[59],"vector-valued":[61],"outputs.":[62],"We":[63,193],"first":[64],"show":[65],"that":[66,109,177],"Wasserstein":[68],"test":[69],"risk":[70],"of":[71,140,169,200,238],"task":[75],"decomposes":[76],"into":[77],"mean":[79],"term":[80],"shape":[83],"term,":[84],"demonstrating":[85,235],"why":[86],"mean-based":[87],"blind":[91],"shape.":[94],"To":[95],"capture":[96],"both,":[97],"we":[98,173],"propose":[99],"transport":[101,155],"Neural":[102],"Tangent":[103],"Kernel":[104],"(tNTK),":[105],"tractable":[107,157],"kernel":[108],"measures":[110],"how":[111],"sensitive":[112],"model's":[115],"predicted":[116],"distribution":[117],"with":[119],"respect":[120],"its":[122],"parameters.":[123],"The":[124],"tNTK":[125,164,225],"recovers":[126],"standard":[128],"NTK":[129,229],"in":[130],"deterministic":[132],"limit":[133],"upper-bounds":[135],"posterior":[137,182],"Fr\u00e9chet":[138],"variance":[139,183],"prediction":[142],"under":[143],"small":[144],"parameter":[145],"perturbations.":[146],"It":[147],"admits":[148],"closed-form":[150],"expression":[151],"affine":[153],"Gaussian":[154,171],"Monte":[158],"Carlo":[159],"estimators":[160],"otherwise.":[161],"Treating":[162],"covariance":[167],"function":[168],"process,":[172],"greedily":[174],"select":[175],"inputs":[176],"minimize":[178],"total":[180],"GP":[181],"across":[184,197],"pool,":[186],"yielding":[187],"distribution-aware":[189,239],"strategy.":[192],"evaluate":[194],"this":[195],"strategy":[196],"four":[198],"classes":[199],"models,":[203],"including":[204],"flow":[206],"matching":[207],"Monge":[210],"gap,":[211],"on":[212],"synthetic":[213],"distributions,":[214],"intent-labeled":[215],"sentences,":[216],"single-cell":[218],"perturbation":[219],"responses.":[220],"In":[221],"these":[222],"experiments,":[223],"outperforms":[226],"baseline":[228],"computed":[230],"from":[231],"mean,":[234],"value":[237],"generative-modeling":[243],"tasks.":[244]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-10-28T00:00:00"}