{"id":"https://openalex.org/W7155183944","doi":"https://doi.org/10.48550/arxiv.2604.19296","title":"Debiased neural operators for estimating functionals","display_name":"Debiased neural operators for estimating functionals","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155183944","doi":"https://doi.org/10.48550/arxiv.2604.19296"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.19296","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19296","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.19296","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035671397","display_name":"Konstantin He\u00df","orcid":"https://orcid.org/0009-0003-8552-6588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hess, Konstantin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060813780","display_name":"Dennis Frauen","orcid":"https://orcid.org/0000-0001-6526-1162"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frauen, Dennis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000443214","display_name":"Niki Kilbertus","orcid":"https://orcid.org/0000-0001-8718-4305"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kilbertus, Niki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081442873","display_name":"Stefan Feuerriegel","orcid":"https://orcid.org/0000-0001-7856-8729"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feuerriegel, Stefan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.311599999666214,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.311599999666214,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.14190000295639038,"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"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.09640000015497208,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6908000111579895},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6028000116348267},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.559499979019165},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5559999942779541},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.5006999969482422},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4593999981880188},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41609999537467957}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6908000111579895},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6028000116348267},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.559499979019165},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5559999942779541},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4984999895095825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46549999713897705},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.42100000381469727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41929998993873596},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4124999940395355},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.30410000681877136},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C140101238","wikidata":"https://www.wikidata.org/wiki/Q1404885","display_name":"Window function","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C2984127161","wikidata":"https://www.wikidata.org/wiki/Q969316","display_name":"Neural activity","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C43929395","wikidata":"https://www.wikidata.org/wiki/Q1198874","display_name":"Operator theory","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.19296","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19296","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.19296","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19296","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Neural":[0],"operators":[1],"are":[2],"widely":[3],"used":[4],"to":[5,21,28,85,113,175,192],"approximate":[6],"solution":[7,25,31,75],"maps":[8],"of":[9,74,177,202],"complex":[10],"physical":[11],"systems.":[12],"In":[13,58],"many":[14],"applications,":[15],"however,":[16],"the":[17,23,30,136,149,171,178,184,200],"goal":[18],"is":[19,82,174],"not":[20],"recover":[22],"full":[24],"trajectory,":[26],"but":[27],"summarize":[29],"trajectory":[32],"via":[33,195],"a":[34,39,46,51,67,129,140,157],"scalar":[35],"target":[36,47,72,172],"quantity":[37,173],"(e.g.,":[38],"functional":[40],"such":[41,71],"as":[42,139],"time":[43,49],"spent":[44],"in":[45,111],"range,":[48],"above":[50],"threshold,":[52],"accumulated":[53],"cost,":[54],"or":[55],"total":[56],"energy).":[57],"this":[59],"paper,":[60],"we":[61,127,186],"introduce":[62],"DOPE":[63,81,155,203],"(debiased":[64],"neural":[65,79,99,137],"operator):":[66],"semiparametric":[68],"estimator":[69,133],"for":[70,163,168],"quantities":[73],"trajectories":[76],"obtained":[77],"from":[78,120],"operators.":[80],"broadly":[83],"applicable":[84],"settings":[86],"with":[87,97],"both":[88],"partial":[89],"and":[90,93,147,167],"irregular":[91,164],"observations":[92],"can":[94,118],"be":[95],"combined":[96],"arbitrary":[98],"operator":[100,138],"architectures.":[101],"We":[102,108,198],"make":[103],"three":[104],"main":[105],"contributions.":[106],"(1)":[107],"show":[109],"that,":[110],"contrast":[112],"DOPE,":[114],"naive":[115],"plug-in":[116],"estimation":[117],"suffer":[119],"first-order":[121],"bias.":[122],"(2)":[123],"To":[124,182],"address":[125],"this,":[126,154],"derive":[128],"novel":[130],"one-step,":[131],"Neyman-orthogonal":[132],"that":[134,160],"treats":[135],"high-dimensional":[141],"nuisance":[142],"mapping":[143],"between":[144],"function":[145],"spaces,":[146],"removes":[148],"leading":[150],"bias":[151],"term.":[152],"For":[153],"uses":[156],"weighting":[158],"mechanism":[159],"simultaneously":[161],"accounts":[162],"observation":[165],"designs":[166],"how":[169],"sensitive":[170],"perturbations":[176],"underlying":[179],"trajectory.":[180],"(3)":[181],"learn":[183],"weights,":[185],"extend":[187],"automatic":[188],"debiased":[189],"machine":[190],"learning":[191],"operator-valued":[193],"nuisances":[194],"Riesz":[196],"regression.":[197],"demonstrate":[199],"benefits":[201],"across":[204],"various":[205],"numerical":[206],"experiments.":[207]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-23T00:00:00"}