{"id":"https://openalex.org/W7133353150","doi":"https://doi.org/10.48550/arxiv.2603.01750","title":"Practical Deep Heteroskedastic Regression","display_name":"Practical Deep Heteroskedastic Regression","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133353150","doi":"https://doi.org/10.48550/arxiv.2603.01750"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.01750","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01750","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.01750","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017588759","display_name":"Mikkel Jordahn","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jordahn, Mikkel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015192307","display_name":"Jonas Vestergaard Jensen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jensen, Jonas Vestergaard","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127902046","display_name":"James Harrison","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harrison, James","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037852501","display_name":"Michael Riis Andersen","orcid":"https://orcid.org/0000-0002-6081-1011"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andersen, Michael Riis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073902328","display_name":"Mikkel N. Schmidt","orcid":"https://orcid.org/0000-0001-6927-8869"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schmidt, Mikkel N.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017588759"],"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.4287000000476837,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.4287000000476837,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.19509999454021454,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.05420000106096268,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/heteroscedasticity","display_name":"Heteroscedasticity","score":0.815500020980835},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6775000095367432},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.6298999786376953},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47699999809265137},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.47369998693466187},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.45100000500679016},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.4334999918937683},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4041000008583069}],"concepts":[{"id":"https://openalex.org/C101104100","wikidata":"https://www.wikidata.org/wiki/Q1063540","display_name":"Heteroscedasticity","level":2,"score":0.815500020980835},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6775000095367432},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.6298999786376953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.576200008392334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5325000286102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5199999809265137},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4041000008583069},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3804999887943268},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3749000132083893},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C70259352","wikidata":"https://www.wikidata.org/wiki/Q1847839","display_name":"Robust regression","level":3,"score":0.3012000024318695},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2903999984264374},{"id":"https://openalex.org/C149769383","wikidata":"https://www.wikidata.org/wiki/Q7520804","display_name":"Simple linear regression","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C103402496","wikidata":"https://www.wikidata.org/wiki/Q1106171","display_name":"Prediction interval","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26829999685287476},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.01750","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01750","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":"doi:10.48550/arxiv.2603.01750","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01750","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7784532308578491}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Uncertainty":[0],"quantification":[1,70,131],"(UQ)":[2],"in":[3,65],"deep":[4,58],"learning":[5],"regression":[6,60],"is":[7,39],"of":[8,29,52,113],"wide":[9],"interest,":[10],"as":[11,75],"it":[12],"supports":[13],"critical":[14],"applications":[15],"including":[16],"sequential":[17],"decision":[18],"making":[19],"and":[20,49,71,80,91,95,142],"risk-sensitive":[21],"tasks.":[22],"In":[23,83],"heteroskedastic":[24,59],"regression,":[25],"where":[26],"the":[27,30,34,47,50,53,66,110],"uncertainty":[28,69,130],"target":[31],"depends":[32],"on":[33,117,132],"input,":[35],"a":[36,42,93,106,114,118],"common":[37],"approach":[38],"to":[40,145],"train":[41],"neural":[43],"network":[44,116],"that":[45,98,123],"parameterizes":[46],"mean":[48,72,139],"variance":[51,81,107],"predictive":[54],"distribution.":[55],"Still,":[56],"training":[57],"models":[61],"poses":[62],"practical":[63],"challenges":[64,101],"trade-off":[67],"between":[68],"prediction,":[73],"such":[74],"optimization":[76],"difficulties,":[77],"representation":[78],"collapse,":[79],"overfitting.":[82],"this":[84],"work":[85],"we":[86],"identify":[87],"previously":[88],"undiscussed":[89],"fallacies":[90],"propose":[92],"simple":[94],"efficient":[96],"procedure":[97],"addresses":[99],"these":[100],"jointly":[102],"by":[103],"post-hoc":[104],"fitting":[105],"model":[108],"across":[109],"intermediate":[111],"layers":[112],"pretrained":[115],"hold-out":[119],"dataset.":[120],"We":[121],"demonstrate":[122],"our":[124],"method":[125],"achieves":[126],"on-par":[127],"or":[128],"state-of-the-art":[129],"several":[133],"molecular":[134],"graph":[135],"datasets,":[136],"without":[137],"compromising":[138],"prediction":[140,148],"accuracy":[141],"remaining":[143],"cheap":[144],"use":[146],"at":[147],"time.":[149]},"counts_by_year":[],"updated_date":"2026-03-04T07:09:34.246503","created_date":"2026-03-04T00:00:00"}