{"id":"https://openalex.org/W4407212482","doi":"https://doi.org/10.52202/085713-4983","title":"Uncertainty Quantification with the Empirical Neural Tangent Kernel","display_name":"Uncertainty Quantification with the Empirical Neural Tangent Kernel","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407212482","doi":"https://doi.org/10.52202/085713-4983"},"language":"en","primary_location":{"id":"doi:10.52202/085713-4983","doi":"https://doi.org/10.52202/085713-4983","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-4983","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.02870","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Joseph Wilson","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Joseph Wilson","raw_affiliation_strings":["University of Queensland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Queensland","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056317705","display_name":"Chris van der Heide","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chris van der Heide","raw_affiliation_strings":["University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030249020","display_name":"Liam Hodgkinson","orcid":"https://orcid.org/0000-0002-4595-0347","observed_orcids":["https://orcid.org/0000-0002-4595-0347"]},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Liam Hodgkinson","raw_affiliation_strings":["University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056884940","display_name":"Fred Roosta","orcid":"https://orcid.org/0000-0002-6920-7072","observed_orcids":["https://orcid.org/0000-0002-6920-7072"]},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Fred Roosta","raw_affiliation_strings":["University of Queensland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Queensland","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.944,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.92528257,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"165431","last_page":"165469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9634000062942505,"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":0.9634000062942505,"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":0.03150000050663948,"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/T10320","display_name":"Neural Networks and Applications","score":0.000699999975040555,"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/uncertainty-quantification","display_name":"uncertainty quantification","score":0.9490000009536743},{"id":"https://openalex.org/keywords/bayesian-neural-networks","display_name":"Bayesian neural networks","score":0.7820000052452087},{"id":"https://openalex.org/keywords/ensemble-deep-learning","display_name":"ensemble deep learning","score":0.8679999709129333},{"id":"https://openalex.org/keywords/overparameterized-neural-networks","display_name":"overparameterized neural networks","score":0.7860000133514404},{"id":"https://openalex.org/keywords/gaussian-process-approximation","display_name":"Gaussian process approximation","score":0.7289999723434448}],"concepts":[{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6304229497909546},{"id":"https://openalex.org/C138187205","wikidata":"https://www.wikidata.org/wiki/Q131251","display_name":"Tangent","level":2,"score":0.4668605625629425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44247886538505554},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.4107302129268646},{"id":"https://openalex.org/C27406209","wikidata":"https://www.wikidata.org/wiki/Q6394203","display_name":"Kernel smoother","level":5,"score":0.4106752872467041},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3765799403190613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3563550114631653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3196064829826355},{"id":"https://openalex.org/C75866337","wikidata":"https://www.wikidata.org/wiki/Q7280263","display_name":"Radial basis function kernel","level":4,"score":0.15587890148162842},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.125040203332901},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.08382377028465271},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.07700195908546448}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/085713-4983","doi":"https://doi.org/10.52202/085713-4983","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-4983","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.02870","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.02870","pdf_url":"https://arxiv.org/pdf/2502.02870","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.2502.02870","doi":"https://doi.org/10.48550/arxiv.2502.02870","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.02870","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:2502.02870","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.02870","pdf_url":"https://arxiv.org/pdf/2502.02870","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/G5388664669","display_name":"Universal Model Selection Criteria for Scientific Machine Learning","funder_award_id":"DE240100144","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G8820337412","display_name":"ARC Training Centre for Information Resilience","funder_award_id":"IC200100022","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407212482.pdf","grobid_xml":"https://content.openalex.org/works/W4407212482.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1502922572","https://openalex.org/W2899874324","https://openalex.org/W2955023002","https://openalex.org/W2963341956","https://openalex.org/W2994797252","https://openalex.org/W3093141676","https://openalex.org/W3102100346","https://openalex.org/W3165050749","https://openalex.org/W3212621823","https://openalex.org/W4288090422","https://openalex.org/W4289600961","https://openalex.org/W4305007249","https://openalex.org/W4318350847","https://openalex.org/W4322618167","https://openalex.org/W4379261252","https://openalex.org/W4379528090","https://openalex.org/W4384643890","https://openalex.org/W4386065840","https://openalex.org/W4393119324","https://openalex.org/W4394663942","https://openalex.org/W4404261333","https://openalex.org/W4415798582"],"related_works":["https://openalex.org/W7133186277","https://openalex.org/W7212261182","https://openalex.org/W7220799106","https://openalex.org/W7161625343","https://openalex.org/W6929614467","https://openalex.org/W4403590075","https://openalex.org/W4399991993","https://openalex.org/W7133206312","https://openalex.org/W4367628325","https://openalex.org/W4312741324"],"abstract_inverted_index":{"While":[0],"neural":[1],"networks":[2,54],"have":[3],"demonstrated":[4],"impressive":[5],"performance":[6,125],"across":[7,126],"various":[8],"tasks,":[9],"accurately":[10],"quantifying":[11],"uncertainty":[12,31],"in":[13,26,114],"their":[14,20],"predictions":[15],"is":[16],"essential":[17],"to":[18],"ensure":[19],"trustworthiness":[21],"and":[22,64,135],"enable":[23],"widespread":[24],"adoption":[25],"critical":[27],"systems.":[28],"Several":[29],"Bayesian":[30],"quantification":[32],"(UQ)":[33],"methods":[34],"exist":[35],"that":[36,81,106],"are":[37],"either":[38],"cheap":[39],"or":[40],"reliable,":[41],"but":[42],"not":[43,109],"both.":[44],"We":[45,79],"propose":[46],"a":[47,70,89,99,127],"post-hoc,":[48],"sampling-based":[49],"UQ":[50,130],"method":[51,83,108],"for":[52,132],"over-parameterized":[53],"at":[55],"the":[56,86,93],"end":[57],"of":[58,88,101,129],"training.":[59],"Our":[60],"approach":[61],"constructs":[62],"efficient":[63],"meaningful":[65],"deep":[66],"ensembles":[67],"by":[68,119],"employing":[69],"(stochastic)":[71],"gradient-descent":[72],"sampling":[73],"process":[74,91],"on":[75],"appropriately":[76],"linearized":[77],"networks.":[78],"demonstrate":[80],"our":[82,107],"effectively":[84],"approximates":[85],"posterior":[87],"Gaussian":[90],"using":[92],"empirical":[94],"Neural":[95],"Tangent":[96],"Kernel.":[97],"Through":[98],"series":[100],"numerical":[102],"experiments,":[103],"we":[104],"show":[105],"only":[110],"outperforms":[111],"competing":[112],"approaches":[113],"computational":[115],"efficiency-often":[116],"reducing":[117],"costs":[118],"multiple":[120],"factors-but":[121],"also":[122],"maintains":[123],"state-of-the-art":[124],"variety":[128],"metrics":[131],"both":[133],"regression":[134],"classification":[136],"tasks.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-02-07T00:00:00"}