{"id":"https://openalex.org/W4406059497","doi":"https://doi.org/10.48550/arxiv.2407.13666","title":"Non-Asymptotic Uncertainty Quantification in High-Dimensional Learning","display_name":"Non-Asymptotic Uncertainty Quantification in High-Dimensional Learning","publication_year":2024,"publication_date":"2024-07-18","ids":{"openalex":"https://openalex.org/W4406059497","doi":"https://doi.org/10.48550/arxiv.2407.13666"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2407.13666","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.13666","pdf_url":"https://arxiv.org/pdf/2407.13666","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.13666","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045213444","display_name":"Frederik Hoppe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoppe, Frederik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085996844","display_name":"Claudio Mayrink Verdun","orcid":"https://orcid.org/0000-0003-2079-797X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Verdun, Claudio Mayrink","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092897307","display_name":"Hannah Laus","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laus, Hannah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090264479","display_name":"Felix Krahmer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krahmer, Felix","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005201576","display_name":"Holger Rauhut","orcid":"https://orcid.org/0000-0003-4750-5092"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rauhut, Holger","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":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/T10876","display_name":"Fault Detection and Control Systems","score":0.9010000228881836,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9010000228881836,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.4587152302265167},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.3892388343811035},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3701244592666626},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.296625018119812},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17675721645355225}],"concepts":[{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.4587152302265167},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3892388343811035},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3701244592666626},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.296625018119812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17675721645355225}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2407.13666","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.13666","pdf_url":"https://arxiv.org/pdf/2407.13666","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.13666","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.13666","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.13666","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.13666","pdf_url":"https://arxiv.org/pdf/2407.13666","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406059497.pdf","grobid_xml":"https://content.openalex.org/works/W4406059497.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W1991093342"],"abstract_inverted_index":{"Uncertainty":[0],"quantification":[1],"(UQ)":[2],"is":[3,58,99],"a":[4,21,26,81,120,129],"crucial":[5],"but":[6],"challenging":[7],"task":[8],"in":[9,32,90,107,164],"many":[10],"high-dimensional":[11,148],"regression":[12,33,39,177],"or":[13],"learning":[14],"problems":[15,92],"to":[16,37,48,66,103,154,178],"increase":[17],"the":[18,43,53,59,64,69,77,96,125,136,141,185,194,200],"confidence":[19,73,110,126,156],"of":[20,52,71,132,140,187,203],"given":[22],"predictor.":[23],"We":[24],"develop":[25],"new":[27],"data-driven":[28,121,179],"approach":[29],"for":[30,68,128],"UQ":[31,56],"that":[34,123],"applies":[35],"both":[36],"classical":[38],"approaches":[40],"such":[41,167,204],"as":[42,45,47,168],"LASSO":[44,65],"well":[46],"neural":[49,182],"networks.":[50],"One":[51],"most":[54],"notable":[55],"techniques":[57],"debiased":[60,205],"LASSO,":[61],"which":[62,158],"modifies":[63],"allow":[67],"construction":[70],"asymptotic":[72],"intervals":[74,127],"by":[75,134],"decomposing":[76],"estimation":[78],"error":[79],"into":[80],"Gaussian":[82],"and":[83,118,138,199],"an":[84],"asymptotically":[85],"vanishing":[86],"bias":[87,97,142],"component.":[88],"However,":[89],"real-world":[91],"with":[93],"finite-dimensional":[94],"data,":[95,146],"term":[98],"often":[100],"too":[101],"significant":[102],"be":[104],"neglected,":[105],"resulting":[106],"overly":[108],"narrow":[109],"intervals.":[111],"Our":[112,191],"work":[113],"rigorously":[114],"addresses":[115],"this":[116],"issue":[117],"derives":[119],"adjustment":[122],"corrects":[124],"large":[130],"class":[131],"predictors":[133,180],"estimating":[135],"means":[137],"variances":[139],"terms":[143],"from":[144],"training":[145],"exploiting":[147],"concentration":[149],"phenomena.":[150],"This":[151],"gives":[152],"rise":[153],"non-asymptotic":[155],"intervals,":[157],"can":[159],"help":[160],"avoid":[161],"overestimating":[162],"uncertainty":[163],"critical":[165],"applications":[166],"MRI":[169],"diagnosis.":[170],"Importantly,":[171],"our":[172],"analysis":[173],"extends":[174],"beyond":[175],"sparse":[176],"like":[181],"networks,":[183],"enhancing":[184],"reliability":[186],"model-based":[188],"deep":[189],"learning.":[190],"findings":[192],"bridge":[193],"gap":[195],"between":[196],"established":[197],"theory":[198],"practical":[201],"applicability":[202],"methods.":[206]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}