{"id":"https://openalex.org/W4399695726","doi":"https://doi.org/10.48550/arxiv.2406.09194","title":"Benign overfitting in Fixed Dimension via Physics-Informed Learning with Smooth Inductive Bias","display_name":"Benign overfitting in Fixed Dimension via Physics-Informed Learning with Smooth Inductive Bias","publication_year":2024,"publication_date":"2024-06-13","ids":{"openalex":"https://openalex.org/W4399695726","doi":"https://doi.org/10.48550/arxiv.2406.09194"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.09194","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09194","pdf_url":"https://arxiv.org/pdf/2406.09194","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":"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/2406.09194","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101251631","display_name":"Honam Wong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wong, Honam","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100866223","display_name":"Wendao Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Wendao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016703530","display_name":"Fanghui Liu","orcid":"https://orcid.org/0000-0003-4133-7921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Fanghui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101947005","display_name":"Yiping Lu","orcid":"https://orcid.org/0000-0001-9459-699X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Yiping","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101251631"],"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/T12072","display_name":"Machine Learning and Algorithms","score":0.913100004196167,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.913100004196167,"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":0.906000018119812,"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/overfitting","display_name":"Overfitting","score":0.9740560054779053},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.7859182953834534},{"id":"https://openalex.org/keywords/critical-dimension","display_name":"Critical dimension","score":0.4919276237487793},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.3893631100654602},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.3408845067024231},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.3349267244338989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3301488757133484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3181161880493164},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27329742908477783},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.11355677247047424},{"id":"https://openalex.org/keywords/quantum-mechanics","display_name":"Quantum mechanics","score":0.10963258147239685},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.0726100504398346}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9740560054779053},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.7859182953834534},{"id":"https://openalex.org/C207789793","wikidata":"https://www.wikidata.org/wiki/Q3028070","display_name":"Critical dimension","level":2,"score":0.4919276237487793},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3893631100654602},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3408845067024231},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3349267244338989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3301488757133484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3181161880493164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27329742908477783},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.11355677247047424},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.10963258147239685},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0726100504398346}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.09194","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09194","pdf_url":"https://arxiv.org/pdf/2406.09194","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.09194","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.09194","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":"pmh:oai:arXiv.org:2406.09194","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09194","pdf_url":"https://arxiv.org/pdf/2406.09194","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399695726.pdf","grobid_xml":"https://content.openalex.org/works/W4399695726.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W3009056573","https://openalex.org/W4297676672","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,67,166],"machine":[3],"learning":[4,48],"have":[5],"inspired":[6],"a":[7,107],"surge":[8],"of":[9,15,96,109,147],"research":[10],"into":[11],"reconstructing":[12],"specific":[13],"quantities":[14],"interest":[16],"from":[17,86],"measurements":[18],"that":[19,31,63,120],"comply":[20],"with":[21],"certain":[22],"physical":[23],"laws.":[24],"These":[25],"efforts":[26],"focus":[27],"on":[28],"inverse":[29,58,69],"problems":[30],"are":[32],"governed":[33],"by":[34,101],"partial":[35],"differential":[36],"equations":[37],"(PDEs).":[38],"In":[39],"this":[40],"work,":[41],"we":[42,118],"develop":[43],"an":[44],"asymptotic":[45],"Sobolev":[46,104],"norm":[47,176],"curve":[49],"for":[50,80,152],"kernel":[51],"ridge(less)":[52],"regression":[53,87],"when":[54],"addressing":[55],"(elliptical)":[56],"linear":[57],"problems.":[59,88],"Our":[60],"results":[61],"show":[62],"the":[64,68,73,94,113,127,132,145,163,171,174],"PDE":[65],"operators":[66],"problem":[70],"can":[71,125],"stabilize":[72],"variance":[74],"and":[75,155,169],"even":[76],"behave":[77],"benign":[78],"overfitting":[79],"fixed-dimensional":[81],"problems,":[82],"exhibiting":[83],"different":[84,103],"behaviors":[85],"Besides,":[89],"our":[90,159],"investigation":[91],"also":[92],"demonstrates":[93],"impact":[95],"various":[97],"inductive":[98,123,150],"biases":[99,124],"introduced":[100],"minimizing":[102],"norms":[105],"as":[106],"form":[108],"implicit":[110],"regularization.":[111],"For":[112],"regularized":[114],"least":[115],"squares":[116],"estimator,":[117],"find":[119],"all":[121],"considered":[122],"achieve":[126],"optimal":[128],"convergence":[129,139],"rate,":[130],"provided":[131],"regularization":[133],"parameter":[134],"is":[135,141],"appropriately":[136],"chosen.":[137],"The":[138],"rate":[140],"actually":[142],"independent":[143],"to":[144,173],"choice":[146],"(smooth":[148],"enough)":[149],"bias":[151],"both":[153],"ridge":[154],"ridgeless":[156],"regression.":[157],"Surprisingly,":[158],"smoothness":[160],"requirement":[161],"recovered":[162],"condition":[164],"found":[165],"Bayesian":[167],"setting":[168],"extend":[170],"conclusion":[172],"minimum":[175],"interpolation":[177],"estimators.":[178]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2024-06-15T00:00:00"}