{"id":"https://openalex.org/W4309045102","doi":"https://doi.org/10.48550/arxiv.2211.06077","title":"Overparameterized random feature regression with nearly orthogonal data","display_name":"Overparameterized random feature regression with nearly orthogonal data","publication_year":2022,"publication_date":"2022-11-11","ids":{"openalex":"https://openalex.org/W4309045102","doi":"https://doi.org/10.48550/arxiv.2211.06077"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2211.06077","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.06077","pdf_url":"https://arxiv.org/pdf/2211.06077","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.06077","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100398379","display_name":"Zhichao Wang","orcid":"https://orcid.org/0009-0007-5676-2353","observed_orcids":["https://orcid.org/0009-0007-5676-2353"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Zhichao","raw_affiliation_strings":["University of California , San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028927697","display_name":"Yizhe Zhu","orcid":"https://orcid.org/0000-0002-5665-0374","observed_orcids":["https://orcid.org/0000-0002-5665-0374"]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhu, Yizhe","raw_affiliation_strings":["University of California , Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Irvine","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.8539999723434448,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.8539999723434448,"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":0.07199999690055847,"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/T12676","display_name":"Machine Learning and ELM","score":0.03590000048279762,"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/overparameterized-neural-networks","display_name":"overparameterized neural networks","score":0.8820000290870667},{"id":"https://openalex.org/keywords/kernel-ridge-regression","display_name":"kernel ridge regression","score":0.9039999842643738},{"id":"https://openalex.org/keywords/hermite-polynomial-expansion","display_name":"Hermite polynomial expansion","score":0.7599999904632568},{"id":"https://openalex.org/keywords/teacher-student-models","display_name":"teacher-student models","score":0.9549999833106995}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.671947717666626},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5580219626426697},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5391194820404053},{"id":"https://openalex.org/C120068334","wikidata":"https://www.wikidata.org/wiki/Q45343","display_name":"Polynomial regression","level":3,"score":0.492378830909729},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48495960235595703},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.4593529999256134},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.4326988756656647},{"id":"https://openalex.org/C200695384","wikidata":"https://www.wikidata.org/wiki/Q1739319","display_name":"Kernel regression","level":3,"score":0.42319706082344055},{"id":"https://openalex.org/C160446489","wikidata":"https://www.wikidata.org/wiki/Q7226642","display_name":"Polynomial kernel","level":4,"score":0.42062145471572876},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4077824354171753},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3345554769039154},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3285325765609741},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.25404441356658936},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.25164592266082764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2110099196434021},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18954643607139587},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.15278619527816772},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.09194120764732361},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2211.06077","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.06077","pdf_url":"https://arxiv.org/pdf/2211.06077","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2211.06077","doi":"https://doi.org/10.48550/arxiv.2211.06077","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.06077","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.06077","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.06077","pdf_url":"https://arxiv.org/pdf/2211.06077","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":null,"license_id":null,"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/G4284953697","display_name":"Brown\u2019s Spectral Measure: New Computational Methods from Stochastics, Partial Differential Equations, and Operator Theory","funder_award_id":"2055340","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8053880684","display_name":"Far apart: outliers, extremal eigenvalues, and spectral gaps in random graphs and random matrices","funder_award_id":"2154099","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320334164","display_name":"Simons Institute for the Theory of Computing, University of California Berkeley","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4309045102.pdf","grobid_xml":"https://content.openalex.org/works/W4309045102.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W3080149057","https://openalex.org/W4221152951","https://openalex.org/W4224815527","https://openalex.org/W4226444507","https://openalex.org/W4280503585","https://openalex.org/W4281619172","https://openalex.org/W4286970764","https://openalex.org/W4306311895","https://openalex.org/W4309202124","https://openalex.org/W4309956477","https://openalex.org/W4388706347","https://openalex.org/W4413182660","https://openalex.org/W7133202629"],"related_works":["https://openalex.org/W4200337531","https://openalex.org/W3121358889","https://openalex.org/W4415796071","https://openalex.org/W4392822353","https://openalex.org/W3080149057","https://openalex.org/W3098901286","https://openalex.org/W2976566529","https://openalex.org/W3007945084","https://openalex.org/W3199041052","https://openalex.org/W7221823478"],"abstract_inverted_index":{"We":[0,20,97],"investigate":[1],"the":[2,22,26,37,41,44,51,62,100,103,112,117,125,135,139,142,173,177],"properties":[3],"of":[4,25,43,69,102,116,138,151,176],"random":[5,17,94],"feature":[6,95],"ridge":[7,79],"regression":[8,80],"(RFRR)":[9],"given":[10],"by":[11,91,105],"a":[12,77,92,106,148,169,180],"two-layer":[13],"neural":[14],"network":[15],"with":[16,28],"Gaussian":[18],"initialization.":[19],"study":[21],"non-asymptotic":[23,58],"behaviors":[24],"RFRR":[27,70,140,178],"nearly":[29,160],"orthogonal":[30,161],"deterministic":[31],"unit-length":[32],"input":[33,155],"data":[34,129,156],"vectors":[35],"in":[36],"overparameterized":[38],"regime,":[39],"where":[40],"width":[42],"first":[45],"layer":[46],"is":[47,84],"much":[48],"larger":[49],"than":[50],"sample":[52],"size.":[53],"Our":[54,144],"analysis":[55],"shows":[56],"high-probability":[57],"concentration":[59],"results":[60,145],"for":[61,76,147,172,179],"training":[63],"errors,":[64],"cross-validations,":[65],"and":[66,141,154],"generalization":[67,174],"errors":[68],"centered":[71],"around":[72],"their":[73],"respective":[74],"values":[75],"kernel":[78,89,108,133],"(KRR).":[81],"This":[82,131],"KRR":[83,104],"derived":[85],"from":[86,111],"an":[87],"expected":[88],"generated":[90],"nonlinear":[93,181],"map.":[96],"then":[98],"approximate":[99],"performance":[101],"polynomial":[107,114,132],"matrix":[109],"obtained":[110],"Hermite":[113],"expansion":[115],"activation":[118,152],"function,":[119],"whose":[120],"degree":[121],"only":[122],"depends":[123],"on":[124,164],"orthogonality":[126],"among":[127],"different":[128],"points.":[130],"determines":[134],"asymptotic":[136],"behavior":[137],"KRR.":[143],"hold":[146],"wide":[149],"variety":[150],"functions":[153],"sets":[157],"that":[158],"exhibit":[159],"properties.":[162],"Based":[163],"these":[165],"approximations,":[166],"we":[167],"obtain":[168],"lower":[170],"bound":[171],"error":[175],"student-teacher":[182],"model.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-11-21T00:00:00"}