{"id":"https://openalex.org/W2976666284","doi":"https://doi.org/10.1109/isit.2019.8849398","title":"A New Look at an Old Problem: A Universal Learning Approach to Linear Regression","display_name":"A New Look at an Old Problem: A Universal Learning Approach to Linear Regression","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2976666284","doi":"https://doi.org/10.1109/isit.2019.8849398","mag":"2976666284"},"language":"en","primary_location":{"id":"doi:10.1109/isit.2019.8849398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2019.8849398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.04708","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019615542","display_name":"Koby Bibas","orcid":"https://orcid.org/0000-0003-2812-1253"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Koby Bibas","raw_affiliation_strings":["School of Electrical Engineering, Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005484384","display_name":"Yaniv Fogel","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yaniv Fogel","raw_affiliation_strings":["School of Electrical Engineering, Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066905280","display_name":"Meir Feder","orcid":"https://orcid.org/0000-0002-1290-0482"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Meir Feder","raw_affiliation_strings":["School of Electrical Engineering, Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019615542"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":3.6165,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.94490779,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2304","last_page":"2308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998999834060669,"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":0.9998999834060669,"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/T10057","display_name":"Face and Expression Recognition","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/learnability","display_name":"Learnability","score":0.7153921127319336},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.6203446984291077},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5926035046577454},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.5754849910736084},{"id":"https://openalex.org/keywords/polynomial-regression","display_name":"Polynomial regression","score":0.534466564655304},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.5181323289871216},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.4994502067565918},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.4848538637161255},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4434429705142975},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4318883419036865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3976951241493225},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.34150078892707825},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2375650405883789},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.12779253721237183},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1064266562461853}],"concepts":[{"id":"https://openalex.org/C2777723229","wikidata":"https://www.wikidata.org/wiki/Q4367921","display_name":"Learnability","level":2,"score":0.7153921127319336},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.6203446984291077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5926035046577454},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.5754849910736084},{"id":"https://openalex.org/C120068334","wikidata":"https://www.wikidata.org/wiki/Q45343","display_name":"Polynomial regression","level":3,"score":0.534466564655304},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5181323289871216},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.4994502067565918},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.4848538637161255},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4434429705142975},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4318883419036865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3976951241493225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34150078892707825},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2375650405883789},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.12779253721237183},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1064266562461853},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isit.2019.8849398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2019.8849398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.04708","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.04708","pdf_url":"https://arxiv.org/pdf/1905.04708","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.04708","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.04708","pdf_url":"https://arxiv.org/pdf/1905.04708","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W92982764","https://openalex.org/W1542073121","https://openalex.org/W1554944419","https://openalex.org/W1975551153","https://openalex.org/W2019363670","https://openalex.org/W2047028564","https://openalex.org/W2075665712","https://openalex.org/W2155195660","https://openalex.org/W2171033594","https://openalex.org/W2172992359","https://openalex.org/W2294584261","https://openalex.org/W2487770199","https://openalex.org/W2905701627","https://openalex.org/W2942101471","https://openalex.org/W4206686222","https://openalex.org/W4234698323","https://openalex.org/W4238893454","https://openalex.org/W4242065205","https://openalex.org/W4255455317","https://openalex.org/W4382677476","https://openalex.org/W6603695008","https://openalex.org/W6682891771","https://openalex.org/W6757735113"],"related_works":["https://openalex.org/W2575826071","https://openalex.org/W2390681602","https://openalex.org/W2379078475","https://openalex.org/W2092994918","https://openalex.org/W2799339361","https://openalex.org/W23477101","https://openalex.org/W4283730101","https://openalex.org/W1645621197","https://openalex.org/W3118299338","https://openalex.org/W1971809020"],"abstract_inverted_index":{"Linear":[0],"regression":[1,27,153],"is":[2,13],"a":[3,38,59,132,170,174,179],"classical":[4],"paradigm":[5],"in":[6,79,114,121,131],"statistics.":[7],"A":[8],"new":[9],"look":[10],"at":[11],"it":[12,160],"provided":[14],"via":[15],"the":[16,28,32,42,90,93,103,126,136,140,144,149,157,167],"lens":[17],"of":[18,41,72,95,105,143,148,172],"universal":[19,23,70],"learning.":[20],"In":[21],"applying":[22],"learning":[24,71],"to":[25,176],"linear":[26,39,152],"hypotheses":[29],"class":[30],"represents":[31],"label":[33],"y":[34],"\u2208":[35,52],"\u211b":[36,53],"as":[37,82,84],"combination":[40],"feature":[43],"vector":[44,128],"x":[45,51],"<sup":[46,54],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[47,55],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">T</sup>":[48],"\u03b8":[49],"where":[50,92],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</sup>":[56],",":[57],"within":[58],"Gaussian":[60],"error.":[61],"The":[62],"Predictive":[63],"Normalized":[64],"Maximum":[65],"Likelihood":[66],"(pNML)":[67],"solution":[68],"for":[69],"individual":[73],"data":[74,177],"can":[75,109,154],"be":[76,100,110,119],"expressed":[77],"analytically":[78],"this":[80,115],"case,":[81],"well":[83],"its":[85],"associated":[86,138],"learnability":[87,117],"measure.":[88],"Interestingly,":[89],"situation":[91],"number":[94,104],"parameters":[96],"M":[97],"may":[98],"even":[99],"larger":[101],"than":[102],"training":[106,150],"samples":[107],"N":[108],"examined.":[111],"As":[112],"expected,":[113],"case":[116],"cannot":[118],"attained":[120],"every":[122],"situation;":[123],"nevertheless,":[124],"if":[125],"test":[127],"resides":[129],"mostly":[130],"subspace":[133],"spanned":[134],"by":[135],"eigenvectors":[137],"with":[139,169,178],"large":[141,181],"eigenvalues":[142],"empirical":[145],"correlation":[146],"matrix":[147],"data,":[151],"generalize":[155],"despite":[156],"fact":[158],"that":[159],"uses":[161],"an":[162],"\"over-parametrized\"":[163],"model.":[164],"We":[165],"demonstrate":[166],"results":[168],"simulation":[171],"fitting":[173],"polynomial":[175,182],"possibly":[180],"degree.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-10-03T00:00:00"}