{"id":"https://openalex.org/W1914219707","doi":"https://doi.org/10.48550/arxiv.1205.2653","title":"L2 Regularization for Learning Kernels","display_name":"L2 Regularization for Learning Kernels","publication_year":2012,"publication_date":"2012-05-09","ids":{"openalex":"https://openalex.org/W1914219707","doi":"https://doi.org/10.48550/arxiv.1205.2653","mag":"1914219707"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1205.2653","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1205.2653","pdf_url":"https://arxiv.org/pdf/1205.2653","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/1205.2653","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013243115","display_name":"Corinna Cortes","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cortes, Corinna","raw_affiliation_strings":["Google Research New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research New York","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058849006","display_name":"Mehryar Mohri","orcid":"https://orcid.org/0000-0002-3987-9847","observed_orcids":["https://orcid.org/0000-0002-3987-9847"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohri, Mehryar","raw_affiliation_strings":["Courant Institute and Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Courant Institute and Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089765894","display_name":"Afshin Rostamizadeh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rostamizadeh, Afshin","raw_affiliation_strings":["Courant Institute New York University","New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Courant Institute New York University","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":520,"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":0.46000000834465027,"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":0.46000000834465027,"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":0.29739999771118164,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.12759999930858612,"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/tikhonov-regularization","display_name":"Tikhonov regularization","score":0.890999972820282},{"id":"https://openalex.org/keywords/kernel-ridge-regression","display_name":"kernel ridge regression","score":0.8560000061988831},{"id":"https://openalex.org/keywords/kernel-selection","display_name":"kernel selection","score":0.597000002861023},{"id":"https://openalex.org/keywords/learning-bounds","display_name":"learning bounds","score":0.6470000147819519},{"id":"https://openalex.org/keywords/stability-bounds","display_name":"stability bounds","score":0.746999979019165},{"id":"https://openalex.org/keywords/kernel-regression","display_name":"kernel regression","score":0.49300000071525574},{"id":"https://openalex.org/keywords/iterative-methods","display_name":"iterative methods","score":0.5410000085830688}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.828424334526062},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6362268328666687},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5205115675926208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48110073804855347},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.472996324300766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.463215172290802},{"id":"https://openalex.org/C79248915","wikidata":"https://www.wikidata.org/wiki/Q17086776","display_name":"Proximal gradient methods for learning","level":5,"score":0.44289061427116394},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.4384186267852783},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3962837755680084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39542391896247864},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38635435700416565},{"id":"https://openalex.org/C141718189","wikidata":"https://www.wikidata.org/wiki/Q7309628","display_name":"Regularization perspectives on support vector machines","level":4,"score":0.3664628863334656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.358445405960083},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2036493718624115},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.1452988088130951},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1438489556312561},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10865059494972229},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.06571811437606812},{"id":"https://openalex.org/C152442038","wikidata":"https://www.wikidata.org/wiki/Q2778212","display_name":"Tikhonov regularization","level":3,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:arXiv.org:1205.2653","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1205.2653","pdf_url":"https://arxiv.org/pdf/1205.2653","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":"mag:2951654630","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1205.2653","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.227.4868","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.227.4868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.nyu.edu/%7Erostami/papers/l2reg-uai.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.1409","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.1409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/35392.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.1205.2653","doi":"https://doi.org/10.48550/arxiv.1205.2653","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1205.2653","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:1205.2653","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1205.2653","pdf_url":"https://arxiv.org/pdf/1205.2653","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1914219707.pdf","grobid_xml":"https://content.openalex.org/works/W1914219707.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1510073064","https://openalex.org/W1559159361","https://openalex.org/W1646506067","https://openalex.org/W1755117326","https://openalex.org/W1967849786","https://openalex.org/W2087347434","https://openalex.org/W2095981367","https://openalex.org/W2106503792","https://openalex.org/W2121033924","https://openalex.org/W2123068691","https://openalex.org/W2139338362","https://openalex.org/W2140069289","https://openalex.org/W2145295623","https://openalex.org/W2148603752","https://openalex.org/W2160392347","https://openalex.org/W2160429500","https://openalex.org/W2163302275","https://openalex.org/W2170356051","https://openalex.org/W3119651796","https://openalex.org/W4239510810"],"related_works":["https://openalex.org/W1518544712","https://openalex.org/W3103790796","https://openalex.org/W2047709005","https://openalex.org/W2263177918","https://openalex.org/W2951792757","https://openalex.org/W2952767562","https://openalex.org/W7097741364","https://openalex.org/W7034140888","https://openalex.org/W194417083","https://openalex.org/W3147650715"],"abstract_inverted_index":{"The":[0],"choice":[1],"of":[2,10,37,44,48,64,71,87,97,100,120,155,170,196],"the":[3,8,20,23,31,62,68,85,95,98,101,121,143,153],"kernel":[4,32,145],"is":[5,16],"critical":[6],"to":[7,19,29,142,163,173],"success":[9],"many":[11],"learning":[12,65,88,128],"algorithms":[13],"but":[14,73,172],"it":[15,35],"typically":[17],"left":[18],"user.":[21],"Instead,":[22],"training":[24],"data":[25],"can":[26,161],"be":[27],"used":[28],"learn":[30],"by":[33,53],"selecting":[34],"out":[36],"a":[38,54,116,167,193],"given":[39],"family,":[40],"such":[41],"as":[42],"that":[43,112,133,158],"non-negative":[45],"linear":[46],"combinations":[47],"p":[49],"base":[50],"kernels,":[51,171],"constrained":[52],"trace":[55],"or":[56],"L1":[57,159],"regularization.":[58],"This":[59],"paper":[60],"studies":[61],"problem":[63,86,103,122],"kernels":[66,72,89,132],"with":[67,74,90,192],"same":[69],"family":[70],"an":[75,106,136],"L2":[76,181],"regularization":[77,160,182],"instead,":[78],"and":[79,104,126,186],"for":[80,110,130,166],"regression":[81,147],"problems.":[82],"We":[83,93,114,150],"analyze":[84],"ridge":[91,146],"regression.":[92],"derive":[94],"form":[96],"solution":[99],"optimization":[102],"give":[105,127],"efficient":[107],"iterative":[108],"algorithm":[109],"computing":[111],"solution.":[113],"present":[115],"novel":[117],"theoretical":[118],"analysis":[119],"based":[123],"on":[124],"stability":[125,148],"bounds":[129],"orthogonal":[131],"contain":[134],"only":[135],"additive":[137],"term":[138],"O(pp/m)":[139],"when":[140],"compared":[141],"standard":[144],"bound.":[149],"also":[151],"report":[152],"results":[154],"experiments":[156],"indicating":[157],"lead":[162],"modest":[164],"improvements":[165,191],"small":[168],"number":[169,195],"performance":[174,185],"degradations":[175],"in":[176,187],"larger-scale":[177],"cases.":[178],"In":[179],"contrast,":[180],"never":[183],"degrades":[184],"fact":[188],"achieves":[189],"significant":[190],"large":[194],"kernels.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":22},{"year":2025,"cited_by_count":75},{"year":2024,"cited_by_count":73},{"year":2023,"cited_by_count":68},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":48},{"year":2020,"cited_by_count":42},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":18}],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2016-06-24T00:00:00"}