{"id":"https://openalex.org/W3008640195","doi":"https://doi.org/10.1137/20m1320031","title":"Diversity Sampling is an Implicit Regularization for Kernel Methods","display_name":"Diversity Sampling is an Implicit Regularization for Kernel Methods","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3008640195","doi":"https://doi.org/10.1137/20m1320031","mag":"3008640195"},"language":"en","primary_location":{"id":"doi:10.1137/20m1320031","is_oa":true,"landing_page_url":"https://doi.org/10.1137/20m1320031","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/20M1320031","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://epubs.siam.org/doi/pdf/10.1137/20M1320031","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071057567","display_name":"Micha\u00ebl Fanuel","orcid":"https://orcid.org/0000-0002-7438-0005"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Michael Fanuel","raw_affiliation_strings":["Katholieke Universiteit Leuven"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Katholieke Universiteit Leuven","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016808637","display_name":"Joachim Schreurs","orcid":"https://orcid.org/0000-0001-8670-2553"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joachim Schreurs","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078854904","display_name":"Johan A. K. Suykens","orcid":"https://orcid.org/0000-0002-8846-6352"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Johan Suykens","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071057567"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":0.1781,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.41917877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":"1","first_page":"280","last_page":"297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9986000061035156,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9962999820709229,"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/regularization","display_name":"Regularization (linguistics)","score":0.606404185295105},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6015675067901611},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5731126666069031},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.5163367986679077},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4974866211414337},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.480101615190506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4629111886024475},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42532339692115784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4023996889591217},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3227185606956482},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3215571641921997},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3135673701763153},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06487381458282471}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.606404185295105},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6015675067901611},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5731126666069031},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.5163367986679077},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4974866211414337},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.480101615190506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4629111886024475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42532339692115784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4023996889591217},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3227185606956482},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3215571641921997},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3135673701763153},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06487381458282471},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1137/20m1320031","is_oa":true,"landing_page_url":"https://doi.org/10.1137/20m1320031","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/20M1320031","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/667238","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/667238","pdf_url":"https://lirias.kuleuven.be/bitstream/123456789/667238/2/20-21.pdf","source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"SIAM Journal on Mathematics of Data Science, vol. 3 (1), (280-297)","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:2002.08616","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.08616","pdf_url":"https://arxiv.org/pdf/2002.08616","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"},{"id":"mag:3008640195","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.08616.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2002.08616","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.08616","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1137/20m1320031","is_oa":true,"landing_page_url":"https://doi.org/10.1137/20m1320031","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/20M1320031","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1150901635","display_name":"Exploring Duality for Future Data-driven Modelling","funder_award_id":"787960","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G1431749042","display_name":null,"funder_award_id":"KUL0076","funder_id":"https://openalex.org/F4320322308","funder_display_name":"KU Leuven"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7923493454","display_name":"Exploring Duality for Future Data-driven Modelling","funder_award_id":"787960","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322308","display_name":"KU Leuven","ror":"https://ror.org/05f950310"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3008640195.pdf","grobid_xml":"https://content.openalex.org/works/W3008640195.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1969468690","https://openalex.org/W2015363484","https://openalex.org/W2032511141","https://openalex.org/W2039859942","https://openalex.org/W2076410399","https://openalex.org/W2080051189","https://openalex.org/W2097645701","https://openalex.org/W2103318769","https://openalex.org/W2138779671","https://openalex.org/W2140095548","https://openalex.org/W2185932763","https://openalex.org/W2187580259","https://openalex.org/W2307132432","https://openalex.org/W2345444914","https://openalex.org/W2787348029","https://openalex.org/W2886836477","https://openalex.org/W2961262728","https://openalex.org/W2963674301","https://openalex.org/W2963742538","https://openalex.org/W2963923734","https://openalex.org/W2963942108","https://openalex.org/W2964258753","https://openalex.org/W2971350322","https://openalex.org/W2998241229","https://openalex.org/W3011721937","https://openalex.org/W3035261884","https://openalex.org/W3103014337","https://openalex.org/W3104969455"],"related_works":["https://openalex.org/W2964153027","https://openalex.org/W2768491555","https://openalex.org/W2934764460","https://openalex.org/W3087532277","https://openalex.org/W3108548045","https://openalex.org/W2807832997","https://openalex.org/W2772118439","https://openalex.org/W1621482170","https://openalex.org/W2240479807","https://openalex.org/W2790949175","https://openalex.org/W2509572357","https://openalex.org/W2085097105","https://openalex.org/W2559832977","https://openalex.org/W1996019203","https://openalex.org/W2154913025","https://openalex.org/W3014779775","https://openalex.org/W2168505892","https://openalex.org/W2396285032","https://openalex.org/W2327416654","https://openalex.org/W2567083482"],"abstract_inverted_index":{"Kernel":[0],"methods":[1,102],"have":[2],"achieved":[3],"very":[4],"good":[5],"performance":[6],"on":[7,27,55,104],"large":[8,165],"scale":[9],"regression":[10,128,137],"and":[11,19,42,92,119],"classification":[12],"problems,":[13],"by":[14],"using":[15,76],"the":[16,39,56,64,88,97,113,133,136,142],"Nystr\u00f6m":[17,23,65,126],"method":[18],"preconditioning":[20],"techniques.":[21],"The":[22],"approximation":[24,37,66],"--":[25,32],"based":[26,103],"a":[28,34,47,116,120,147],"subset":[29],"of":[30,38,49,58,99,107,135,141,161],"landmarks":[31,61,131],"gives":[33],"low":[35],"rank":[36],"kernel":[40,73,101,127],"matrix,":[41],"is":[43,154,171],"known":[44],"to":[45,146,157],"provide":[46],"form":[48],"implicit":[50],"regularization.":[51,93],"We":[52],"further":[53],"elaborate":[54],"impact":[57],"sampling":[59,170],"diverse":[60,108,130,159],"for":[62,80],"constructing":[63],"in":[67,138],"supervised":[68],"as":[69,71],"well":[70],"unsupervised":[72],"methods.":[74],"By":[75],"Determinantal":[77],"Point":[78],"Processes":[79],"sampling,":[81],"we":[82,95,123],"obtain":[83],"additional":[84],"theoretical":[85],"results":[86],"concerning":[87],"interplay":[89],"between":[90],"diversity":[91],"Empirically,":[94],"demonstrate":[96],"advantages":[98],"training":[100],"subsets":[105],"made":[106],"points.":[109],"In":[110],"particular,":[111],"if":[112],"dataset":[114],"has":[115],"dense":[117],"bulk":[118],"sparser":[121,139],"tail,":[122],"show":[124],"that":[125],"with":[129,144],"increases":[132],"accuracy":[134],"regions":[140],"dataset,":[143],"respect":[145],"uniform":[148],"landmark":[149],"sampling.":[150],"A":[151],"greedy":[152],"heuristic":[153],"also":[155],"proposed":[156],"select":[158],"samples":[160],"significant":[162],"size":[163],"within":[164],"datasets":[166],"when":[167],"exact":[168],"DPP":[169],"not":[172],"practically":[173],"feasible.":[174]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-10T00:00:00"}