{"id":"https://openalex.org/W4391432108","doi":"https://doi.org/10.3390/computation12020024","title":"Data Augmentation for Regression Machine Learning Problems in High Dimensions","display_name":"Data Augmentation for Regression Machine Learning Problems in High Dimensions","publication_year":2024,"publication_date":"2024-02-01","ids":{"openalex":"https://openalex.org/W4391432108","doi":"https://doi.org/10.3390/computation12020024"},"language":"en","primary_location":{"id":"doi:10.3390/computation12020024","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computation12020024","pdf_url":"https://www.mdpi.com/2079-3197/12/2/24/pdf?version=1706755465","source":{"id":"https://openalex.org/S2738402919","display_name":"Computation","issn_l":"2079-3197","issn":["2079-3197"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2079-3197/12/2/24/pdf?version=1706755465","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092963901","display_name":"Clara Guilhaumon","orcid":"https://orcid.org/0009-0009-4094-3744"},"institutions":[{"id":"https://openalex.org/I190861549","display_name":"Arts et M\u00e9tiers","ror":"https://ror.org/018pp1107","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583","https://openalex.org/I190861549","https://openalex.org/I4210134562"]},{"id":"https://openalex.org/I199388852","display_name":"\u00c9cole de Biologie Industrielle","ror":"https://ror.org/029rzwj76","country_code":"FR","type":"education","lineage":["https://openalex.org/I199388852"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Clara Guilhaumon","raw_affiliation_strings":["PIMM, Arts et M\u00e9tiers Institute of Technology, 151 Boulevard de l\u2019Hopital, 75013 Paris, France","UPR EBINNOV, Ecole de Biologie Industrielle, 49 Avenue des Genottes, 95895 Cergy, France"],"raw_orcid":"https://orcid.org/0009-0009-4094-3744","affiliations":[{"raw_affiliation_string":"PIMM, Arts et M\u00e9tiers Institute of Technology, 151 Boulevard de l\u2019Hopital, 75013 Paris, France","institution_ids":["https://openalex.org/I190861549"]},{"raw_affiliation_string":"UPR EBINNOV, Ecole de Biologie Industrielle, 49 Avenue des Genottes, 95895 Cergy, France","institution_ids":["https://openalex.org/I199388852"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049607785","display_name":"Nicolas Hasco\u00ebt","orcid":"https://orcid.org/0000-0002-3823-1045"},"institutions":[{"id":"https://openalex.org/I190861549","display_name":"Arts et M\u00e9tiers","ror":"https://ror.org/018pp1107","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583","https://openalex.org/I190861549","https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Hasco\u00ebt","raw_affiliation_strings":["PIMM, Arts et M\u00e9tiers Institute of Technology, 151 Boulevard de l\u2019Hopital, 75013 Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PIMM, Arts et M\u00e9tiers Institute of Technology, 151 Boulevard de l\u2019Hopital, 75013 Paris, France","institution_ids":["https://openalex.org/I190861549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083504898","display_name":"Francisco Chinesta","orcid":null},"institutions":[{"id":"https://openalex.org/I103562704","display_name":"ESI Group (France)","ror":"https://ror.org/05ww4z228","country_code":"FR","type":"company","lineage":["https://openalex.org/I103562704"]},{"id":"https://openalex.org/I190861549","display_name":"Arts et M\u00e9tiers","ror":"https://ror.org/018pp1107","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583","https://openalex.org/I190861549","https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Francisco Chinesta","raw_affiliation_strings":["CNRS@CREATE Ltd., 1 Create Way, 08-01 CREATE Tower, Singapore 138602, Singapore","ESI Group, Parc Icade, Immeuble le Seville, 3bis, Saarinen, CEDEX, 94528 Rungis, France","PIMM, Arts et M\u00e9tiers Institute of Technology, 151 Boulevard de l\u2019Hopital, 75013 Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS@CREATE Ltd., 1 Create Way, 08-01 CREATE Tower, Singapore 138602, Singapore","institution_ids":[]},{"raw_affiliation_string":"ESI Group, Parc Icade, Immeuble le Seville, 3bis, Saarinen, CEDEX, 94528 Rungis, France","institution_ids":["https://openalex.org/I103562704"]},{"raw_affiliation_string":"PIMM, Arts et M\u00e9tiers Institute of Technology, 151 Boulevard de l\u2019Hopital, 75013 Paris, France","institution_ids":["https://openalex.org/I190861549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019413502","display_name":"Marc Lavarde","orcid":"https://orcid.org/0000-0003-1186-0295"},"institutions":[{"id":"https://openalex.org/I199388852","display_name":"\u00c9cole de Biologie Industrielle","ror":"https://ror.org/029rzwj76","country_code":"FR","type":"education","lineage":["https://openalex.org/I199388852"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marc Lavarde","raw_affiliation_strings":["UPR EBINNOV, Ecole de Biologie Industrielle, 49 Avenue des Genottes, 95895 Cergy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UPR EBINNOV, Ecole de Biologie Industrielle, 49 Avenue des Genottes, 95895 Cergy, France","institution_ids":["https://openalex.org/I199388852"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027094709","display_name":"Fatima Daim","orcid":"https://orcid.org/0000-0003-4001-3132"},"institutions":[{"id":"https://openalex.org/I103562704","display_name":"ESI Group (France)","ror":"https://ror.org/05ww4z228","country_code":"FR","type":"company","lineage":["https://openalex.org/I103562704"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fatima Daim","raw_affiliation_strings":["ESI Group, Parc Icade, Immeuble le Seville, 3bis, Saarinen, CEDEX, 94528 Rungis, France"],"raw_orcid":"https://orcid.org/0000-0003-4001-3132","affiliations":[{"raw_affiliation_string":"ESI Group, Parc Icade, Immeuble le Seville, 3bis, Saarinen, CEDEX, 94528 Rungis, France","institution_ids":["https://openalex.org/I103562704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092963901"],"corresponding_institution_ids":["https://openalex.org/I190861549","https://openalex.org/I199388852"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":2.6491,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90518957,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"12","issue":"2","first_page":"24","last_page":"24"},"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/T12282","display_name":"Mineral Processing and Grinding","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9696000218391418,"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/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.6903152465820312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6839050054550171},{"id":"https://openalex.org/keywords/high-dimensional","display_name":"High dimensional","score":0.5211384296417236},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5153100490570068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5101321339607239},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4389801323413849},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.4201146364212036},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4146011471748352},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2105606496334076},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.09412190318107605},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0762595534324646}],"concepts":[{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6903152465820312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6839050054550171},{"id":"https://openalex.org/C3019722297","wikidata":"https://www.wikidata.org/wiki/Q4440864","display_name":"High dimensional","level":2,"score":0.5211384296417236},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5153100490570068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5101321339607239},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4389801323413849},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4201146364212036},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4146011471748352},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2105606496334076},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.09412190318107605},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0762595534324646},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/computation12020024","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computation12020024","pdf_url":"https://www.mdpi.com/2079-3197/12/2/24/pdf?version=1706755465","source":{"id":"https://openalex.org/S2738402919","display_name":"Computation","issn_l":"2079-3197","issn":["2079-3197"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computation","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-04784982v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04784982","pdf_url":"https://hal.science/hal-04784982v1/document","source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Computation, 2024, 12 (2), pp.24. ⟨10.3390/computation12020024⟩","raw_type":"Journal articles"},{"id":"pmh:oai:doaj.org/article:bdbb9385c30e4465a9e4166070b42ed0","is_oa":true,"landing_page_url":"https://doaj.org/article/bdbb9385c30e4465a9e4166070b42ed0","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computation, Vol 12, Iss 2, p 24 (2024)","raw_type":"article"},{"id":"pmh:oai:sam.ensam.eu:10985/25776","is_oa":true,"landing_page_url":"http://hdl.handle.net/10985/25776","pdf_url":null,"source":{"id":"https://openalex.org/S4306400009","display_name":"SAM, the Arts et M\u00e9tiers ParisTech open access repository (Paris Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190752583","host_organization_name":"ParisTech","host_organization_lineage":["https://openalex.org/I190752583"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hdl.handle.net/10985/25776","raw_type":null}],"best_oa_location":{"id":"doi:10.3390/computation12020024","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computation12020024","pdf_url":"https://www.mdpi.com/2079-3197/12/2/24/pdf?version=1706755465","source":{"id":"https://openalex.org/S2738402919","display_name":"Computation","issn_l":"2079-3197","issn":["2079-3197"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computation","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5699999928474426,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391432108.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1513874326","https://openalex.org/W1549228047","https://openalex.org/W1553262910","https://openalex.org/W1580375566","https://openalex.org/W1976220195","https://openalex.org/W1995875735","https://openalex.org/W2006901874","https://openalex.org/W2019736931","https://openalex.org/W2064868327","https://openalex.org/W2080021732","https://openalex.org/W2084840427","https://openalex.org/W2115305054","https://openalex.org/W2116108132","https://openalex.org/W2162676140","https://openalex.org/W2273687286","https://openalex.org/W2787035179","https://openalex.org/W2863231833","https://openalex.org/W2899062473","https://openalex.org/W2949071206","https://openalex.org/W2951911250","https://openalex.org/W2979481569","https://openalex.org/W3008707413","https://openalex.org/W3130898281","https://openalex.org/W3170063332","https://openalex.org/W3192495122","https://openalex.org/W3212628295","https://openalex.org/W4237151101","https://openalex.org/W4245605522","https://openalex.org/W4252861488","https://openalex.org/W4319018356","https://openalex.org/W4322625893","https://openalex.org/W4387923662","https://openalex.org/W6632922266","https://openalex.org/W6644414443","https://openalex.org/W6660254288","https://openalex.org/W6675206559","https://openalex.org/W6677436389","https://openalex.org/W6735374517"],"related_works":["https://openalex.org/W4324092386","https://openalex.org/W3198417070","https://openalex.org/W1988922486","https://openalex.org/W1571495475","https://openalex.org/W3117541208","https://openalex.org/W2034324715","https://openalex.org/W2622612405","https://openalex.org/W1595984608","https://openalex.org/W3099723194","https://openalex.org/W2977728051"],"abstract_inverted_index":{"Machine":[0],"learning":[1,106,135],"approaches":[2,81],"are":[3],"currently":[4],"used":[5],"to":[6,23,47,90,96,99],"understand":[7],"or":[8,38],"model":[9,26],"complex":[10],"physical":[11],"systems.":[12],"In":[13],"general,":[14],"a":[15,25,56,111,115,132,151],"substantial":[16],"number":[17,58,93],"of":[18,43,59,70,75,94,117,131,147],"samples":[19,95],"must":[20],"be":[21,48,97],"collected":[22],"create":[24],"with":[27],"reliable":[28],"results.":[29],"However,":[30],"collecting":[31],"numerous":[32],"data":[33,71],"is":[34,78],"often":[35],"relatively":[36],"time-consuming":[37],"expensive.":[39],"Moreover,":[40],"the":[41,65,73,92,101,118,129,145,167,171],"problems":[42,62],"industrial":[44,159],"interest":[45],"tend":[46],"more":[49,51],"and":[50,53,122,156],"complex,":[52],"depend":[54],"on":[55,83,114,150,157],"high":[57,139],"parameters.":[60],"High-dimensional":[61],"intrinsically":[63],"involve":[64],"need":[66],"for":[67],"large":[68],"amounts":[69],"through":[72],"curse":[74],"dimensionality.":[76],"That":[77],"why":[79],"new":[80,133],"based":[82,113],"smart":[84],"sampling":[85],"techniques":[86],"have":[87],"been":[88],"investigated":[89],"minimize":[91],"given":[98],"train":[100],"model,":[102],"such":[103],"as":[104],"active":[105,134],"methods.":[107],"Here,":[108],"we":[109],"propose":[110],"technique":[112,149],"combination":[116],"Fisher":[119],"information":[120],"matrix":[121],"sparse":[123],"proper":[124],"generalized":[125],"decomposition":[126],"that":[127,166],"enables":[128],"definition":[130],"informativeness":[136],"criterion":[137],"in":[138],"dimensions.":[140],"We":[141],"provide":[142],"examples":[143],"proving":[144],"performances":[146],"this":[148],"theoretical":[152],"5D":[153],"polynomial":[154],"function":[155],"an":[158],"crash":[160],"simulation":[161],"application.":[162],"The":[163],"results":[164],"prove":[165],"proposed":[168],"strategy":[169],"outperforms":[170],"usual":[172],"ones.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-01-24T23:23:39.755997","created_date":"2025-10-10T00:00:00"}