{"id":"https://openalex.org/W2947593239","doi":"https://doi.org/10.1109/cec48606.2020.9185777","title":"Improved Training Speed, Accuracy, and Data Utilization Through Loss Function Optimization","display_name":"Improved Training Speed, Accuracy, and Data Utilization Through Loss Function Optimization","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W2947593239","doi":"https://doi.org/10.1109/cec48606.2020.9185777","mag":"2947593239"},"language":"en","primary_location":{"id":"doi:10.1109/cec48606.2020.9185777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec48606.2020.9185777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.11528","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066709653","display_name":"Santiago Gonz\u00e1lez","orcid":"https://orcid.org/0000-0001-5685-4580"},"institutions":[{"id":"https://openalex.org/I163361683","display_name":"Cognizant (United States)","ror":"https://ror.org/036s7bw54","country_code":"US","type":"company","lineage":["https://openalex.org/I163361683"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Santiago Gonzalez","raw_affiliation_strings":["Cognizant Technology Solutions, San Francisco, California, USA","University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"Cognizant Technology Solutions, San Francisco, California, USA","institution_ids":["https://openalex.org/I163361683"]},{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020441009","display_name":"Risto Miikkulainen","orcid":"https://orcid.org/0000-0002-0062-0037"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]},{"id":"https://openalex.org/I163361683","display_name":"Cognizant (United States)","ror":"https://ror.org/036s7bw54","country_code":"US","type":"company","lineage":["https://openalex.org/I163361683"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Risto Miikkulainen","raw_affiliation_strings":["Cognizant Technology Solutions, San Francisco, California, USA","University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"Cognizant Technology Solutions, San Francisco, California, USA","institution_ids":["https://openalex.org/I163361683"]},{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066709653"],"corresponding_institution_ids":["https://openalex.org/I163361683","https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.2344,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.83505478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","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/T12535","display_name":"Machine Learning and Data Classification","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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9994999766349792,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.6532049179077148},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6181620359420776},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5228571891784668},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.46358534693717957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45805442333221436},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4481736421585083},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4375160336494446},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.419772207736969},{"id":"https://openalex.org/keywords/hinge-loss","display_name":"Hinge loss","score":0.415690153837204},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4106217324733734},{"id":"https://openalex.org/keywords/cma-es","display_name":"CMA-ES","score":0.41003191471099854},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37027478218078613},{"id":"https://openalex.org/keywords/evolution-strategy","display_name":"Evolution strategy","score":0.3476948142051697},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3301961123943329},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.28373003005981445},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.257974237203598},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.20968014001846313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6532049179077148},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6181620359420776},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5228571891784668},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.46358534693717957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45805442333221436},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4481736421585083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4375160336494446},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.419772207736969},{"id":"https://openalex.org/C39891107","wikidata":"https://www.wikidata.org/wiki/Q5767098","display_name":"Hinge loss","level":3,"score":0.415690153837204},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4106217324733734},{"id":"https://openalex.org/C205555498","wikidata":"https://www.wikidata.org/wiki/Q505588","display_name":"CMA-ES","level":4,"score":0.41003191471099854},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37027478218078613},{"id":"https://openalex.org/C207002847","wikidata":"https://www.wikidata.org/wiki/Q2912857","display_name":"Evolution strategy","level":3,"score":0.3476948142051697},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3301961123943329},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.28373003005981445},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.257974237203598},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.20968014001846313},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cec48606.2020.9185777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec48606.2020.9185777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.11528","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.11528","pdf_url":"https://arxiv.org/pdf/1905.11528","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:2947593239","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1905.11528.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.1905.11528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.11528","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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.11528","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.11528","pdf_url":"https://arxiv.org/pdf/1905.11528","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2947593239.pdf","grobid_xml":"https://content.openalex.org/works/W2947593239.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W86586912","https://openalex.org/W1522301498","https://openalex.org/W1605438009","https://openalex.org/W1665214252","https://openalex.org/W1904365287","https://openalex.org/W1979769287","https://openalex.org/W2099471712","https://openalex.org/W2101677491","https://openalex.org/W2112036188","https://openalex.org/W2123408238","https://openalex.org/W2146502635","https://openalex.org/W2148317584","https://openalex.org/W2163605009","https://openalex.org/W2344075909","https://openalex.org/W2402144811","https://openalex.org/W2593744649","https://openalex.org/W2594265094","https://openalex.org/W2792012198","https://openalex.org/W2804047946","https://openalex.org/W2906697496","https://openalex.org/W2913868188","https://openalex.org/W2949736877","https://openalex.org/W2950300355","https://openalex.org/W2955863859","https://openalex.org/W2963351448","https://openalex.org/W2964054038","https://openalex.org/W2964059111","https://openalex.org/W2964212578","https://openalex.org/W2964227899","https://openalex.org/W2965658867","https://openalex.org/W3118608800","https://openalex.org/W6603572680","https://openalex.org/W6617145748","https://openalex.org/W6631190155","https://openalex.org/W6635845569","https://openalex.org/W6637242042","https://openalex.org/W6640036494","https://openalex.org/W6681435938","https://openalex.org/W6684191040","https://openalex.org/W6704744639","https://openalex.org/W6713134421","https://openalex.org/W6732696085","https://openalex.org/W6748317118","https://openalex.org/W6749121346","https://openalex.org/W6753278433","https://openalex.org/W6757973382"],"related_works":["https://openalex.org/W2996955463","https://openalex.org/W3118136760","https://openalex.org/W2998166845","https://openalex.org/W2182982932","https://openalex.org/W2807434070","https://openalex.org/W1565301672","https://openalex.org/W3130774444","https://openalex.org/W2899911233","https://openalex.org/W2998006993","https://openalex.org/W3206105267","https://openalex.org/W3206816108","https://openalex.org/W2914317573","https://openalex.org/W3110217300","https://openalex.org/W3204520992","https://openalex.org/W1597253794","https://openalex.org/W2366094445","https://openalex.org/W79692902","https://openalex.org/W2896230333","https://openalex.org/W2802636049","https://openalex.org/W2959065637"],"abstract_inverted_index":{"As":[0],"the":[1,127],"complexity":[2],"of":[3,86,166],"neural":[4],"network":[5],"models":[6],"has":[7,10],"grown,":[8],"it":[9],"become":[11],"increasingly":[12],"important":[13,171],"to":[14,32,98,113,125,155],"optimize":[15],"their":[16],"design":[17],"automatically":[18],"through":[19],"metalearning.":[20],"Methods":[21],"for":[22,69,152],"discovering":[23],"hyperparameters,":[24],"topologies,":[25],"and":[26,50,66,88,96,103,150,168],"learning":[27],"rate":[28],"schedules":[29],"have":[30],"lead":[31],"significant":[33],"increases":[34],"in":[35,52,146],"performance.":[36],"This":[37],"paper":[38],"shows":[39],"that":[40],"loss":[41,62,80,121,130,140],"functions":[42,63,81,92,122,141],"can":[43],"be":[44,156],"optimized":[45],"with":[46,119,137],"metalearning":[47],"as":[48],"well,":[49],"result":[51],"similar":[53],"improvements.":[54],"The":[55],"method,":[56],"Genetic":[57],"Lossfunction":[58],"Optimization":[59],"(GLO),":[60],"discovers":[61],"de":[64],"novo,":[65],"optimizes":[67],"them":[68],"a":[70,84,105,163],"target":[71],"task.":[72],"Leveraging":[73],"techniques":[74],"from":[75,83],"genetic":[76],"programming,":[77],"GLO":[78,120],"builds":[79],"hierarchically":[82],"set":[85],"operators":[87],"leaf":[89],"nodes.":[90],"These":[91],"are":[93,123],"repeatedly":[94],"recombined":[95],"mutated":[97],"find":[99,114],"an":[100,170],"optimal":[101,115],"structure,":[102],"then":[104],"covariance-matrix":[106],"adaptation":[107],"evolutionary":[108],"strategy":[109],"(CMA-ES)":[110],"is":[111],"used":[112],"coefficients.":[116],"Networks":[117],"trained":[118],"found":[124],"outperform":[126],"standard":[128,132],"cross-entropy":[129],"on":[131],"image":[133],"classification":[134],"tasks.":[135],"Training":[136],"these":[138],"new":[139,164],"requires":[142],"fewer":[143],"steps,":[144],"results":[145],"lower":[147],"test":[148],"error,":[149],"allows":[151],"smaller":[153],"datasets":[154],"used.":[157],"Loss":[158],"function":[159],"optimization":[160],"thus":[161],"provides":[162],"dimension":[165],"metalearning,":[167],"constitutes":[169],"step":[172],"towards":[173],"AutoML.":[174]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}