{"id":"https://openalex.org/W2919302225","doi":"https://doi.org/10.1109/tencon.2018.8650070","title":"On the Difficulty of DNN Hyperparameter Optimization Using Learning Curve Prediction","display_name":"On the Difficulty of DNN Hyperparameter Optimization Using Learning Curve Prediction","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2919302225","doi":"https://doi.org/10.1109/tencon.2018.8650070","mag":"2919302225"},"language":"en","primary_location":{"id":"doi:10.1109/tencon.2018.8650070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon.2018.8650070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2018 - 2018 IEEE Region 10 Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101854638","display_name":"Daeyoung Choi","orcid":"https://orcid.org/0000-0001-6323-4478"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Daeyoung Choi","raw_affiliation_strings":["Department of Transdisciplinary Studies, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Transdisciplinary Studies, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023054084","display_name":"Hyunghun Cho","orcid":"https://orcid.org/0000-0001-8478-5762"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunghun Cho","raw_affiliation_strings":["Department of Transdisciplinary Studies, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Transdisciplinary Studies, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103058698","display_name":"Wonjong Rhee","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonjong Rhee","raw_affiliation_strings":["Department of Transdisciplinary Studies, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Transdisciplinary Studies, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101854638"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":1.1402,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.84414375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"15","issue":null,"first_page":"0651","last_page":"0656"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9980000257492065,"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/hyperparameter","display_name":"Hyperparameter","score":0.9629729986190796},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.8757510185241699},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.8578624725341797},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"Hyperparameter optimization","score":0.8059715628623962},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7344516515731812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7221733331680298},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7075128555297852},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4814800024032593},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46390244364738464},{"id":"https://openalex.org/keywords/learning-curve","display_name":"Learning curve","score":0.4527299106121063},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43812820315361023},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4342869818210602}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.9629729986190796},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8757510185241699},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.8578624725341797},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.8059715628623962},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7344516515731812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7221733331680298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7075128555297852},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4814800024032593},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46390244364738464},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.4527299106121063},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43812820315361023},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4342869818210602},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tencon.2018.8650070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon.2018.8650070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2018 - 2018 IEEE Region 10 Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W60686164","https://openalex.org/W2097998348","https://openalex.org/W2112796928","https://openalex.org/W2113207845","https://openalex.org/W2131241448","https://openalex.org/W2151554678","https://openalex.org/W2266822037","https://openalex.org/W2553303224","https://openalex.org/W2594529350","https://openalex.org/W2732547613","https://openalex.org/W2751836095","https://openalex.org/W2911964244","https://openalex.org/W2949264490","https://openalex.org/W2951886768","https://openalex.org/W2962746461","https://openalex.org/W2964294659","https://openalex.org/W4295185264","https://openalex.org/W4297778814","https://openalex.org/W4300687381","https://openalex.org/W6674385629","https://openalex.org/W6677088747","https://openalex.org/W6678911119","https://openalex.org/W6693270258","https://openalex.org/W6729956949","https://openalex.org/W6729972426","https://openalex.org/W6734593296","https://openalex.org/W6748057086"],"related_works":["https://openalex.org/W3169687406","https://openalex.org/W3206613651","https://openalex.org/W4286902601","https://openalex.org/W2200000192","https://openalex.org/W2395916875","https://openalex.org/W2405673391","https://openalex.org/W3103707007","https://openalex.org/W2906178137","https://openalex.org/W2963001956","https://openalex.org/W2782093256"],"abstract_inverted_index":{"With":[0],"the":[1,69,73,78,86,130,133,140,160,171,198,203,219,225,253,280],"recent":[2,256],"success":[3],"of":[4,10,15,59,72,108,120,132,150,162,175,243,255,265,268,272],"deep":[5],"learning":[6,57,135,151,163,179,205,246,266],"on":[7,170,193,197,202,261,279],"a":[8,25,105,147,154,186,269],"variety":[9],"applications,":[11],"efficiently":[12],"tuning":[13],"hyperparameters":[14],"Deep":[16],"Neural":[17],"Networks":[18],"(DNNs)":[19],"with":[20],"less":[21],"effort":[22],"has":[23],"become":[24],"timely":[26],"and":[27,64,122,124,173,189,200,214,216,236,286],"practical":[28],"topic.":[29],"As":[30],"an":[31,97],"algorithmic":[32],"solution,":[33],"automatic":[34],"hyperparameter":[35,55,75,110,118,143,241,284,287],"optimization":[36,40,111,119,242],"methods":[37],"like":[38],"Bayesian":[39],"have":[41],"gained":[42],"popularity":[43],"for":[44,104,125,153,181],"achieving":[45],"human-comparable":[46],"or":[47],"even":[48],"human-surpassing":[49],"performance.":[50],"To":[51],"further":[52],"speed":[53,182],"up":[54],"optimization,":[56],"curves":[58,136,152,180,267],"DNNs":[60,244],"can":[61,101,166,190,221,229],"be":[62,102,191,222,230,275],"predicted":[63],"used":[65],"to":[66,139],"early":[67,210],"terminate":[68],"training":[70,80],"phase":[71],"chosen":[74],"setting":[76],"when":[77],"expected":[79],"performance":[81],"is":[82,93,184,249],"not":[83,185],"satisfactory.":[84],"While":[85],"previous":[87],"studies":[88,257],"show":[89,217],"promising":[90],"results,":[91],"it":[92],"still":[94],"unclear":[95],"if":[96],"effective":[98],"general":[99],"rule":[100],"derived":[103],"broad":[106],"spectrum":[107],"DNN":[109,282],"problems.":[112],"In":[113,251],"this":[114],"work,":[115],"we":[116,128,157,207],"consider":[117],"MNIST":[121],"CIFAR-10,":[123],"each":[126],"task,":[127,156,281],"analyze":[129],"characteristics":[131,161],"20,000":[134,141,204],"that":[137,159,218,240,258],"correspond":[138],"different":[142],"configurations.":[144],"By":[145],"investigating":[146],"large":[148],"number":[149,271],"given":[155],"find":[158],"curve":[164,247],"shapes":[165],"drastically":[167],"change":[168],"depending":[169,278],"choice":[172],"range":[174],"hyperparameters.":[176],"Therefore,":[177],"utilizing":[178],"improvement":[183],"simple":[187],"task":[188],"dependent":[192],"many":[194],"factors.":[195],"Based":[196],"observations":[199,235],"analyses":[201],"curves,":[206],"design":[208],"two":[209],"termination":[211],"rules,":[212],"ETR-1":[213],"ETR-2,":[215],"rules":[220],"beneficial":[223],"in":[224],"best":[226],"case":[227],"but":[228],"harmful":[231],"as":[232],"well.":[233],"Our":[234],"experimental":[237],"results":[238,254],"highlight":[239],"using":[245],"prediction":[248],"challenging.":[250],"particular,":[252],"are":[259],"based":[260],"at":[262],"most":[263],"thousands":[264],"limited":[270],"tasks":[273],"should":[274],"carefully":[276],"interpreted":[277],"model,":[283],"choice,":[285],"range.":[288]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}