{"id":"https://openalex.org/W4386815423","doi":"https://doi.org/10.14428/esann/2023.es2023-84","title":"Is One Epoch All You Need For Multi-Fidelity Hyperparameter Optimization?","display_name":"Is One Epoch All You Need For Multi-Fidelity Hyperparameter Optimization?","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386815423","doi":"https://doi.org/10.14428/esann/2023.es2023-84"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2023.es2023-84","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-84","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-84","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.14428/esann/2023.es2023-84","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006450724","display_name":"Romain \u00c9gel\u00e9","orcid":"https://orcid.org/0000-0002-8992-8192"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]}],"countries":["FR","US"],"is_corresponding":true,"raw_author_name":"Romain Egele","raw_affiliation_strings":["-MCS, Argonne Ntl Lab, USA;","-LISN, U. Paris-Saclay, France;"],"affiliations":[{"raw_affiliation_string":"-MCS, Argonne Ntl Lab, USA;","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"-LISN, U. Paris-Saclay, France;","institution_ids":["https://openalex.org/I277688954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006360335","display_name":"Isabelle Guyon","orcid":"https://orcid.org/0000-0002-9266-1783"},"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"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Isabelle Guyon","raw_affiliation_strings":["-Google, USA & ChaLearn, USA;","-LISN, U. Paris-Saclay, France;"],"affiliations":[{"raw_affiliation_string":"-Google, USA & ChaLearn, USA;","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"-LISN, U. Paris-Saclay, France;","institution_ids":["https://openalex.org/I277688954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029261205","display_name":"Yixuan Sun","orcid":"https://orcid.org/0000-0003-1109-3380"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yixuan Sun","raw_affiliation_strings":["-MCS, Argonne Ntl Lab, USA;"],"affiliations":[{"raw_affiliation_string":"-MCS, Argonne Ntl Lab, USA;","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068721920","display_name":"Prasanna Balaprakash","orcid":"https://orcid.org/0000-0002-0292-5715"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasanna Balaprakash","raw_affiliation_strings":["-CCSD, Oak Ridge Ntl Lab, USA"],"affiliations":[{"raw_affiliation_string":"-CCSD, Oak Ridge Ntl Lab, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006450724"],"corresponding_institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I277688954"],"apc_list":null,"apc_paid":null,"fwci":0.5237,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71613478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"555","last_page":"560"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9966999888420105,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9811999797821045,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9061415791511536},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7114626169204712},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"Hyperparameter optimization","score":0.6972239017486572},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6958103775978088},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6766868829727173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.632953941822052},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5771739482879639},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5650458335876465},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5105465650558472},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.4996461868286133},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4312744736671448},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.10975468158721924}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.9061415791511536},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7114626169204712},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.6972239017486572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6958103775978088},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6766868829727173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.632953941822052},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5771739482879639},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5650458335876465},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5105465650558472},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.4996461868286133},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4312744736671448},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.10975468158721924},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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":1,"locations":[{"id":"doi:10.14428/esann/2023.es2023-84","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-84","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-84","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2023.es2023-84","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-84","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-84","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386815423.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1575029535","https://openalex.org/W2266822037","https://openalex.org/W2408019865","https://openalex.org/W2556522401","https://openalex.org/W2751836095","https://openalex.org/W2786615446","https://openalex.org/W2804268694","https://openalex.org/W2921683824","https://openalex.org/W2963474950","https://openalex.org/W2963842222","https://openalex.org/W3011655242","https://openalex.org/W3012023297","https://openalex.org/W3037833767","https://openalex.org/W3139250374","https://openalex.org/W4226379115","https://openalex.org/W4286977192","https://openalex.org/W4286982322","https://openalex.org/W4287242089","https://openalex.org/W4288357194","https://openalex.org/W4297778814","https://openalex.org/W4301373168","https://openalex.org/W4320502886"],"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":{"Hyperparameter":[0],"optimization":[1,137,214,261],"(HPO)":[2,138],"is":[3,139,208,280,359],"crucial":[4],"for":[5,61],"fine-tuning":[6],"machine":[7,154,249,277],"learning":[8,27,92,103,155,176,184,204,248,278],"models,":[9],"but":[10,181],"it":[11],"can":[12,231,287],"be":[13,170,232,288],"computationally":[14],"expensive.To":[15],"reduce":[16,253],"costs,":[17],"Multi-fidelity":[18,236],"HPO":[19,207,237],"(MF-HPO)":[20,238],"leverages":[21],"intermediate":[22,247],"accuracy":[23,271,353],"levels":[24,284],"in":[25,122,201],"the":[26,57,71,91,95,107,119,127,149,174,183,187,190,254,260,268,292,316,326,343],"process":[28,185],"and":[29,124,162,186,197,234,257,282,297,307,336],"discards":[30],"low-performing":[31],"models":[32,55],"early":[33],"on.We":[34],"conducted":[35],"a":[36,44,100,140,153,212,218,221,225,276,300,309,312,319,347],"comparison":[37],"of":[38,86,94,109,129,143,152,160,189,195,270,285,315,349],"various":[39],"representative":[40],"MF-HPO":[41,130],"methods":[42,239],"against":[43],"simple":[45],"baseline":[46,51,75,121],"on":[47,311],"classical":[48],"benchmark":[49,96],"data.The":[50],"involved":[52],"discarding":[53],"all":[54],"except":[56],"Top-K":[58],"after":[59],"training":[60,68,306],"only":[62],"one":[63],"epoch,":[64],"followed":[65],"by":[66,341],"further":[67],"to":[69,79,132,147,224,252,267,290,333,361],"select":[70],"best":[72,150],"model.Surprisingly,":[73],"this":[74,229,331],"achieved":[76],"similar":[77],"results":[78],"its":[80],"counterparts,":[81],"while":[82,318],"requiring":[83],"an":[84],"order":[85],"magnitude":[87],"less":[88],"computation.Upon":[89],"analyzing":[90],"curves":[93],"data,":[97,317],"we":[98],"observed":[99],"few":[101],"dominant":[102],"curves,":[104],"which":[105,158,245,275],"explained":[106],"success":[108],"our":[110],"baseline.This":[111],"suggests":[112],"that":[113,168],"researchers":[114],"should":[115],"(1)":[116],"always":[117],"use":[118,246,330],"suggested":[120],"benchmarks":[123,131],"(2)":[125],"broaden":[126],"diversity":[128],"include":[133,193],"more":[134],"complex":[135],"cases.Hyperparameter":[136],"key":[141],"component":[142],"AutoML":[144],"systems.It":[145],"aims":[146],"find":[148],"configuration":[151,223],"(ML)":[156],"pipeline,":[157],"consists":[159],"data":[161],"model":[163,279,310,338,344],"components.Hyperparameters":[164],"(HP)":[165],"are":[166],"parameters":[167,339],"cannot":[169],"learned":[171],"directly":[172],"with":[173],"primarly":[175],"algorithm":[177],"(e.g.,":[178],"gradient":[179],"descent),":[180],"affect":[182],"performance":[188,226,250],"pipeline.Those":[191],"may":[192],"number":[194],"layers":[196],"units":[198],"per":[199],"layer":[200],"deep":[202],"networks,":[203],"rates,":[205],"etc.":[206],"usually":[209],"formulated":[210],"as":[211],"black-box":[213],"problem":[215],"[1],":[216],"where":[217],"function":[219,230],"maps":[220],"HP":[222],"score.However,":[227],"evaluating":[228,308],"costly":[233],"time-consuming.Therefore,":[235],"have":[240],"been":[241],"proposed":[242],"[2,":[243],"3],":[244],"estimates":[251],"computational":[255,295],"cost":[256,296],"speed":[258],"up":[259],"process.In":[262],"multi-fidelity":[263],"algorithms,":[264],"fidelity":[265,286,302,321,351,357],"refers":[266],"level":[269,303,322,358],"or":[272],"resolution":[273],"at":[274,355],"trained":[281],"evaluated.Different":[283],"used":[289,360],"balance":[291],"trade-off":[293],"between":[294],"accuracy.For":[298],"example,":[299],"low":[301],"could":[304],"involve":[305,324],"small":[313],"subset":[314],"high":[320],"would":[323],"using":[325,346],"entire":[327],"dataset.Multi-fidelity":[328],"algorithms":[329],"concept":[332],"optimize":[334],"hyperparameters":[335],"other":[337],"efficiently":[340],"exploring":[342],"space":[345],"combination":[348],"different":[350],"levels.The":[352],"obtained":[354],"each":[356],"guide":[362]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}