{"id":"https://openalex.org/W4401863939","doi":"https://doi.org/10.1145/3637528.3671933","title":"BTTackler: A Diagnosis-based Framework for Efficient Deep Learning Hyperparameter Optimization","display_name":"BTTackler: A Diagnosis-based Framework for Efficient Deep Learning Hyperparameter Optimization","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863939","doi":"https://doi.org/10.1145/3637528.3671933"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671933","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671933","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671933","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671933","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063244527","display_name":"Zhongyi Pei","orcid":"https://orcid.org/0000-0002-4324-6989"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhongyi Pei","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005157168","display_name":"Zhiyao Cen","orcid":"https://orcid.org/0009-0001-8836-6773"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyao Cen","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113348060","display_name":"Yipeng Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yipeng Huang","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337653","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0003-1698-8992"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Wang","raw_affiliation_strings":["School of Software, EIRI, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, EIRI, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102160299","display_name":"Lin Liu","orcid":"https://orcid.org/0000-0002-3704-2322"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Liu","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Philip Yu","raw_affiliation_strings":["School of Software, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025662362","display_name":"M.W. Long","orcid":"https://orcid.org/0000-0002-5412-9120"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingsheng Long","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100373517","display_name":"Jianmin Wang","orcid":"https://orcid.org/0000-0001-6841-7943"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianmin Wang","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5063244527"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3442,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65487102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2340","last_page":"2351"},"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":0.984000027179718,"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":0.9768999814987183,"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":0.9188315868377686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7172011137008667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6623293161392212},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6449703574180603},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5015435218811035},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"Hyperparameter optimization","score":0.4307299852371216},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.1151127815246582}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.9188315868377686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7172011137008667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6623293161392212},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6449703574180603},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5015435218811035},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.4307299852371216},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.1151127815246582}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3637528.3671933","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671933","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671933","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:doi:10.48550/arxiv.2602.23630","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1145/3637528.3671933","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671933","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671933","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401863939.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2097998348","https://openalex.org/W2102539288","https://openalex.org/W2192203593","https://openalex.org/W2293634267","https://openalex.org/W2556522401","https://openalex.org/W2604847698","https://openalex.org/W2616028256","https://openalex.org/W2732547613","https://openalex.org/W2898868990","https://openalex.org/W2964882141","https://openalex.org/W2978190445","https://openalex.org/W3011974631","https://openalex.org/W3030054017","https://openalex.org/W3045004532","https://openalex.org/W3109004940","https://openalex.org/W3129585545","https://openalex.org/W3134796670","https://openalex.org/W3160349922","https://openalex.org/W3160369295","https://openalex.org/W3179950556","https://openalex.org/W4229068576","https://openalex.org/W4284681547","https://openalex.org/W4286977192","https://openalex.org/W4287328644","https://openalex.org/W4313458531","https://openalex.org/W6674385629"],"related_works":["https://openalex.org/W2953665647","https://openalex.org/W4281646320","https://openalex.org/W4205712847","https://openalex.org/W3169687406","https://openalex.org/W4388119537","https://openalex.org/W3014750173","https://openalex.org/W3114025147","https://openalex.org/W2602382373","https://openalex.org/W4283697347","https://openalex.org/W3198113463"],"abstract_inverted_index":{"Hyperparameter":[0],"optimization":[1,84],"(HPO)":[2],"is":[3],"known":[4],"to":[5,30,81,124,214,220,253,257],"be":[6,61],"costly":[7],"in":[8,66,76],"deep":[9,168],"learning,":[10],"especially":[11],"when":[12],"leveraging":[13],"automated":[14,20,185,258],"approaches.":[15],"Most":[16],"of":[17,34,70,98,142,165,183,203,211],"the":[18,32,67,71,87,96,181,201,216],"existing":[19],"HPO":[21,118,162,176,186,259],"methods":[22,222,235],"are":[23,28,155,158],"accuracy-based,":[24],"i.e.,":[25],"accuracy":[26,64,195,218],"metrics":[27,65],"used":[29,175],"guide":[31],"trials":[33,45,89,232],"different":[35],"hyperparameter":[36,101],"configurations":[37,102],"amongst":[38],"a":[39,104,116,140,239],"specific":[40],"search":[41],"space.":[42],"However,":[43],"many":[44],"may":[46],"encounter":[47],"severe":[48],"training":[49,72,122,126,153],"problems,":[50],"such":[51],"as":[52],"vanishing":[53],"gradients":[54],"and":[55,73,94,129,147,172,196,225],"insufficient":[56],"convergence,":[57],"which":[58],"can":[59],"hardly":[60],"reflected":[62],"by":[63,138],"early":[68,149],"stages":[69],"often":[74],"result":[75],"poor":[77],"performance.":[78],"This":[79],"leads":[80],"an":[82,184,246],"inefficient":[83],"trajectory":[85],"because":[86],"bad":[88,132],"occupy":[90],"considerable":[91],"computation":[92],"resources":[93],"reduce":[95],"probability":[97],"finding":[99],"excellent":[100],"within":[103,238],"time":[105,197,212,241],"limitation.":[106],"In":[107],"this":[108],"paper,":[109],"we":[110,188],"propose":[111,189],"Bad":[112],"Trial":[113],"Tackler":[114],"(BTTackler),":[115],"novel":[117],"framework":[119],"that":[120,250],"introduces":[121],"diagnosis":[123],"identify":[125],"problems":[127,154],"automatically":[128],"hence":[130],"tackles":[131],"trials.":[133],"BTTackler":[134,204,256],"diagnoses":[135],"each":[136],"trial":[137],"calculating":[139],"set":[141],"carefully":[143],"designed":[144],"quantified":[145],"indicators":[146],"triggers":[148],"termination":[150],"if":[151],"any":[152],"detected.":[156],"Evaluations":[157],"performed":[159],"on":[160,194,205,223,236],"representative":[161],"tasks":[163],"consisting":[164],"three":[166],"classical":[167],"neural":[169],"networks":[170],"(DNN)":[171],"four":[173],"widely":[174],"methods.":[177],"To":[178],"better":[179],"quantify":[180],"effectiveness":[182],"method,":[187],"two":[190],"new":[191],"measurements":[192],"based":[193],"consumption.":[198],"Results":[199],"show":[200],"advantage":[202],"two-fold:":[206],"(1)":[207],"it":[208,227],"reduces":[209],"40.33%":[210],"consumption":[213],"achieve":[215],"same":[217],"comparable":[219],"baseline":[221,234],"average":[224,237],"(2)":[226],"conducts":[228],"44.5%":[229],"more":[230],"top-10":[231],"than":[233],"given":[240],"budget.":[242],"We":[243],"also":[244],"released":[245],"open-source":[247],"Python":[248],"library":[249],"allows":[251],"users":[252],"easily":[254],"apply":[255],"processes":[260],"with":[261],"minimal":[262],"code":[263],"changes\\footnotehttps://github.com/thuml/BTTackler.":[264]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}