{"id":"https://openalex.org/W2963527567","doi":"https://doi.org/10.1145/3292500.3330649","title":"A Generalized Framework for Population Based Training","display_name":"A Generalized Framework for Population Based Training","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2963527567","doi":"https://doi.org/10.1145/3292500.3330649","mag":"2963527567"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330649","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330649","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330649","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & 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/10.1145/3292500.3330649","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100413662","display_name":"Ang Li","orcid":"https://orcid.org/0000-0003-4472-4919"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ang Li","raw_affiliation_strings":["DeepMind, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"DeepMind, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ola Spyra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ola Spyra","raw_affiliation_strings":["DeepMind, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"DeepMind, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044992209","display_name":"Sagi Perel","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sagi Perel","raw_affiliation_strings":["Google Brain, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Google Brain, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044929367","display_name":"Valentin Dalibard","orcid":"https://orcid.org/0009-0005-4944-6745"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Valentin Dalibard","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004153109","display_name":"Max Jaderberg","orcid":"https://orcid.org/0000-0002-9033-2695"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Max Jaderberg","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088326953","display_name":"Chenjie Gu","orcid":"https://orcid.org/0000-0002-1339-4534"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenjie Gu","raw_affiliation_strings":["DeepMind, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"DeepMind, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003238807","display_name":"David Budden","orcid":"https://orcid.org/0000-0003-4372-8985"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Budden","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059282957","display_name":"Tim Harley","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tim Harley","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057184074","display_name":"Pramod Gupta","orcid":"https://orcid.org/0000-0002-6767-3520"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pramod Gupta","raw_affiliation_strings":["DeepMind, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"DeepMind, Mountain View, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100413662"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6776,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.96798929,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1791","last_page":"1799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8301250338554382},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7817785739898682},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5772661566734314},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5248743891716003},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5037350058555603},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5003607273101807},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4867813289165497},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4430937170982361},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.43456417322158813},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.4306705892086029},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4240751564502716},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.10966339707374573},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08964541554450989},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08963847160339355}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8301250338554382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817785739898682},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5772661566734314},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5248743891716003},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5037350058555603},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5003607273101807},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4867813289165497},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4430937170982361},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.43456417322158813},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.4306705892086029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4240751564502716},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.10966339707374573},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08964541554450989},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08963847160339355},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3330649","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330649","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330649","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3292500.3330649","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330649","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330649","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963527567.pdf","grobid_xml":"https://content.openalex.org/works/W2963527567.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1986490585","https://openalex.org/W2097998348","https://openalex.org/W2106411961","https://openalex.org/W2112036188","https://openalex.org/W2166107799","https://openalex.org/W2556522401","https://openalex.org/W2732547613","https://openalex.org/W2785430118","https://openalex.org/W2914304175","https://openalex.org/W2949264490","https://openalex.org/W2949382160","https://openalex.org/W2950182411","https://openalex.org/W2951665052","https://openalex.org/W2953384591","https://openalex.org/W2963403868","https://openalex.org/W2963815651","https://openalex.org/W3124229194","https://openalex.org/W4385245566","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W2140186469","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W2775233965","https://openalex.org/W4294338060","https://openalex.org/W1491017262","https://openalex.org/W1494824878","https://openalex.org/W4297819361"],"abstract_inverted_index":{"Population":[0],"Based":[1],"Training":[2],"(PBT)":[3],"is":[4],"a":[5,39,58,99],"recent":[6],"approach":[7],"that":[8,44,110],"jointly":[9],"optimizes":[10],"neural":[11],"network":[12],"weights":[13,19],"and":[14,24,90,117],"hyperparameters":[15,26],"which":[16],"periodically":[17],"copies":[18],"of":[20,52],"the":[21,62,125],"best":[22],"performers":[23],"mutates":[25],"during":[27],"training.":[28],"Previous":[29],"PBT":[30,42,63,112],"implementations":[31],"have":[32],"been":[33],"synchronized":[34],"glass-box":[35],"systems.":[36],"We":[37,93,108],"propose":[38],"general,":[40],"black-box":[41,66],"framework":[43],"distributes":[45],"many":[46],"asynchronous":[47],"\"trials\"":[48],"(a":[49],"small":[50],"number":[51],"training":[53,78],"steps":[54],"with":[55],"warm-starting)":[56],"across":[57],"cluster,":[59],"coordinated":[60],"by":[61],"controller.":[64],"The":[65],"design":[67],"does":[68],"not":[69],"make":[70],"assumptions":[71],"on":[72],"model":[73,103],"architectures,":[74],"loss":[75],"functions":[76],"or":[77],"procedures.":[79],"Our":[80],"system":[81,96,113],"supports":[82],"dynamic":[83],"hyperparameter":[84],"schedules":[85],"to":[86,97,121],"optimize":[87],"both":[88],"differentiable":[89],"non-differentiable":[91],"metrics.":[92],"apply":[94],"our":[95,111],"train":[98],"state-of-the-art":[100],"WaveNet":[101],"generative":[102],"for":[104],"human":[105],"voice":[106],"synthesis.":[107],"show":[109],"achieves":[114],"better":[115],"accuracy":[116],"faster":[118],"convergence":[119],"compared":[120],"existing":[122],"methods,":[123],"given":[124],"same":[126],"computational":[127],"resource.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":13}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}