{"id":"https://openalex.org/W2963862287","doi":"https://doi.org/10.1609/aaai.v33i01.33015297","title":"HyperAdam: A Learnable Task-Adaptive Adam for Network Training","display_name":"HyperAdam: A Learnable Task-Adaptive Adam for Network Training","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2963862287","doi":"https://doi.org/10.1609/aaai.v33i01.33015297","mag":"2963862287"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33015297","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015297","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33015297","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101824702","display_name":"Shipeng Wang","orcid":"https://orcid.org/0000-0003-4586-8287"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shipeng Wang","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037419606","display_name":"Jian Sun","orcid":"https://orcid.org/0000-0001-7206-0641"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Sun","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113541537","display_name":"Zongben Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongben Xu","raw_affiliation_strings":["Xi\u2019an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"5297","last_page":"5304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9968000054359436,"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/T10320","display_name":"Neural Networks and Applications","score":0.9968000054359436,"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":0.9925000071525574,"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/T12676","display_name":"Machine Learning and ELM","score":0.9695000052452087,"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":0.8103471994400024},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7209745049476624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7090321183204651},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.690787672996521},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.6276575326919556},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5661956071853638},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5642579197883606},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.447252094745636},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.4244718551635742},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4136390686035156},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09767240285873413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8103471994400024},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7209745049476624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7090321183204651},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.690787672996521},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.6276575326919556},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5661956071853638},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5642579197883606},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.447252094745636},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.4244718551635742},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4136390686035156},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09767240285873413},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33015297","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015297","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4466","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4466","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4466/4344","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33015297","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015297","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W28412257","https://openalex.org/W1522301498","https://openalex.org/W1994616650","https://openalex.org/W2061863621","https://openalex.org/W2089217417","https://openalex.org/W2112796928","https://openalex.org/W2130942839","https://openalex.org/W2137825550","https://openalex.org/W2140804329","https://openalex.org/W2146502635","https://openalex.org/W2150355110","https://openalex.org/W2162953669","https://openalex.org/W2173248099","https://openalex.org/W2176412452","https://openalex.org/W2194775991","https://openalex.org/W2427497464","https://openalex.org/W2465345967","https://openalex.org/W2472819217","https://openalex.org/W2552808051","https://openalex.org/W2601450892","https://openalex.org/W2602585184","https://openalex.org/W2604451232","https://openalex.org/W2624086852","https://openalex.org/W2755546070","https://openalex.org/W2765507192","https://openalex.org/W2770522929","https://openalex.org/W2785523195","https://openalex.org/W2787035179","https://openalex.org/W2792422168","https://openalex.org/W2951634833","https://openalex.org/W2963230762","https://openalex.org/W2963285578","https://openalex.org/W2963775850","https://openalex.org/W2963864421","https://openalex.org/W3118608800","https://openalex.org/W4320013936","https://openalex.org/W6601131277","https://openalex.org/W6631190155","https://openalex.org/W6648914341","https://openalex.org/W6679436768","https://openalex.org/W6680455300","https://openalex.org/W6680776955","https://openalex.org/W6683992514","https://openalex.org/W6687483927","https://openalex.org/W6714477741","https://openalex.org/W6729455701","https://openalex.org/W6735236233","https://openalex.org/W6747620207","https://openalex.org/W6748869568","https://openalex.org/W6760385162"],"related_works":["https://openalex.org/W2065370636","https://openalex.org/W4312822655","https://openalex.org/W3157170264","https://openalex.org/W4377865163","https://openalex.org/W4312601715","https://openalex.org/W4298185893","https://openalex.org/W2896078964","https://openalex.org/W4281399026","https://openalex.org/W2897842727","https://openalex.org/W4205830908"],"abstract_inverted_index":{"Deep":[0],"neural":[1,126],"networks":[2],"are":[3,113],"traditionally":[4],"trained":[5],"using":[6],"humandesigned":[7],"stochastic":[8],"optimization":[9],"algorithms,":[10],"such":[11,143],"as":[12,27,60,123,144],"SGD":[13],"and":[14,72,108,131,148],"Adam.":[15],"Recently,":[16],"the":[17,42,66,118],"approach":[18],"of":[19,68,94],"learning":[20],"to":[21,70,136],"optimize":[22],"network":[23,78,127,141],"parameters":[24],"has":[25],"emerged":[26],"a":[28,56,77,124],"promising":[29],"research":[30],"topic.":[31],"However,":[32],"these":[33],"learned":[34,115],"black-box":[35],"optimizers":[36],"sometimes":[37],"do":[38],"not":[39],"fully":[40],"utilize":[41],"experience":[43],"in":[44,50,84,111],"human-designed":[45],"optimizers,":[46],"therefore":[47],"have":[48],"limitation":[49],"generalization":[51],"ability.":[52],"In":[53],"this":[54],"paper,":[55],"new":[57],"optimizer,":[58],"dubbed":[59],"HyperAdam,":[61],"is":[62,90,121,134],"proposed":[63],"that":[64],"combines":[65],"idea":[67],"\u201clearning":[69],"optimize\u201d":[71],"traditional":[73],"Adam":[74,99],"optimizer.":[75],"Given":[76],"for":[79,139],"training,":[80,142],"its":[81],"parameter":[82],"update":[83],"each":[85],"iteration":[86],"generated":[87,97],"by":[88,98],"HyperAdam":[89,112,120],"an":[91],"adaptive":[92],"combination":[93,106],"multiple":[95],"updates":[96],"with":[100,128],"varying":[101],"decay":[102,109],"rates":[103,110],".":[104],"The":[105],"weights":[107],"adaptively":[114],"depending":[116],"on":[117],"task.":[119],"modeled":[122],"recurrent":[125],"AdamCell,":[129],"WeightCell":[130],"StateCell.":[132],"It":[133],"justified":[135],"be":[137],"state-of-the-art":[138],"various":[140],"multilayer":[145],"perceptron,":[146],"CNN":[147],"LSTM.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}