{"id":"https://openalex.org/W3129694574","doi":"https://doi.org/10.1109/tpami.2021.3061581","title":"Variational HyperAdam: A Meta-learning Approach to Network Training","display_name":"Variational HyperAdam: A Meta-learning Approach to Network Training","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3129694574","doi":"https://doi.org/10.1109/tpami.2021.3061581","mag":"3129694574","pmid":"https://pubmed.ncbi.nlm.nih.gov/33621172"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3061581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3061581","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/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":true,"raw_author_name":"Shipeng Wang","raw_affiliation_strings":["School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, (e-mail: wangshipeng8128@stu.xjtu.edu.cn)","[School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, (e-mail: wangshipeng8128@stu.xjtu.edu.cn)]"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, (e-mail: wangshipeng8128@stu.xjtu.edu.cn)","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"[School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, (e-mail: wangshipeng8128@stu.xjtu.edu.cn)]","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101785878","display_name":"Yan Yang","orcid":"https://orcid.org/0000-0001-6227-5235"},"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":"Yan Yang","raw_affiliation_strings":["School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, (e-mail: yangyan92@stu.xjtu.edu.cn)","[School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, (e-mail: yangyan92@stu.xjtu.edu.cn)]"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, (e-mail: yangyan92@stu.xjtu.edu.cn)","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"[School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, (e-mail: yangyan92@stu.xjtu.edu.cn)]","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":["School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, 710049 (e-mail: jiansun@mail.xjtu.edu.cn)","[School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, 710049 (e-mail: jiansun@mail.xjtu.edu.cn)]"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, 710049 (e-mail: jiansun@mail.xjtu.edu.cn)","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"[School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, 710049 (e-mail: jiansun@mail.xjtu.edu.cn)]","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109280540","display_name":"Zongben Xu","orcid":"https://orcid.org/0000-0002-4066-2338"},"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":["School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, (e-mail: zbxu@mail.xjtu.edu.cn)","[School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, (e-mail: zbxu@mail.xjtu.edu.cn)]"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, (e-mail: zbxu@mail.xjtu.edu.cn)","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"[School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi, China, (e-mail: zbxu@mail.xjtu.edu.cn)]","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101824702"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":1.0568,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.78259804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"44","issue":"8","first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T10320","display_name":"Neural Networks and Applications","score":0.9983000159263611,"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/T12676","display_name":"Machine Learning and ELM","score":0.998199999332428,"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":0.6483311057090759},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6144667267799377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5985569357872009},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5058293342590332},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4584569036960602},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4522536098957062},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4454534351825714},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43270260095596313},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4326152801513672},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42137789726257324},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37860536575317383},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2769530415534973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6483311057090759},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6144667267799377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5985569357872009},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5058293342590332},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4584569036960602},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4522536098957062},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4454534351825714},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43270260095596313},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4326152801513672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42137789726257324},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37860536575317383},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2769530415534973},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2021.3061581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3061581","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:33621172","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33621172","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3056973599","display_name":null,"funder_award_id":"11971373","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5372072380","display_name":null,"funder_award_id":"U1811461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G575329728","display_name":null,"funder_award_id":"U20B2075","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8104038856","display_name":null,"funder_award_id":"12026605","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":115,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W6908809","https://openalex.org/W28412257","https://openalex.org/W1522301498","https://openalex.org/W1592305655","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1959608418","https://openalex.org/W1994616650","https://openalex.org/W2057853719","https://openalex.org/W2061863621","https://openalex.org/W2064675550","https://openalex.org/W2089217417","https://openalex.org/W2095705004","https://openalex.org/W2100341991","https://openalex.org/W2108677974","https://openalex.org/W2111406701","https://openalex.org/W2112796928","https://openalex.org/W2115629999","https://openalex.org/W2137825550","https://openalex.org/W2140804329","https://openalex.org/W2146502635","https://openalex.org/W2150355110","https://openalex.org/W2162953669","https://openalex.org/W2163605009","https://openalex.org/W2164411961","https://openalex.org/W2166096645","https://openalex.org/W2167433878","https://openalex.org/W2194775991","https://openalex.org/W2472819217","https://openalex.org/W2552808051","https://openalex.org/W2589226201","https://openalex.org/W2601450892","https://openalex.org/W2604451232","https://openalex.org/W2604763608","https://openalex.org/W2619307294","https://openalex.org/W2624086852","https://openalex.org/W2753738274","https://openalex.org/W2755546070","https://openalex.org/W2765507192","https://openalex.org/W2785523195","https://openalex.org/W2787035179","https://openalex.org/W2792422168","https://openalex.org/W2803526748","https://openalex.org/W2889965839","https://openalex.org/W2892122929","https://openalex.org/W2892359699","https://openalex.org/W2899771611","https://openalex.org/W2902719825","https://openalex.org/W2912984848","https://openalex.org/W2920582597","https://openalex.org/W2949935872","https://openalex.org/W2950378732","https://openalex.org/W2950942124","https://openalex.org/W2951326654","https://openalex.org/W2951634833","https://openalex.org/W2952258850","https://openalex.org/W2952825952","https://openalex.org/W2962739609","https://openalex.org/W2963043696","https://openalex.org/W2963081790","https://openalex.org/W2963230762","https://openalex.org/W2963285578","https://openalex.org/W2963562522","https://openalex.org/W2963586744","https://openalex.org/W2963775850","https://openalex.org/W2963862287","https://openalex.org/W2963864421","https://openalex.org/W2964112702","https://openalex.org/W3118608800","https://openalex.org/W3176049064","https://openalex.org/W4212863985","https://openalex.org/W4320013936","https://openalex.org/W6600213771","https://openalex.org/W6600284362","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6640963894","https://openalex.org/W6674330103","https://openalex.org/W6675186613","https://openalex.org/W6681435938","https://openalex.org/W6682824805","https://openalex.org/W6684191040","https://openalex.org/W6684488266","https://openalex.org/W6684809622","https://openalex.org/W6684921986","https://openalex.org/W6685562342","https://openalex.org/W6717367658","https://openalex.org/W6720057410","https://openalex.org/W6727654133","https://openalex.org/W6729455701","https://openalex.org/W6733532687","https://openalex.org/W6735236233","https://openalex.org/W6735618850","https://openalex.org/W6735961515","https://openalex.org/W6736057607","https://openalex.org/W6738693370","https://openalex.org/W6739653404","https://openalex.org/W6744066916","https://openalex.org/W6744181227","https://openalex.org/W6744627333","https://openalex.org/W6746868464","https://openalex.org/W6747620207","https://openalex.org/W6748284727","https://openalex.org/W6748869568","https://openalex.org/W6749700008","https://openalex.org/W6752245542","https://openalex.org/W6753113894","https://openalex.org/W6753311412","https://openalex.org/W6754038005","https://openalex.org/W6754615192","https://openalex.org/W6754756046","https://openalex.org/W6755318316","https://openalex.org/W6757751764","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W4375867731","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2080152487","https://openalex.org/W2082756648","https://openalex.org/W2239445980","https://openalex.org/W2065370636"],"abstract_inverted_index":{"Stochastic":[0],"optimization":[1],"algorithms":[2],"have":[3,54],"been":[4],"popular":[5],"for":[6,25,90,133,154,161,202],"training":[7,26,91,104,117,135,200],"deep":[8],"neural":[9,27,92,100],"networks.":[10,28],"Recently,":[11],"there":[12],"emerges":[13],"a":[14,63,74,82,149,159,180],"new":[15],"approach":[16,182],"of":[17,39,98,165,170,205],"learning-based":[18,32],"optimizer,":[19,65],"which":[20,70],"has":[21],"achieved":[22,197],"promising":[23],"performance":[24,201],"However,":[29],"these":[30],"black-box":[31],"optimizers":[33,44],"do":[34],"not":[35],"fully":[36],"take":[37],"advantage":[38],"the":[40,94,99,116,163,166,193],"experience":[41],"in":[42,81,144,179],"human-designed":[43],"and":[45,119,216],"heavily":[46],"rely":[47],"on":[48,73,207],"learning":[49],"from":[50,138],"meta-training":[51,184],"tasks,":[52],"therefore":[53],"limited":[55],"generalization":[56],"ability.":[57],"In":[58],"this":[59,139],"paper,":[60],"we":[61,147],"propose":[62],"novel":[64],"dubbed":[66],"as":[67,88,108,211],"Variational":[68,86,127,145,175,195],"HyperAdam,":[69,80,146],"is":[71,106,124,136,177],"based":[72],"parametric":[75],"generalized":[76,151],"Adam":[77,152],"algorithm,":[78],"i.e.,":[79],"variational":[83,188],"framework.":[84],"With":[85],"HyperAdam":[87,176,196],"optimizer":[89],"network,":[93],"parameter":[95,122,130,171],"update":[96,131,172],"vector":[97,123,132],"network":[101,121,134,199],"at":[102],"each":[103],"step":[105],"considered":[107],"random":[109],"variable,":[110],"whose":[111],"approximate":[112,140,167],"posterior":[113,141,168],"distribution":[114,169],"given":[115],"data":[118],"current":[120],"predicted":[125],"by":[126,187],"HyperAdam.":[128],"The":[129,174],"sampled":[137],"distribution.":[142],"Specifically,":[143],"design":[148],"learnable":[150],"algorithm":[153],"estimating":[155,162],"expectation,":[156],"paired":[157],"with":[158,183],"VarBlock":[160],"variance":[164],"vector.":[173],"learned":[178,194],"meta-learning":[181],"loss":[185],"derived":[186],"inference.":[189],"Experiments":[190],"verify":[191],"that":[192],"state-of-the-art":[198],"various":[203],"types":[204],"networks":[206],"different":[208],"datasets,":[209],"such":[210],"multilayer":[212],"perceptron,":[213],"CNN,":[214],"LSTM":[215],"ResNet.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}