{"id":"https://openalex.org/W3206466242","doi":"https://doi.org/10.1109/access.2021.3120749","title":"Unified Algorithm Framework for Nonconvex Stochastic Optimization in Deep Neural Networks","display_name":"Unified Algorithm Framework for Nonconvex Stochastic Optimization in Deep Neural Networks","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3206466242","doi":"https://doi.org/10.1109/access.2021.3120749","mag":"3206466242"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3120749","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3120749","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2021.3120749","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107828678","display_name":"Yini Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I16656306","display_name":"Meiji University","ror":"https://ror.org/02rqvrp93","country_code":"JP","type":"education","lineage":["https://openalex.org/I16656306"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yini Zhu","raw_affiliation_strings":["Computer Science Course, Graduate School of Science and Technology, Meiji University, Kawasaki-shi, Kanagawa, Japan","ORCiD"],"raw_orcid":"https://orcid.org/0000-0003-2607-4369","affiliations":[{"raw_affiliation_string":"Computer Science Course, Graduate School of Science and Technology, Meiji University, Kawasaki-shi, Kanagawa, Japan","institution_ids":["https://openalex.org/I16656306"]},{"raw_affiliation_string":"ORCiD","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016609320","display_name":"Hideaki Iiduka","orcid":"https://orcid.org/0000-0001-9173-6723"},"institutions":[{"id":"https://openalex.org/I16656306","display_name":"Meiji University","ror":"https://ror.org/02rqvrp93","country_code":"JP","type":"education","lineage":["https://openalex.org/I16656306"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideaki Iiduka","raw_affiliation_strings":["Department of Computer Science, Meiji University, Kawasaki-shi, Kanagawa, Japan","ORCiD"],"raw_orcid":"https://orcid.org/0000-0001-9173-6723","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Meiji University, Kawasaki-shi, Kanagawa, Japan","institution_ids":["https://openalex.org/I16656306"]},{"raw_affiliation_string":"ORCiD","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16656306"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.3904,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70201734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"9","issue":null,"first_page":"143807","last_page":"143823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","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/T12676","display_name":"Machine Learning and ELM","score":0.9991000294685364,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.603805422782898},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5464673042297363},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5114923715591431},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.509975790977478},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.4891207814216614},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4817781150341034},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4749305844306946},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4546719789505005},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.4461633563041687},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.4439803659915924},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4415474236011505},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.42084503173828125},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.4184167981147766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3445190191268921},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2862088084220886},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.07570764422416687}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.603805422782898},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5464673042297363},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5114923715591431},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.509975790977478},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.4891207814216614},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4817781150341034},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4749305844306946},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4546719789505005},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4461633563041687},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.4439803659915924},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4415474236011505},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.42084503173828125},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.4184167981147766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3445190191268921},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2862088084220886},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.07570764422416687},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3120749","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3120749","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9d62f92093c84b2ca7bc1d16406ced08","is_oa":true,"landing_page_url":"https://doaj.org/article/9d62f92093c84b2ca7bc1d16406ced08","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 143807-143823 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3120749","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3120749","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5366413431","display_name":"Riemannian Fixed Point Optimization Algorithm and Its Application to Machine Learning","funder_award_id":"21K11773","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2026267944","https://openalex.org/W2117595234","https://openalex.org/W2146502635","https://openalex.org/W2168081761","https://openalex.org/W2557283755","https://openalex.org/W2605396865","https://openalex.org/W2785523195","https://openalex.org/W2889545660","https://openalex.org/W2947705626","https://openalex.org/W2949935872","https://openalex.org/W2954796449","https://openalex.org/W2963563140","https://openalex.org/W2964121744","https://openalex.org/W3034547948","https://openalex.org/W3100197791","https://openalex.org/W3103900341","https://openalex.org/W3113153429","https://openalex.org/W3121184178","https://openalex.org/W3197228570","https://openalex.org/W4287864992","https://openalex.org/W6631190155","https://openalex.org/W6681435938","https://openalex.org/W6747620207","https://openalex.org/W6753892653","https://openalex.org/W6757751764","https://openalex.org/W6774569997","https://openalex.org/W6784591795","https://openalex.org/W6786291537"],"related_works":["https://openalex.org/W2913271688","https://openalex.org/W4286899070","https://openalex.org/W4323366756","https://openalex.org/W3207830353","https://openalex.org/W4285259204","https://openalex.org/W3109737792","https://openalex.org/W3109198354","https://openalex.org/W937081240","https://openalex.org/W2760303966","https://openalex.org/W4401866412"],"abstract_inverted_index":{"This":[0],"paper":[1,72,148],"presents":[2],"a":[3,89,97,101,108,114,190],"unified":[4,20,79,155,177,196],"algorithmic":[5],"framework":[6],"for":[7,81,169],"nonconvex":[8,102,137],"stochastic":[9,103,138],"optimization,":[10],"which":[11],"is":[12],"needed":[13],"to":[14,113,124,136],"train":[15,158],"deep":[16,141,159],"neural":[17,142,160],"networks.":[18],"The":[19,71,185],"algorithm":[21,80,94,156,178,193,197],"includes":[22],"the":[23,65,78,93,118,121,125,128,154,176,195],"existing":[24,129],"adaptive-learning-rate":[25,130],"optimization":[26,104,131,139,183,192],"algorithms,":[27],"such":[28],"as":[29],"Adaptive":[30,34],"Moment":[31],"Estimation":[32],"(Adam),":[33],"Mean":[35],"Square":[36],"Gradient":[37],"(AMSGrad),":[38],"Adam":[39],"with":[40,51,179],"weighted":[41,52],"gradient":[42,53],"and":[43,54,61,83,194],"dynamic":[44,55],"bound":[45,56],"of":[46,57,77,100,117,175],"learning":[47,58,85,91],"rate":[48,59],"(GWDC),":[49],"AMSGrad":[50],"(AMSGWDC),":[60],"Adapting":[62],"stepsizes":[63],"by":[64],"belief":[66],"in":[67,140,144,162],"observed":[68],"gradients":[69],"(AdaBelief).":[70],"also":[73],"gives":[74],"convergence":[75],"analyses":[76,122],"constant":[82,90],"diminishing":[84,109],"rates.":[86],"When":[87,106],"using":[88,107,172],"rate,":[92,110],"can":[95,133,157],"approximate":[96],"stationary":[98,115],"point":[99,116],"problem.":[105,119],"it":[111,165],"converges":[112],"Hence,":[120],"lead":[123],"finding":[126],"that":[127,153,189],"algorithms":[132],"be":[134],"applied":[135],"networks":[143,161],"theory.":[145],"Additionally,":[146],"this":[147],"provides":[149,166],"numerical":[150,167,186],"results":[151],"showing":[152],"practice.":[163],"Moreover,":[164],"comparisons":[168,187],"unconstrained":[170],"minimization":[171],"benchmark":[173],"functions":[174],"certain":[180],"heuristic":[181],"intelligent":[182],"algorithms.":[184],"show":[188],"teaching-learning-based":[191],"perform":[198],"well.":[199]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}