{"id":"https://openalex.org/W7126403168","doi":"https://doi.org/10.1007/s40747-026-02226-2","title":"A general learning rate improvement strategy for deep neural networks training","display_name":"A general learning rate improvement strategy for deep neural networks training","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7126403168","doi":"https://doi.org/10.1007/s40747-026-02226-2"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-026-02226-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-026-02226-2","pdf_url":null,"source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s40747-026-02226-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tingting Wu","orcid":"https://orcid.org/0009-0003-6982-6994"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Wu","raw_affiliation_strings":["China Mobile Research Institute, Xicheng, Beijing, 100053, China"],"raw_orcid":"https://orcid.org/0009-0003-6982-6994","affiliations":[{"raw_affiliation_string":"China Mobile Research Institute, Xicheng, Beijing, 100053, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124683469","display_name":"Qingwei Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qingwei Dong","raw_affiliation_strings":["Key Laboratory of Networked Control Systems, Chinese Academy of Sciences, Shenyang, 110016, China","State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China","University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Networked Control Systems, Chinese Academy of Sciences, Shenyang, 110016, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124492189","display_name":"Wei Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Yu","raw_affiliation_strings":["China Mobile Research Institute, Xicheng, Beijing, 100053, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute, Xicheng, Beijing, 100053, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124499815","display_name":"Zheng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Li","raw_affiliation_strings":["China Mobile Research Institute, Xicheng, Beijing, 100053, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute, Xicheng, Beijing, 100053, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081185134","display_name":"Manxue Guo","orcid":"https://orcid.org/0000-0002-9522-0318"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Manxue Guo","raw_affiliation_strings":["China Mobile Research Institute, Xicheng, Beijing, 100053, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute, Xicheng, Beijing, 100053, China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5124683469"],"corresponding_institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366","https://openalex.org/I4210165038"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11795977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.26100000739097595,"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":0.26100000739097595,"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":0.2467000037431717,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.17560000717639923,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.6291000247001648},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.49380001425743103},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4564000070095062},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.45339998602867126},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4325999915599823},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4020000100135803},{"id":"https://openalex.org/keywords/adaptive-learning","display_name":"Adaptive learning","score":0.3921999931335449},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.3815000057220459},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.37940001487731934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246000170707703},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6291000247001648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.607200026512146},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5849000215530396},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.49380001425743103},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4564000070095062},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.32820001244544983},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C10431821","wikidata":"https://www.wikidata.org/wiki/Q6510174","display_name":"Learning effect","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-026-02226-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-026-02226-2","pdf_url":null,"source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2e55b590ba8f44f18df75eea9a7b507d","is_oa":true,"landing_page_url":"https://doaj.org/article/2e55b590ba8f44f18df75eea9a7b507d","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":"Complex & Intelligent Systems, Vol 12, Iss 3, Pp 1-17 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-026-02226-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-026-02226-2","pdf_url":null,"source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1806891645","https://openalex.org/W2117539524","https://openalex.org/W2465345967","https://openalex.org/W2963587345","https://openalex.org/W2964054038","https://openalex.org/W3007844454","https://openalex.org/W3035336589","https://openalex.org/W3124089710","https://openalex.org/W3149827756","https://openalex.org/W3197228570","https://openalex.org/W3201675503","https://openalex.org/W4382318707","https://openalex.org/W4390490845","https://openalex.org/W4392222230","https://openalex.org/W4404897708"],"related_works":[],"abstract_inverted_index":{"Learning":[0],"rate":[1,28,69,85,95,118,129,149],"is":[2],"the":[3,26,36,41,47,73,77,91,102,111,114,121,126,132,140,146],"most":[4],"important":[5],"parameter":[6],"for":[7],"neural":[8],"network":[9],"performance":[10,37,144],"optimization,":[11],"and":[12,15,54,142],"its":[13],"selection":[14],"theoretical":[16],"exploration":[17],"have":[18],"always":[19],"been":[20,31],"an":[21],"active":[22],"research":[23],"field.":[24],"Although":[25],"learning":[27,68,84,94,117,128,148],"scheduler":[29,70,119,130,150],"has":[30],"widely":[32],"observed":[33],"to":[34],"improve":[35],"of":[38,49,52,76,93,113,145,155],"model":[39],"training,":[40],"current":[42,133],"works":[43],"do":[44],"not":[45],"consider":[46],"characteristics":[48],"different":[50,74,97],"stages":[51,75,99],"training":[53,78,98],"are":[55],"mostly":[56],"incompatible":[57],"with":[58,125],"adaptive":[59,122],"optimizers.":[60,123],"In":[61,106],"this":[62],"work,":[63],"we":[64,108,137],"construct":[65],"a":[66,152],"general":[67,116],"based":[71],"on":[72,104,120,131],"process":[79],"\"warm-up":[80],"-":[81,86],"maintain":[82],"large":[83,153],"decay\",":[87],"which":[88],"can":[89],"meet":[90],"changes":[92],"in":[96],"while":[100],"reducing":[101],"dependence":[103],"hyperparameters.":[105],"addition,":[107],"theoretically":[109],"demonstrate":[110],"convergence":[112],"proposed":[115,147],"Compared":[124],"mainstream":[127],"common":[134],"data":[135],"sets,":[136],"comprehensively":[138],"evaluate":[139],"advanced":[141],"robust":[143],"through":[151],"number":[154],"experiments.":[156]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-02-02T00:00:00"}