{"id":"https://openalex.org/W4320057462","doi":"https://doi.org/10.1145/3573834.3574539","title":"Layer-wise based Adabelief Optimization Algorithm for Deep Learning","display_name":"Layer-wise based Adabelief Optimization Algorithm for Deep Learning","publication_year":2022,"publication_date":"2022-11-25","ids":{"openalex":"https://openalex.org/W4320057462","doi":"https://doi.org/10.1145/3573834.3574539"},"language":"en","primary_location":{"id":"doi:10.1145/3573834.3574539","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573834.3574539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Advanced Information Science and System","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5040931409","display_name":"Zhi\u2010Yong Qiu","orcid":"https://orcid.org/0000-0002-2488-0060"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Qiu","raw_affiliation_strings":["State Key Laboratory of High-end Server and Storage Technology, Shandong massive information technology research institute, China"],"raw_orcid":"https://orcid.org/0000-0002-2488-0060","affiliations":[{"raw_affiliation_string":"State Key Laboratory of High-end Server and Storage Technology, Shandong massive information technology research institute, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055656398","display_name":"Zhenhua Guo","orcid":"https://orcid.org/0000-0002-1303-6681"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenhua Guo","raw_affiliation_strings":["State Key Laboratory of High-end Server and Storage Technology, Shandong massive information technology research institute, China"],"raw_orcid":"https://orcid.org/0000-0002-1303-6681","affiliations":[{"raw_affiliation_string":"State Key Laboratory of High-end Server and Storage Technology, Shandong massive information technology research institute, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077819187","display_name":"Li Wang","orcid":"https://orcid.org/0000-0003-3975-104X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Wang","raw_affiliation_strings":["State Key Laboratory of High-end Server and Storage Technology, Shandong massive information technology research institute, China"],"raw_orcid":"https://orcid.org/0000-0003-3975-104X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of High-end Server and Storage Technology, Shandong massive information technology research institute, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101568187","display_name":"Yaqian Zhao","orcid":"https://orcid.org/0000-0002-9170-0090"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqian Zhao","raw_affiliation_strings":["State Key Laboratory of High-end Server and Storage Technology, Inspur Electronic Information Industry Co., Ltd., China"],"raw_orcid":"https://orcid.org/0000-0002-9170-0090","affiliations":[{"raw_affiliation_string":"State Key Laboratory of High-end Server and Storage Technology, Inspur Electronic Information Industry Co., Ltd., China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064453711","display_name":"Rengang Li","orcid":"https://orcid.org/0000-0002-4297-4335"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rengang Li","raw_affiliation_strings":["State Key Laboratory of High-end Server and Storage Technology, Inspur Electronic Information Industry Co., Ltd., China"],"raw_orcid":"https://orcid.org/0000-0002-4297-4335","affiliations":[{"raw_affiliation_string":"State Key Laboratory of High-end Server and Storage Technology, Inspur Electronic Information Industry Co., Ltd., China","institution_ids":["https://openalex.org/I4210144143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9980999827384949,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.995199978351593,"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/convergence","display_name":"Convergence (economics)","score":0.7034135460853577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6636292934417725},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6334450244903564},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5771123170852661},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5750730633735657},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5240818858146667},{"id":"https://openalex.org/keywords/optimization-algorithm","display_name":"Optimization algorithm","score":0.5225583910942078},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5059594511985779},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5054943561553955},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48427480459213257},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4616239666938782},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4332638382911682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4016832113265991},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2023814618587494},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.08411166071891785},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.050222039222717285}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7034135460853577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6636292934417725},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6334450244903564},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5771123170852661},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5750730633735657},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5240818858146667},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.5225583910942078},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5059594511985779},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5054943561553955},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48427480459213257},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4616239666938782},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4332638382911682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4016832113265991},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2023814618587494},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.08411166071891785},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.050222039222717285},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3573834.3574539","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573834.3574539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Advanced Information Science and System","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2146502635","https://openalex.org/W2155894447","https://openalex.org/W3037045207","https://openalex.org/W3170565703","https://openalex.org/W3173304480","https://openalex.org/W4221064450","https://openalex.org/W6601323341"],"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/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W2008149323"],"abstract_inverted_index":{"For":[0],"the":[1,18,36,44,50,71,76,86,91,101,105,110,114,118],"optimization":[2,13,32,39],"problem":[3],"of":[4,49,79,90,104],"deep":[5,37,51],"learning,":[6],"it":[7],"is":[8,54,109],"important":[9],"to":[10,34,62],"formulate":[11],"a":[12,28,64],"method":[14],"that":[15,73,100],"can":[16,74],"improve":[17],"convergence":[19,66,77,125],"rate":[20,58],"without":[21],"sacrificing":[22],"generalization":[23],"ability.":[24],"This":[25],"paper":[26],"proposes":[27],"layer-wise":[29],"based":[30],"Adabelief":[31],"algorithm":[33,93,108,120],"solve":[35],"learning":[38,57],"problems":[40],"more":[41],"efficiently.":[42],"In":[43],"proposed":[45,92],"algorithm,":[46],"each":[47],"layer":[48],"neural":[52],"network":[53],"set":[55],"different":[56],"appropriately":[59],"in":[60,127],"order":[61],"achieve":[63],"faster":[65],"rate.":[67],"We":[68],"also":[69,121],"give":[70],"theorems":[72],"guarantee":[75],"property":[78],"Layer-wised":[80],"AdaBelief":[81,107],"method.":[82],"Finally,":[83],"we":[84],"evaluate":[85],"effectiveness":[87],"and":[88],"efficiency":[89],"on":[94],"experimental":[95],"examples.":[96,130],"Experimental":[97],"results":[98],"show":[99],"converges":[102],"speed":[103],"layer-wised":[106],"fastest":[111],"compared":[112],"with":[113],"mainstream":[115],"algorithms.":[116],"Besides,":[117],"new":[119],"maintaining":[122],"an":[123],"excellent":[124],"result":[126],"all":[128],"numerical":[129]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}