{"id":"https://openalex.org/W2912290085","doi":"https://doi.org/10.1109/iwqos.2018.8624183","title":"Improved Adam Optimizer for Deep Neural Networks","display_name":"Improved Adam Optimizer for Deep Neural Networks","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2912290085","doi":"https://doi.org/10.1109/iwqos.2018.8624183","mag":"2912290085"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos.2018.8624183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos.2018.8624183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"},"type":"article","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/A5100764713","display_name":"Zijun Zhang","orcid":"https://orcid.org/0000-0002-2717-5033"},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Zijun Zhang","raw_affiliation_strings":["Department of Computer Science, University of Calgary"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Calgary","institution_ids":["https://openalex.org/I168635309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100764713"],"corresponding_institution_ids":["https://openalex.org/I168635309"],"apc_list":null,"apc_paid":null,"fwci":37.0582,"has_fulltext":false,"cited_by_count":1328,"citation_normalized_percentile":{"value":0.99755761,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9990000128746033,"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":0.9984999895095825,"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/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.812470555305481},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7723993062973022},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.7618544101715088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7087217569351196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6432485580444336},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.6294058561325073},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5600345730781555},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.48714348673820496},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.45934444665908813},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.434109628200531},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38965222239494324},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1976412832736969}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.812470555305481},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7723993062973022},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7618544101715088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7087217569351196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6432485580444336},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6294058561325073},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5600345730781555},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.48714348673820496},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.45934444665908813},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.434109628200531},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38965222239494324},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1976412832736969},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos.2018.8624183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos.2018.8624183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1522301498","https://openalex.org/W2097117768","https://openalex.org/W2146502635","https://openalex.org/W2194775991","https://openalex.org/W2401231614","https://openalex.org/W2619516334","https://openalex.org/W2682189153","https://openalex.org/W2752782242","https://openalex.org/W2912811302","https://openalex.org/W2963096987","https://openalex.org/W2963208657","https://openalex.org/W2963420686","https://openalex.org/W2964121744","https://openalex.org/W2964137095","https://openalex.org/W3137695714","https://openalex.org/W6681435938","https://openalex.org/W6738491991","https://openalex.org/W6763485134"],"related_works":["https://openalex.org/W3021529903","https://openalex.org/W4300326282","https://openalex.org/W2742395793","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W2810018382","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668"],"abstract_inverted_index":{"Adaptive":[0],"optimization":[1,11,128],"algorithms,":[2],"such":[3],"as":[4],"Adam":[5,50,60,71],"and":[6,55,80,117],"RMSprop,":[7],"have":[8],"witnessed":[9],"better":[10,131],"performance":[12,32,102],"than":[13,33,53,132],"stochastic":[14],"gradient":[15],"descent":[16],"(SGD)":[17],"in":[18,103],"some":[19],"scenarios.":[20],"However,":[21],"recent":[22],"studies":[23],"show":[24],"that":[25,49],"they":[26],"often":[27],"lead":[28],"to":[29,61,88,122],"worse":[30,52],"generalization":[31,64,91,101],"SGD,":[34,54],"especially":[35],"for":[36,83],"training":[37],"deep":[38],"neural":[39],"networks":[40],"(DNNs).":[41],"In":[42],"this":[43],"work,":[44],"we":[45,97,119],"identify":[46],"the":[47,63,78,100,108,113],"reasons":[48],"generalizes":[51],"develop":[56],"a":[57,94],"variant":[58],"of":[59,77],"eliminate":[62],"gap.":[65],"The":[66],"proposed":[67],"method,":[68],"normalized":[69],"direction-preserving":[70],"(ND-Adam),":[72],"enables":[73],"more":[74],"precise":[75],"control":[76],"direction":[79],"step":[81],"size":[82],"updating":[84],"weight":[85],"vectors,":[86],"leading":[87],"significantly":[89],"improved":[90],"performance.":[92],"Following":[93],"similar":[95],"rationale,":[96],"further":[98],"improve":[99],"classification":[104],"tasks":[105],"by":[106],"regularizing":[107],"softmax":[109],"logits.":[110],"By":[111],"bridging":[112],"gap":[114],"between":[115],"SGD":[116],"Adam,":[118],"also":[120],"hope":[121],"shed":[123],"light":[124],"on":[125],"why":[126],"certain":[127],"algorithms":[129],"generalize":[130],"others.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":32},{"year":2025,"cited_by_count":296},{"year":2024,"cited_by_count":312},{"year":2023,"cited_by_count":266},{"year":2022,"cited_by_count":203},{"year":2021,"cited_by_count":148},{"year":2020,"cited_by_count":62},{"year":2019,"cited_by_count":9}],"updated_date":"2026-04-20T07:46:08.049788","created_date":"2025-10-10T00:00:00"}