{"id":"https://openalex.org/W3090595192","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207166","title":"On the Trend-corrected Variant of Adaptive Stochastic Optimization Methods","display_name":"On the Trend-corrected Variant of Adaptive Stochastic Optimization Methods","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3090595192","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207166","mag":"3090595192"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.06130","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027695625","display_name":"Bingxin Zhou","orcid":"https://orcid.org/0000-0002-3897-9766"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Bingxin Zhou","raw_affiliation_strings":["The University of Sydney Business School, The University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Sydney Business School, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019662747","display_name":"Xuebin Zheng","orcid":"https://orcid.org/0000-0002-1643-9937"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuebin Zheng","raw_affiliation_strings":["The University of Sydney Business School, The University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Sydney Business School, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015817857","display_name":"Junbin Gao","orcid":"https://orcid.org/0000-0001-9803-0256"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Junbin Gao","raw_affiliation_strings":["The University of Sydney Business School, The University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Sydney Business School, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027695625"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":0.2743,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64758948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"15","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9976999759674072,"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":0.7289514541625977},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5421906113624573},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.5386213660240173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5037619471549988},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.44821327924728394},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.4415859878063202},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4379371404647827},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4167899191379547},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4123392701148987},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37808388471603394},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34012144804000854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20181429386138916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289514541625977},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5421906113624573},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.5386213660240173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5037619471549988},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.44821327924728394},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.4415859878063202},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4379371404647827},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4167899191379547},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4123392701148987},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37808388471603394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34012144804000854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20181429386138916},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.06130","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.06130","pdf_url":"https://arxiv.org/pdf/2001.06130","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.06130","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.06130","pdf_url":"https://arxiv.org/pdf/2001.06130","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1491394602","https://openalex.org/W1520152940","https://openalex.org/W1522301498","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W1980287119","https://openalex.org/W2069729888","https://openalex.org/W2085866051","https://openalex.org/W2095705004","https://openalex.org/W2146502635","https://openalex.org/W2148825261","https://openalex.org/W2335728318","https://openalex.org/W2523246573","https://openalex.org/W2741924441","https://openalex.org/W2750384547","https://openalex.org/W2785523195","https://openalex.org/W2803323821","https://openalex.org/W2808042107","https://openalex.org/W2811507150","https://openalex.org/W2886294525","https://openalex.org/W2886463271","https://openalex.org/W2886837499","https://openalex.org/W2903382683","https://openalex.org/W2908510526","https://openalex.org/W2951992264","https://openalex.org/W2963563140","https://openalex.org/W2963698657","https://openalex.org/W2964121744","https://openalex.org/W2968917279","https://openalex.org/W2994689640","https://openalex.org/W4288265053","https://openalex.org/W6600284362","https://openalex.org/W6631190155","https://openalex.org/W6639732818","https://openalex.org/W6640963894","https://openalex.org/W6674330103","https://openalex.org/W6681435938","https://openalex.org/W6703116779","https://openalex.org/W6727249380","https://openalex.org/W6742042246","https://openalex.org/W6743688258","https://openalex.org/W6747620207","https://openalex.org/W6751579197","https://openalex.org/W6752663585","https://openalex.org/W6752775508","https://openalex.org/W6753170497","https://openalex.org/W6753272172","https://openalex.org/W6753892653","https://openalex.org/W6757107679","https://openalex.org/W6757817989","https://openalex.org/W6767164110"],"related_works":["https://openalex.org/W2357256365","https://openalex.org/W2348502264","https://openalex.org/W2365486383","https://openalex.org/W2362059367","https://openalex.org/W2350084742","https://openalex.org/W1975289146","https://openalex.org/W2901443725","https://openalex.org/W2357988862","https://openalex.org/W1855558850","https://openalex.org/W1852677413"],"abstract_inverted_index":{"Adam-type":[0,51],"optimizers,":[1],"as":[2],"a":[3,47],"class":[4],"of":[5,23,96],"adaptive":[6,63],"moment":[7],"estimation":[8],"methods":[9,27,52,110],"with":[10,38,53,61,116],"the":[11,32,54,59,62,72,79,85,94,98,105,113],"exponential":[12],"moving":[13],"average":[14],"scheme,":[15],"have":[16],"been":[17],"successfully":[18],"used":[19],"in":[20,71],"many":[21],"applications":[22],"deep":[24],"learning.":[25],"Such":[26],"are":[28],"appealing":[29],"due":[30],"to":[31],"capability":[33],"on":[34,78,112],"large-scale":[35],"sparse":[36],"datasets":[37],"high":[39],"computational":[40],"efficiency.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"present":[46],"new":[48],"framework":[49,103],"for":[50],"trend":[55,99],"information":[56],"when":[57],"updating":[58],"parameters":[60],"step":[64],"size":[65],"and":[66,83,108],"gradients.":[67],"The":[68],"additional":[69],"terms":[70],"algorithm":[73],"promise":[74],"an":[75],"efficient":[76],"movement":[77],"complex":[80],"cost":[81],"surface,":[82],"thus":[84],"loss":[86],"would":[87],"converge":[88],"more":[89],"rapidly.":[90],"We":[91],"show":[92],"empirically":[93],"importance":[95],"adding":[97],"component,":[100],"where":[101],"our":[102],"outperforms":[104],"conventional":[106],"Adam":[107],"AMSGrad":[109],"constantly":[111],"classical":[114],"models":[115],"several":[117],"real-world":[118],"datasets.":[119]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2020-10-08T00:00:00"}