{"id":"https://openalex.org/W2169322818","doi":"https://doi.org/10.1109/icdm.2010.26","title":"Averaged Stochastic Gradient Descent with Feedback: An Accurate, Robust, and Fast Training Method","display_name":"Averaged Stochastic Gradient Descent with Feedback: An Accurate, Robust, and Fast Training Method","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2169322818","doi":"https://doi.org/10.1109/icdm.2010.26","mag":"2169322818"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2010.26","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2010.26","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Data Mining","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/A5101441137","display_name":"Xu Sun","orcid":"https://orcid.org/0000-0001-8241-9320"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I4210165074","display_name":"Information and Mathematical Science and Bioinformatics (Japan)","ror":"https://ror.org/05rgpb984","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210165074"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Xu Sun","raw_affiliation_strings":["Department of Mathematical Informatics, University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Mathematical Informatics, University of Tokyo, Japan","institution_ids":["https://openalex.org/I4210165074","https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031707680","display_name":"Hisashi Kashima","orcid":"https://orcid.org/0000-0002-2770-0184"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I4210165074","display_name":"Information and Mathematical Science and Bioinformatics (Japan)","ror":"https://ror.org/05rgpb984","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210165074"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kashima","raw_affiliation_strings":["Department of Mathematical Informatics, University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Mathematical Informatics, University of Tokyo, Japan","institution_ids":["https://openalex.org/I4210165074","https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016823828","display_name":"Takuya Matsuzaki","orcid":"https://orcid.org/0000-0002-7425-4914"},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Matsuzaki","raw_affiliation_strings":["Department of Computer Science, University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974","https://openalex.org/I161296585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105268757","display_name":"Naonori Ueda","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naonori Ueda","raw_affiliation_strings":["NTT Communication Science Laboratories, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101441137"],"corresponding_institution_ids":["https://openalex.org/I4210165074","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":2.2552,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.8989617,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"9","issue":null,"first_page":"1067","last_page":"1072"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","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/T12072","display_name":"Machine Learning and Algorithms","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9990000128746033,"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/robustness","display_name":"Robustness (evolution)","score":0.8698645830154419},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.8319016695022583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7408077120780945},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.559079647064209},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5537531971931458},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5368853807449341},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45897454023361206},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4232966899871826},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12191945314407349}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8698645830154419},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8319016695022583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408077120780945},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.559079647064209},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5537531971931458},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5368853807449341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45897454023361206},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4232966899871826},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12191945314407349},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdm.2010.26","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2010.26","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Data Mining","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":22,"referenced_works":["https://openalex.org/W1568229137","https://openalex.org/W2008652694","https://openalex.org/W2047782770","https://openalex.org/W2099336098","https://openalex.org/W2109614908","https://openalex.org/W2117497855","https://openalex.org/W2125993116","https://openalex.org/W2131148434","https://openalex.org/W2132559980","https://openalex.org/W2132726600","https://openalex.org/W2142623206","https://openalex.org/W2145835757","https://openalex.org/W2150024778","https://openalex.org/W2168194229","https://openalex.org/W3029645440","https://openalex.org/W4237640996","https://openalex.org/W4293775970","https://openalex.org/W6676241556","https://openalex.org/W6680008805","https://openalex.org/W6681579763","https://openalex.org/W6682133467","https://openalex.org/W6684941630"],"related_works":["https://openalex.org/W2966297898","https://openalex.org/W2955229517","https://openalex.org/W2895097035","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W3020853991","https://openalex.org/W4362706668","https://openalex.org/W4231621013"],"abstract_inverted_index":{"On":[0],"large":[1],"datasets,":[2],"the":[3,29,37,49,56,61,70,79,84,87,99,102,110,127,132],"popular":[4],"training":[5,34,103],"approach":[6],"has":[7],"been":[8],"stochastic":[9,116],"gradient":[10,117],"descent":[11],"(SGD).":[12],"This":[13],"paper":[14],"proposes":[15],"a":[16,135],"modification":[17],"of":[18,83,95,113],"SGD,":[19,141],"called":[20],"averaged":[21,57],"SGD":[22,53,62],"with":[23],"feedback":[24,71],"(ASF),":[25],"that":[26],"significantly":[27],"improves":[28],"performance":[30],"(robustness,":[31],"accuracy,":[32,96],"and":[33,65,101,142],"speed)":[35],"over":[36,98],"traditional":[38],"SGD.":[39],"The":[40],"proposal":[41],"is":[42,109,134],"based":[43],"on":[44],"three":[45],"simple":[46],"ideas:":[47],"averaging":[48],"weight":[50],"vectors":[51],"across":[52],"iterations,":[54],"feeding":[55],"weights":[58],"back":[59],"into":[60],"update":[63],"process,":[64],"deciding":[66],"when":[67],"to":[68,147],"perform":[69],"(linearly":[72],"slowing":[73],"down":[74],"feedback).":[75],"Theoretically,":[76],"we":[77,120],"demonstrate":[78],"reasonable":[80],"convergence":[81],"properties":[82],"ASF.":[85],"Empirically,":[86],"ASF":[88,128,133],"outperforms":[89],"several":[90],"strong":[91],"baselines":[92],"in":[93,115,129],"terms":[94],"robustness":[97],"noise,":[100],"speed.":[104],"To":[105],"our":[106],"knowledge,":[107],"this":[108,130],"first":[111],"study":[112],"``feedback''":[114],"learning.":[118],"Although":[119],"choose":[121],"latent":[122],"conditional":[123],"models":[124],"for":[125],"verifying":[126],"paper,":[131],"general":[136],"purpose":[137],"technique":[138],"just":[139],"like":[140],"can":[143],"be":[144],"directly":[145],"applied":[146],"other":[148],"models.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}