{"id":"https://openalex.org/W2905519666","doi":"https://doi.org/10.1609/aaai.v33i01.33019348","title":"Calibrated Stochastic Gradient Descent for Convolutional Neural Networks","display_name":"Calibrated Stochastic Gradient Descent for Convolutional Neural Networks","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2905519666","doi":"https://doi.org/10.1609/aaai.v33i01.33019348","mag":"2905519666"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33019348","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019348","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4973/4846","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4973/4846","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020995962","display_name":"Li\u2019an Zhuo","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li\u2019an Zhuo","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015525872","display_name":"Baochang Zhang","orcid":"https://orcid.org/0000-0001-7396-6218"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baochang Zhang","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418568","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-3957-7061"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["University of North Carolina at Charlotte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015317495","display_name":"Qixiang Ye","orcid":null},"institutions":[{"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":false,"raw_author_name":"Qixiang Ye","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039205892","display_name":"Jianzhuang Liu","orcid":"https://orcid.org/0000-0002-7960-9382"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianzhuang Liu","raw_affiliation_strings":["Huawei Technologies Company, Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Company, Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003875781","display_name":"David Doermann","orcid":"https://orcid.org/0000-0003-1639-4561"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Doermann","raw_affiliation_strings":["State University of New York at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"9348","last_page":"9355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9994999766349792,"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":0.9983000159263611,"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":0.7889928817749023},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.726421058177948},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6947374939918518},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.6814136505126953},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6211105585098267},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5630114674568176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.53407222032547},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5238751769065857},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.4561462104320526},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.4435006380081177},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4107590615749359},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39451873302459717},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36888939142227173},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3560123145580292},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1730956733226776}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.7889928817749023},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.726421058177948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6947374939918518},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.6814136505126953},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6211105585098267},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5630114674568176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.53407222032547},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5238751769065857},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.4561462104320526},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.4435006380081177},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4107590615749359},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39451873302459717},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36888939142227173},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3560123145580292},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1730956733226776},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33019348","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019348","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4973/4846","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4973","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33019348","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019348","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4973/4846","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1295000622","display_name":null,"funder_award_id":"61836012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2470178619","display_name":null,"funder_award_id":"61473086","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3038207137","display_name":null,"funder_award_id":"61672079","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G74207617","display_name":null,"funder_award_id":"KQTD2016112515134654","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8412823565","display_name":null,"funder_award_id":"KQTD2016112515134654","funder_id":"https://openalex.org/F4320335790","funder_display_name":"Shenzhen Peacock Plan"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326873","display_name":"National Laboratory of Pattern Recognition","ror":null},{"id":"https://openalex.org/F4320335790","display_name":"Shenzhen Peacock Plan","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2905519666.pdf","grobid_xml":"https://content.openalex.org/works/W2905519666.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1980287119","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2146989110","https://openalex.org/W2161758346","https://openalex.org/W2162931300","https://openalex.org/W2163605009","https://openalex.org/W2167090521","https://openalex.org/W2194775991","https://openalex.org/W2259167532","https://openalex.org/W2263490141","https://openalex.org/W2401231614","https://openalex.org/W2523246573","https://openalex.org/W2549139847","https://openalex.org/W2610018085","https://openalex.org/W2613718673","https://openalex.org/W2751791039","https://openalex.org/W2903382683","https://openalex.org/W2962685744","https://openalex.org/W2963586744","https://openalex.org/W2963675378","https://openalex.org/W2963749936","https://openalex.org/W2963804082","https://openalex.org/W2964121744","https://openalex.org/W2964137095","https://openalex.org/W2997680707","https://openalex.org/W3118608800","https://openalex.org/W4239072543","https://openalex.org/W4297781872","https://openalex.org/W6631190155","https://openalex.org/W6638803421","https://openalex.org/W6676297131","https://openalex.org/W6713132643","https://openalex.org/W6757107679"],"related_works":["https://openalex.org/W3008580913","https://openalex.org/W2896628485","https://openalex.org/W1701967867","https://openalex.org/W4315785049","https://openalex.org/W2115605526","https://openalex.org/W3015792155","https://openalex.org/W3093883775","https://openalex.org/W1539246760","https://openalex.org/W2786746258","https://openalex.org/W4225893763"],"abstract_inverted_index":{"In":[0,96],"stochastic":[1,30],"gradient":[2,10,21,31,73,102],"descent":[3,32],"(SGD)":[4],"and":[5,140,156],"its":[6],"variants,":[7],"the":[8,19,51,63,86,92,128,158],"optimized":[9],"estimators":[11],"may":[12],"be":[13,55,107],"as":[14,18],"expensive":[15],"to":[16,44,90,110],"compute":[17],"true":[20],"in":[22,57,85],"many":[23],"scenarios.":[24],"This":[25,144],"paper":[26],"introduces":[27],"a":[28,58,78,100],"calibrated":[29],"(CSGD)":[33],"algorithm":[34],"for":[35,50,81,131,150],"deep":[36,87],"neural":[37,113],"network":[38,52],"optimization.":[39],"A":[40],"theorem":[41],"is":[42,68],"developed":[43],"prove":[45],"that":[46,119],"an":[47],"unbiased":[48,82],"estimator":[49],"variables":[53],"can":[54,106,126],"obtained":[56],"probabilistic":[59],"way":[60],"based":[61],"on":[62],"Lipschitz":[64],"hypothesis.":[65],"Our":[66],"work":[67,145],"significantly":[69],"distinct":[70],"from":[71],"existing":[72],"optimization":[74,124],"methods,":[75],"by":[76],"providing":[77],"theoretical":[79],"framework":[80],"variable":[83],"estimation":[84],"learning":[88],"paradigm":[89],"optimize":[91],"model":[93],"parameter":[94],"calculation.":[95],"particular,":[97],"we":[98],"develop":[99],"generic":[101],"calibration":[103],"layer":[104],"which":[105],"easily":[108],"used":[109],"build":[111],"convolutional":[112],"networks":[114],"(CNNs).":[115],"Experimental":[116],"results":[117],"demonstrate":[118],"CNNs":[120],"with":[121],"our":[122],"CSGD":[123],"scheme":[125],"improve":[127],"stateof-the-art":[129],"performance":[130],"natural":[132],"image":[133],"classification,":[134,139],"digit":[135],"recognition,":[136],"ImageNet":[137],"object":[138,141],"detection":[142],"tasks.":[143],"opens":[146],"new":[147],"research":[148],"directions":[149],"developing":[151],"more":[152],"efficient":[153],"SGD":[154],"updates":[155],"analyzing":[157],"backpropagation":[159],"algorithm.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}