{"id":"https://openalex.org/W3035386872","doi":"https://doi.org/10.1109/icme46284.2020.9102970","title":"Rethinking The Pid Optimizer For Stochastic Optimization Of Deep Networks","display_name":"Rethinking The Pid Optimizer For Stochastic Optimization Of Deep Networks","publication_year":2020,"publication_date":"2020-06-09","ids":{"openalex":"https://openalex.org/W3035386872","doi":"https://doi.org/10.1109/icme46284.2020.9102970","mag":"3035386872"},"language":"en","primary_location":{"id":"doi:10.1109/icme46284.2020.9102970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100658547","display_name":"Lei Shi","orcid":"https://orcid.org/0000-0002-1965-2602"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Shi","raw_affiliation_strings":["NLPR & AIRIA, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR & AIRIA, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114686064","display_name":"Yifan Zhang","orcid":"https://orcid.org/0000-0002-9190-3509"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Zhang","raw_affiliation_strings":["NLPR & AIRIA, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR & AIRIA, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113868886","display_name":"Wanguo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanguo Wang","raw_affiliation_strings":["State Grid Intelligence Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Intelligence Technology Co., Ltd","institution_ids":["https://openalex.org/I17442442"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112149353","display_name":"Jian Cheng","orcid":"https://orcid.org/0000-0003-1289-2758"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Cheng","raw_affiliation_strings":["NLPR & AIRIA, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR & AIRIA, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100511737","display_name":"Hanqing Lu","orcid":"https://orcid.org/0000-0001-9506-3407"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanqing Lu","raw_affiliation_strings":["NLPR & AIRIA, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR & AIRIA, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9789,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.78130068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9977999925613403,"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/pid-controller","display_name":"PID controller","score":0.8263270854949951},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7717344760894775},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.6657745838165283},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6465153694152832},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6301256418228149},{"id":"https://openalex.org/keywords/overshoot","display_name":"Overshoot (microwave communication)","score":0.5963975191116333},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.5832682847976685},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5759120583534241},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5654580593109131},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.49814391136169434},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4981226921081543},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.48147574067115784},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4386964440345764},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.4322391450405121},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3233208656311035},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2631072700023651},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13314715027809143},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.12195387482643127},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11375981569290161},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07566478848457336},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.06669461727142334}],"concepts":[{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.8263270854949951},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7717344760894775},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6657745838165283},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6465153694152832},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6301256418228149},{"id":"https://openalex.org/C2780323453","wikidata":"https://www.wikidata.org/wiki/Q7113957","display_name":"Overshoot (microwave communication)","level":2,"score":0.5963975191116333},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.5832682847976685},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5759120583534241},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5654580593109131},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.49814391136169434},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4981226921081543},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.48147574067115784},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4386964440345764},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.4322391450405121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3233208656311035},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2631072700023651},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13314715027809143},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.12195387482643127},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11375981569290161},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07566478848457336},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.06669461727142334},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme46284.2020.9102970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","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":32,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W104184427","https://openalex.org/W1522301498","https://openalex.org/W2071345726","https://openalex.org/W2124450277","https://openalex.org/W2132211083","https://openalex.org/W2134282505","https://openalex.org/W2140246545","https://openalex.org/W2146502635","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2619516334","https://openalex.org/W2798391154","https://openalex.org/W2898987415","https://openalex.org/W2948058585","https://openalex.org/W2948246283","https://openalex.org/W2963177640","https://openalex.org/W2963208657","https://openalex.org/W2963446712","https://openalex.org/W2964121744","https://openalex.org/W2964137095","https://openalex.org/W2980070341","https://openalex.org/W6600284362","https://openalex.org/W6604254268","https://openalex.org/W6631190155","https://openalex.org/W6666877243","https://openalex.org/W6681435938","https://openalex.org/W6684191040","https://openalex.org/W6698183232","https://openalex.org/W6725739302","https://openalex.org/W6738491991"],"related_works":["https://openalex.org/W4293868274","https://openalex.org/W4386412075","https://openalex.org/W2698567378","https://openalex.org/W4389515241","https://openalex.org/W2810278913","https://openalex.org/W2110981444","https://openalex.org/W4315785049","https://openalex.org/W3015792155","https://openalex.org/W2547959363","https://openalex.org/W2588803791"],"abstract_inverted_index":{"Stochastic":[0],"gradient":[1,53],"descent":[2,54],"with":[3,31,122],"momentum":[4,18],"(SGD-Momentum)":[5],"always":[6],"causes":[7],"the":[8,13,17,28,32,38,43,46,51,75,78,90,96,99,111,131],"overshoot":[9,29,91],"problem":[10,30],"due":[11],"to":[12,26,86,109],"integral":[14],"action":[15],"of":[16,34,45,77,98,133],"term.":[19],"Recently,":[20],"an":[21],"ID":[22],"optimizer":[23,137],"is":[24],"proposed":[25,108,135],"solve":[27],"help":[33],"derivative":[35,39],"information.":[36],"However,":[37],"term":[40,80,85],"suffers":[41],"from":[42],"interference":[44,97],"high-frequency":[47,100],"noise,":[48,101],"especially":[49],"for":[50],"stochastic":[52],"method":[55],"that":[56],"uses":[57],"minibatch":[58],"data":[59],"in":[60],"each":[61],"update":[62],"step.":[63],"In":[64],"this":[65],"work,":[66],"we":[67],"propose":[68],"a":[69,83],"complete":[70],"PID":[71,136],"optimizer,":[72],"which":[73],"weakens":[74],"effect":[76],"D":[79],"and":[81,104,128],"adds":[82],"P":[84],"more":[87],"stably":[88],"alleviate":[89],"problem.":[92],"To":[93],"further":[94],"reduce":[95],"two":[102],"effective":[103],"efficient":[105],"methods":[106],"are":[107],"stabilize":[110],"training":[112],"process.":[113],"Extensive":[114],"experiments":[115],"on":[116,138],"three":[117],"widely":[118],"used":[119],"benchmark":[120],"datasets":[121],"different":[123],"scales,":[124],"i.e.,":[125],"MNIST,":[126],"Cifar10":[127],"TinyImageNet,":[129],"demonstrate":[130],"superiority":[132],"our":[134],"various":[139],"popular":[140],"deep":[141],"neural":[142],"networks.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}