{"id":"https://openalex.org/W2793290155","doi":"https://doi.org/10.1109/vcip.2017.8305126","title":"Exponential decay sine wave learning rate for fast deep neural network training","display_name":"Exponential decay sine wave learning rate for fast deep neural network training","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2793290155","doi":"https://doi.org/10.1109/vcip.2017.8305126","mag":"2793290155"},"language":"en","primary_location":{"id":"doi:10.1109/vcip.2017.8305126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip.2017.8305126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Visual Communications and Image Processing (VCIP)","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/A5059454224","display_name":"Wangpeng An","orcid":"https://orcid.org/0000-0002-1869-1837"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wangpeng An","raw_affiliation_strings":["Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","Shenzhen Institute of Future Media Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen Institute of Future Media Technology, Shenzhen, China","institution_ids":["https://openalex.org/I158809036"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028229824","display_name":"Haoqian Wang","orcid":"https://orcid.org/0000-0003-2792-8469"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqian Wang","raw_affiliation_strings":["Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","Shenzhen Institute of Future Media Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen Institute of Future Media Technology, Shenzhen, China","institution_ids":["https://openalex.org/I158809036"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074865219","display_name":"Yulun Zhang","orcid":"https://orcid.org/0000-0002-2288-5079"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulun Zhang","raw_affiliation_strings":["Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","Shenzhen Institute of Future Media Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen Institute of Future Media Technology, Shenzhen, China","institution_ids":["https://openalex.org/I158809036"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080722708","display_name":"Qionghai Dai","orcid":"https://orcid.org/0000-0001-7043-3061"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qionghai Dai","raw_affiliation_strings":["Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","Shenzhen Institute of Future Media Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen Institute of Future Media Technology, Shenzhen, China","institution_ids":["https://openalex.org/I158809036"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059454224"],"corresponding_institution_ids":["https://openalex.org/I158809036","https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.3653,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.89018325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/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/T11689","display_name":"Adversarial Robustness in Machine Learning","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/sine-wave","display_name":"Sine wave","score":0.636389970779419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6280599236488342},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6222553253173828},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6075283288955688},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5854722261428833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5775958895683289},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5254756212234497},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5088346600532532},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5074352622032166},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4739782214164734},{"id":"https://openalex.org/keywords/exponential-decay","display_name":"Exponential decay","score":0.47024431824684143},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.45842161774635315},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3960941731929779},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37003064155578613},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1135164201259613}],"concepts":[{"id":"https://openalex.org/C66907618","wikidata":"https://www.wikidata.org/wiki/Q207527","display_name":"Sine wave","level":3,"score":0.636389970779419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6280599236488342},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6222553253173828},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6075283288955688},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5854722261428833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5775958895683289},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5254756212234497},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5088346600532532},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5074352622032166},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4739782214164734},{"id":"https://openalex.org/C180188523","wikidata":"https://www.wikidata.org/wiki/Q574576","display_name":"Exponential decay","level":2,"score":0.47024431824684143},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.45842161774635315},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3960941731929779},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37003064155578613},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1135164201259613},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185544564","wikidata":"https://www.wikidata.org/wiki/Q81197","display_name":"Nuclear physics","level":1,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/vcip.2017.8305126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip.2017.8305126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Visual Communications and Image Processing (VCIP)","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":20,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W104184427","https://openalex.org/W114517082","https://openalex.org/W1522301498","https://openalex.org/W1980287119","https://openalex.org/W2051434435","https://openalex.org/W2143612262","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2331143823","https://openalex.org/W2964054038","https://openalex.org/W2964121744","https://openalex.org/W2964137095","https://openalex.org/W3118608800","https://openalex.org/W6604254268","https://openalex.org/W6631190155","https://openalex.org/W6684191040","https://openalex.org/W6698183232","https://openalex.org/W6713132643"],"related_works":["https://openalex.org/W2955229517","https://openalex.org/W2966297898","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668","https://openalex.org/W3008318776","https://openalex.org/W1977633006"],"abstract_inverted_index":{"Most":[0],"state-of-the-art":[1],"results":[2],"on":[3,167],"image":[4],"classification":[5],"tasks":[6],"were":[7],"obtained":[8],"by":[9,30],"residual":[10,155],"neural":[11,97,189],"networks,":[12],"which":[13,91],"use":[14],"stochastic":[15],"gradient":[16,75],"descent":[17],"(SGD)":[18],"with":[19,148,157],"momentum":[20],"for":[21,95,117],"training.":[22,99],"In":[23,100,124],"most":[24,183],"cases,":[25],"the":[26,52,70,125,128,138],"learning":[27,53,60,79,87,114,129,160,185],"rate":[28,61,80,115,130,186],"drops":[29],"a":[31,83,105],"constant":[32],"factor":[33],"every":[34],"pre-defined":[35],"number":[36,179],"of":[37,86,90,141,153,180],"epochs.":[38,150],"However,":[39],"it":[40],"is":[41,62],"difficult":[42],"and":[43,164,169],"time-consuming":[44],"to":[45,50,68,119],"estimate":[46],"how":[47],"many":[48],"epochs":[49,181],"drop":[51],"rate.":[54],"To":[55],"tackle":[56],"this":[57,101],"problem,":[58],"cyclical":[59,78],"gaining":[63],"popularity":[64],"in":[65,73,133],"gradient-based":[66],"optimization":[67],"improve":[69,120],"convergence":[71,122],"speed":[72],"accelerated":[74],"schemes.":[76],"But":[77],"scheme":[81,161],"scans":[82],"broad":[84],"range":[85],"rate,":[88],"some":[89],"are":[92],"not":[93],"suitable":[94],"deep":[96],"network":[98,190],"paper,":[102],"we":[103],"propose":[104],"simple":[106],"yet":[107],"effective":[108],"exponential":[109],"decay":[110,145],"sine":[111,134,142],"wave":[112,135,143],"like":[113],"technique":[116],"SGD":[118],"its":[121],"speed.":[123],"training":[126,149,191],"process,":[127],"would":[131,144],"vary":[132],"way.":[136],"While":[137],"maximum":[139],"value":[140],"exponentially":[146],"along":[147],"An":[151],"ensemble":[152],"wide":[154],"nets":[156],"our":[158,173],"proposed":[159,174],"achieves":[162],"3.01%":[163],"16.03%":[165],"errors":[166],"CIFAR-10":[168],"CIFAR-100":[170],"respectively.":[171],"Furthermore,":[172],"method":[175],"uses":[176],"far":[177],"less":[178],"than":[182],"recent":[184],"strategies,":[187],"accelerating":[188],"tremendously.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}