{"id":"https://openalex.org/W2995059005","doi":"https://doi.org/10.1109/tencon.2019.8929465","title":"Polynomial Learning Rate Policy with Warm Restart for Deep Neural Network","display_name":"Polynomial Learning Rate Policy with Warm Restart for Deep Neural Network","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2995059005","doi":"https://doi.org/10.1109/tencon.2019.8929465","mag":"2995059005"},"language":"en","primary_location":{"id":"doi:10.1109/tencon.2019.8929465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon.2019.8929465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON)","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/A5032671035","display_name":"Purnendu Mishra","orcid":"https://orcid.org/0000-0003-2060-8972"},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289"]},{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Purnendu Mishra","raw_affiliation_strings":["Department of Electronics Engineering, Indian Institute of Technology (BHU), Varanasi, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Indian Institute of Technology (BHU), Varanasi, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054081739","display_name":"Kishor Sarawadekar","orcid":"https://orcid.org/0000-0001-8230-6481"},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289"]},{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kishor Sarawadekar","raw_affiliation_strings":["Department of Electronics Engineering, Indian Institute of Technology (BHU), Varanasi, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Indian Institute of Technology (BHU), Varanasi, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032671035"],"corresponding_institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"],"apc_list":null,"apc_paid":null,"fwci":3.6788,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.94675688,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2087","last_page":"2092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9973999857902527,"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":0.9957000017166138,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.6506953239440918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.600782036781311},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5386161208152771},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.5021419525146484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48035725951194763},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.41813135147094727},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27212220430374146}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6506953239440918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.600782036781311},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5386161208152771},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.5021419525146484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48035725951194763},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.41813135147094727},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27212220430374146},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tencon.2019.8929465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon.2019.8929465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON)","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/W1677182931","https://openalex.org/W1772464306","https://openalex.org/W1817277359","https://openalex.org/W1910131649","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2184045248","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2342840547","https://openalex.org/W2401231614","https://openalex.org/W2412782625","https://openalex.org/W2570343428","https://openalex.org/W2963263347","https://openalex.org/W2964054038","https://openalex.org/W2964137095","https://openalex.org/W3118608800","https://openalex.org/W6637940777","https://openalex.org/W6684191040","https://openalex.org/W6726497184"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W3086377361"],"abstract_inverted_index":{"Learning":[0],"rate":[1,59,85,92,107,147],"(LR)":[2],"is":[3,42,70,109,127,142,184],"one":[4],"of":[5,22,28,39,46,66,74,102,167,179],"the":[6,20,26,53,57,71,76,105,168,180],"most":[7],"important":[8],"hyper-parameters":[9],"in":[10,52,111,164],"any":[11],"deep":[12],"neural":[13],"network":[14,23],"(DNN)":[15],"optimization":[16],"process.":[17],"It":[18],"controls":[19],"speed":[21],"convergence":[24,166],"to":[25],"point":[27],"global":[29],"minima":[30],"by":[31,44,60,129],"navigation":[32],"through":[33],"non-convex":[34],"loss":[35,54],"surface.":[36,55],"The":[37,139,159,177],"performance":[38,178],"a":[40,61,112,155],"DNN":[41,169],"affected":[43],"presence":[45],"local":[47],"minima,":[48],"saddle":[49],"points,":[50],"etc.":[51],"Decaying":[56],"learning":[58,84,91,106,146],"factor":[62],"at":[63],"fixed":[64],"number":[65],"epochs":[67],"or":[68],"exponentially":[69],"conventional":[72],"way":[73],"varying":[75],"LR.":[77],"Recently,":[78],"two":[79,116,131],"new":[80],"approaches":[81,132],"for":[82],"setting":[83],"have":[86],"been":[87],"introduced":[88],"namely":[89],"cyclical":[90],"and":[93,133,151,170,189,196],"stochastic":[94],"gradient":[95],"descent":[96],"with":[97,148,193],"warm":[98,123,149,157],"restarts.":[99],"In":[100],"both":[101],"these":[103,130],"approaches,":[104],"value":[108],"varied":[110],"cyclic":[113],"pattern":[114],"between":[115],"boundary":[117],"values.":[118],"This":[119],"paper":[120],"introduces":[121],"another":[122],"restart":[124,150],"technique":[125,141],"which":[126],"inspired":[128],"it":[134,152,171],"uses":[135],"\u201cpoly\u201d":[136],"LR":[137,161,182],"policy.":[138],"proposed":[140,160,181],"called":[143],"as":[144],"polynomial":[145],"requires":[153],"only":[154],"single":[156],"restart.":[158],"policy":[162,183],"helps":[163],"faster":[165],"has":[172],"slightly":[173],"higher":[174],"classification":[175],"accuracy.":[176],"demonstrated":[185],"on":[186],"CIFAR-10,":[187],"CIFAR-100":[188],"tiny":[190],"ImageNet":[191],"dataset":[192],"CNN,":[194],"ResNets":[195],"Wide":[197],"Residual":[198],"Networks":[199],"(WRN)":[200],"architectures.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}