{"id":"https://openalex.org/W1587755118","doi":"https://doi.org/10.1109/icassp.2015.7178917","title":"A nonmonotone learning rate strategy for SGD training of deep neural networks","display_name":"A nonmonotone learning rate strategy for SGD training of deep neural networks","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1587755118","doi":"https://doi.org/10.1109/icassp.2015.7178917","mag":"1587755118"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5028709336","display_name":"Nitish Shirish Keskar","orcid":"https://orcid.org/0000-0002-2223-8496"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nitish Shirish Keskar","raw_affiliation_strings":["Northwestern University, Evanston, IL","Northwestern University; Evanston IL USA"],"affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, IL","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern University; Evanston IL USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["Northwestern University, Evanston, IL","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, IL","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028709336"],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":1.7258,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.87760917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9997000098228455,"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/T10320","display_name":"Neural Networks and Applications","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7916293740272522},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.7083759307861328},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6493087410926819},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.572925329208374},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5431299805641174},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5345228314399719},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5258964896202087},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4780043661594391},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4679967761039734},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4533010721206665},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4404629170894623},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43403276801109314},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37789440155029297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7916293740272522},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.7083759307861328},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6493087410926819},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.572925329208374},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5431299805641174},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5345228314399719},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5258964896202087},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4780043661594391},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4679967761039734},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4533010721206665},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4404629170894623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43403276801109314},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37789440155029297},{"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":27,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1916951228","https://openalex.org/W2000200144","https://openalex.org/W2043430160","https://openalex.org/W2061863621","https://openalex.org/W2079623482","https://openalex.org/W2084894614","https://openalex.org/W2090068900","https://openalex.org/W2113372738","https://openalex.org/W2144331407","https://openalex.org/W2146502635","https://openalex.org/W2154776925","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2167137033","https://openalex.org/W2168231600","https://openalex.org/W2179354704","https://openalex.org/W2963470657","https://openalex.org/W4210836678","https://openalex.org/W4255949318","https://openalex.org/W4310843049","https://openalex.org/W6600284362","https://openalex.org/W6640145343","https://openalex.org/W6681435938","https://openalex.org/W6682981795","https://openalex.org/W6684859321","https://openalex.org/W6685457534"],"related_works":["https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4362706668","https://openalex.org/W4231621013","https://openalex.org/W3171021120","https://openalex.org/W3008318776","https://openalex.org/W4377865163","https://openalex.org/W2041416246"],"abstract_inverted_index":{"The":[0],"algorithm":[1,27],"of":[2,7,21],"choice":[3],"for":[4,25,107],"cross-entropy":[5],"training":[6],"deep":[8],"neural":[9],"network":[10],"(DNN)":[11],"acoustic":[12],"models":[13],"is":[14,28,50],"mini-batch":[15],"stochastic":[16],"gradient":[17],"descent":[18],"(SGD).":[19],"One":[20],"the":[22,29,60,108],"important":[23],"decisions":[24],"this":[26],"learning":[30,46],"rate":[31,47],"strategy":[32,48,64],"(also":[33],"called":[34],"stepsize":[35],"selection).":[36],"We":[37],"investigate":[38],"several":[39],"existing":[40],"schemes":[41],"and":[42,59,75,96],"propose":[43],"a":[44],"new":[45],"which":[49],"inspired":[51],"by":[52,110],"nonmonotone":[53],"linesearch":[54],"techniques":[55],"in":[56,77,116],"nonlinear":[57],"optimization":[58,117],"NewBob":[61],"algorithm.":[62],"This":[63],"was":[65],"found":[66],"to":[67,71,83,114],"be":[68],"relatively":[69],"insensitive":[70],"poorly":[72],"tuned":[73],"parameters":[74],"resulted":[76],"lower":[78],"word":[79],"error":[80],"rates":[81],"compared":[82],"Newbob":[84],"on":[85],"two":[86],"different":[87],"LVCSR":[88],"tasks":[89],"(English":[90],"broadcast":[91],"news":[92],"transcription":[93],"50":[94],"hours":[95],"Switchboard":[97],"telephone":[98],"conversations":[99],"300":[100],"hours).":[101],"Further,":[102],"we":[103],"discuss":[104],"some":[105],"justifications":[106],"method":[109],"briefly":[111],"linking":[112],"it":[113],"results":[115],"theory.":[118]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}