{"id":"https://openalex.org/W1980474876","doi":"https://doi.org/10.1109/icassp.2014.6854928","title":"Exploring one pass learning for deep neural network training with averaged stochastic gradient descent","display_name":"Exploring one pass learning for deep neural network training with averaged stochastic gradient descent","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1980474876","doi":"https://doi.org/10.1109/icassp.2014.6854928","mag":"1980474876"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5083126155","display_name":"You Zhao","orcid":"https://orcid.org/0000-0002-8305-5984"},"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":"Zhao You","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, P.R. China","Interactive Digital Media Technol. Res. Center Inst. of Autom., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Interactive Digital Media Technol. Res. Center Inst. of Autom., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"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":"Xiaorui Wang","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, P.R. China","Interactive Digital Media Technol. Res. Center Inst. of Autom., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Interactive Digital Media Technol. Res. Center Inst. of Autom., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"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":"Bo Xu","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, P.R. China","Interactive Digital Media Technol. Res. Center Inst. of Autom., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Interactive Digital Media Technol. Res. Center Inst. of Autom., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6854","last_page":"6858"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9987000226974487,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9987000226974487,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9966999888420105,"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":0.8327662944793701},{"id":"https://openalex.org/keywords/hessian-matrix","display_name":"Hessian matrix","score":0.7148314714431763},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7054539918899536},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6785973906517029},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6726093888282776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.634303092956543},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.5951375961303711},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.555220901966095},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5207381248474121},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.45926985144615173},{"id":"https://openalex.org/keywords/stochastic-neural-network","display_name":"Stochastic neural network","score":0.4186934232711792},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37086689472198486},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35058921575546265},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3331902027130127},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.30848008394241333},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21550244092941284},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.13768932223320007}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8327662944793701},{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.7148314714431763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7054539918899536},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6785973906517029},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6726093888282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.634303092956543},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.5951375961303711},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.555220901966095},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5207381248474121},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.45926985144615173},{"id":"https://openalex.org/C86582703","wikidata":"https://www.wikidata.org/wiki/Q7617824","display_name":"Stochastic neural network","level":4,"score":0.4186934232711792},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37086689472198486},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35058921575546265},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3331902027130127},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.30848008394241333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21550244092941284},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.13768932223320007},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/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.2014.6854928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320313357","display_name":"Audubon Society of Greater Denver","ror":"https://ror.org/019zjtv03"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1524333225","https://openalex.org/W1629097610","https://openalex.org/W1993882792","https://openalex.org/W2000200144","https://openalex.org/W2076794394","https://openalex.org/W2086161653","https://openalex.org/W2087402357","https://openalex.org/W2097428361","https://openalex.org/W2146502635","https://openalex.org/W2394932179","https://openalex.org/W2403195671","https://openalex.org/W2766736793","https://openalex.org/W2951282416","https://openalex.org/W6631362777","https://openalex.org/W6674634876","https://openalex.org/W6681435938"],"related_works":["https://openalex.org/W2355987247","https://openalex.org/W3177326532","https://openalex.org/W3143650729","https://openalex.org/W4297883503","https://openalex.org/W2895097035","https://openalex.org/W2042173174","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280"],"abstract_inverted_index":{"Deep":[0],"neural":[1,21,124,140],"network":[2,125],"acoustic":[3],"models":[4,14],"have":[5],"shown":[6],"large":[7,57],"improvement":[8],"in":[9,16,74,93],"performance":[10,147],"over":[11],"Gaussian":[12],"mixture":[13],"(G-MMs)":[15],"recent":[17],"studies.":[18],"Typically,":[19],"deep":[20,123,139],"networks":[22],"are":[23],"trained":[24],"based":[25],"on":[26,130],"the":[27,40,48,64,78,88,94,119,131,146],"cross-entropy":[28],"criterion":[29],"using":[30,138],"stochastic":[31,102],"gradient":[32,103],"descent":[33,104],"(SGD).":[34],"However,":[35,81],"plain":[36],"SGD":[37,67],"requires":[38],"scanning":[39],"whole":[41],"training":[42,79],"set":[43],"many":[44],"passes":[45,159],"before":[46],"reaching":[47],"asymptotic":[49,72],"region,":[50],"making":[51],"it":[52,83],"difficult":[53],"to":[54,56,155],"scale":[55],"dataset.":[58,80],"It":[59],"has":[60],"been":[61],"established":[62],"that":[63,145,156],"second":[65],"order":[66],"can":[68],"potentially":[69],"reach":[70],"its":[71,97],"region":[73],"one":[75,112,149],"pass":[76,113,150],"through":[77],"since":[82],"involves":[84],"expensive":[85],"computing":[86],"for":[87,111,122],"inverse":[89],"of":[90,148,157],"Hessian":[91],"matrix":[92],"loss":[95],"function,":[96],"application":[98],"is":[99,106,152],"limited.":[100],"Averaged":[101],"(ASGD)":[105],"proved":[107],"simple":[108],"and":[109],"effective":[110],"online":[114],"learning.":[115],"This":[116],"paper":[117],"investigates":[118],"ASGD":[120,129,151],"algorithm":[121],"training.":[126],"We":[127],"tested":[128],"Mandarin":[132],"Chinese":[133],"record":[134],"speech":[135],"recognition":[136],"task":[137],"networks.":[141],"Experimental":[142],"results":[143],"show":[144],"very":[153],"close":[154],"multiple":[158],"SGD.":[160]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}