{"id":"https://openalex.org/W2102865215","doi":"https://doi.org/10.1109/asru.2013.6707750","title":"Combining stochastic average gradient and Hessian-free optimization for sequence training of deep neural networks","display_name":"Combining stochastic average gradient and Hessian-free optimization for sequence training of deep neural networks","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2102865215","doi":"https://doi.org/10.1109/asru.2013.6707750","mag":"2102865215"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","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/A5006329390","display_name":"Pierre Dognin","orcid":"https://orcid.org/0000-0001-5688-6005"},"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/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pierre Dognin","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034451965","display_name":"Vaibhava Goel","orcid":"https://orcid.org/0000-0002-5504-3863"},"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/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhava Goel","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"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":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9393,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75410312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"321","last_page":"325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9943000078201294,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9847000241279602,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hessian-matrix","display_name":"Hessian matrix","score":0.7497296333312988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6808688640594482},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6498605608940125},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5866785049438477},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5421643257141113},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5072367191314697},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5039786696434021},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4841080904006958},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4426068663597107},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4111388325691223},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.41015326976776123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39990296959877014},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33702537417411804},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2615887522697449},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20589369535446167},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.1358790099620819}],"concepts":[{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.7497296333312988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6808688640594482},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6498605608940125},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5866785049438477},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5421643257141113},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5072367191314697},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5039786696434021},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4841080904006958},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4426068663597107},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4111388325691223},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.41015326976776123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39990296959877014},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33702537417411804},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2615887522697449},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20589369535446167},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.1358790099620819},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2013.6707750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","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":14,"referenced_works":["https://openalex.org/W196761320","https://openalex.org/W1932057668","https://openalex.org/W1987238397","https://openalex.org/W2102486516","https://openalex.org/W2105875671","https://openalex.org/W2114016253","https://openalex.org/W2150907703","https://openalex.org/W2963746765","https://openalex.org/W6608133726","https://openalex.org/W6640321102","https://openalex.org/W6647191204","https://openalex.org/W6675672627","https://openalex.org/W6675761068","https://openalex.org/W6682398751"],"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":{"Minimum":[0],"phone":[1],"error":[2,17],"(MPE)":[3],"training":[4,25,61,85,124],"of":[5,19,83,103,128,169],"deep":[6],"neural":[7],"networks":[8],"(DNN)":[9],"is":[10,26,88],"an":[11,153],"effective":[12],"technique":[13],"for":[14,91,123],"reducing":[15],"word":[16],"rate":[18],"automatic":[20],"speech":[21],"recognition":[22],"tasks.":[23],"This":[24],"often":[27],"carried":[28],"out":[29],"using":[30],"a":[31,54,111],"Hessian-free":[32],"(HF)":[33],"quasi-Newton":[34],"approach,":[35],"although":[36],"other":[37],"methods":[38],"such":[39],"as":[40,179],"stochastic":[41,56,66,112],"gradient":[42,68,73],"descent":[43],"have":[44],"also":[45],"been":[46],"applied":[47],"successfully.":[48],"In":[49],"this":[50,171],"paper":[51],"we":[52],"present":[53],"novel":[55],"approach":[57],"to":[58,110,134,140,152],"HF":[59,113,136,181],"sequence":[60,182],"inspired":[62],"by":[63,98,107],"recently":[64],"proposed":[65],"average":[67],"(SAG)":[69],"method.":[70],"SAG":[71,97],"reuses":[72],"information":[74],"from":[75],"past":[76],"updates,":[77],"and":[78,106,150],"consequently":[79],"simulates":[80],"the":[81,101,117,177],"presence":[82],"more":[84],"data":[86,130],"than":[87],"really":[89],"observed":[90],"each":[92,146,160],"model":[93,147],"update.":[94],"We":[95,115],"extend":[96],"dynamically":[99],"weighting":[100],"contribution":[102],"previous":[104],"gradients,":[105],"combining":[108],"it":[109],"optimization.":[114],"term":[116],"resulting":[118],"procedure":[119,172],"DSAG-HF.":[120],"Experimental":[121],"results":[122],"DNNs":[125],"on":[126],"1500h":[127],"audio":[129],"show":[131],"that":[132],"compared":[133],"baseline":[135,180],"training,":[137],"DSAG-HF":[138,163],"leads":[139],"better":[141,155],"held-out":[142],"MPE":[143],"loss":[144,156],"after":[145],"parameter":[148],"update,":[149],"converges":[151,173],"overall":[154],"value.":[157],"Furthermore,":[158],"since":[159],"update":[161],"in":[162,174],"takes":[164],"place":[165],"over":[166],"smaller":[167],"amount":[168],"data,":[170],"about":[175],"half":[176],"time":[178],"training.":[183]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}