{"id":"https://openalex.org/W2555215491","doi":"https://doi.org/10.1109/mlsp.2016.7738864","title":"Variance reduction for optimization in speech recognition","display_name":"Variance reduction for optimization in speech recognition","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2555215491","doi":"https://doi.org/10.1109/mlsp.2016.7738864","mag":"2555215491"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2016.7738864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2016.7738864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020268102","display_name":"Peiwen Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Pei-Wen Huang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061908942"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07933342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":1.0,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":1.0,"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/T12676","display_name":"Machine Learning and ELM","score":0.9987999796867371,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/variance-reduction","display_name":"Variance reduction","score":0.7669002413749695},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6619608402252197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6457244753837585},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5486047863960266},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.5431420803070068},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5337250232696533},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5101607441902161},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5009105205535889},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.4995713233947754},{"id":"https://openalex.org/keywords/random-optimization","display_name":"Random optimization","score":0.49395114183425903},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.4625266194343567},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.46133553981781006},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4368111491203308},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4241284728050232},{"id":"https://openalex.org/keywords/continuous-optimization","display_name":"Continuous optimization","score":0.3137946128845215},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3082382380962372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2942217290401459},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.2755066752433777},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2742253541946411},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22741669416427612},{"id":"https://openalex.org/keywords/multi-swarm-optimization","display_name":"Multi-swarm optimization","score":0.10168111324310303}],"concepts":[{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.7669002413749695},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6619608402252197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6457244753837585},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5486047863960266},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.5431420803070068},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5337250232696533},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5101607441902161},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5009105205535889},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.4995713233947754},{"id":"https://openalex.org/C109578324","wikidata":"https://www.wikidata.org/wiki/Q3354463","display_name":"Random optimization","level":5,"score":0.49395114183425903},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.4625266194343567},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.46133553981781006},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4368111491203308},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4241284728050232},{"id":"https://openalex.org/C92995354","wikidata":"https://www.wikidata.org/wiki/Q5165499","display_name":"Continuous optimization","level":4,"score":0.3137946128845215},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3082382380962372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2942217290401459},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.2755066752433777},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2742253541946411},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22741669416427612},{"id":"https://openalex.org/C122357587","wikidata":"https://www.wikidata.org/wiki/Q6934508","display_name":"Multi-swarm optimization","level":3,"score":0.10168111324310303},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp.2016.7738864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2016.7738864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"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/W1813021177","https://openalex.org/W1939652453","https://openalex.org/W2015631279","https://openalex.org/W2019991208","https://openalex.org/W2106728335","https://openalex.org/W2107438106","https://openalex.org/W2118545728","https://openalex.org/W2137515395","https://openalex.org/W2515339036","https://openalex.org/W2952594493","https://openalex.org/W6608133726","https://openalex.org/W6676105031","https://openalex.org/W6680610060"],"related_works":["https://openalex.org/W2107438106","https://openalex.org/W584331704","https://openalex.org/W2353480216","https://openalex.org/W1995068956","https://openalex.org/W3006531883","https://openalex.org/W4214884207","https://openalex.org/W4256133869","https://openalex.org/W2148463925","https://openalex.org/W2134401588","https://openalex.org/W4251603141"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"(DNN)":[3],"is":[4,108],"trained":[5],"according":[6],"to":[7,64,79,118],"a":[8,19,103],"mini-batch":[9],"optimization":[10,51,56,74,96,123,151],"based":[11],"on":[12],"the":[13,39,46,55,58,65,76,81,85,95,113,135,149],"stochastic":[14,20,42,59],"gradient":[15],"descent":[16],"algorithm.":[17],"Such":[18],"learning":[21,43],"suffers":[22],"from":[23,57],"instability":[24],"in":[25,50,102,124],"parameter":[26],"updating":[27,82],"and":[28,130,143],"may":[29],"easily":[30],"trap":[31],"into":[32],"local":[33],"optimum.":[34],"This":[35,73],"study":[36],"deals":[37],"with":[38,116],"stability":[40],"of":[41,48,87,97,100,105,137,141],"by":[44,110,147],"reducing":[45],"variance":[47,86,140],"gradients":[49,88,142],"procedure.":[52],"We":[53],"upgrade":[54],"dual":[60,98],"coordinated":[61],"ascent":[62],"(SDCA)":[63],"accelerated":[66],"SDCA":[67,101],"without":[68],"duality":[69],"(or":[70],"dual-free":[71,93],"ASDCA).":[72],"incorporates":[75],"momentum":[77],"method":[78],"accelerate":[80],"rule":[83],"where":[84],"can":[89,127],"be":[90,128],"reduced.":[91],"Using":[92],"ASDCA,":[94],"function":[99,115],"form":[104],"convex":[106],"loss":[107],"implemented":[109],"directly":[111],"optimizing":[112],"primal":[114],"respect":[117],"pseudo-dual":[119],"parameters.":[120],"The":[121],"non-convex":[122],"DNN":[125,153],"training":[126,138],"resolved":[129],"accelerated.":[131],"Experimental":[132],"results":[133],"illustrate":[134],"reduction":[136],"loss,":[139],"word":[144],"error":[145],"rate":[146],"using":[148],"proposed":[150],"for":[152],"speech":[154],"recognition.":[155]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}