{"id":"https://openalex.org/W3015927205","doi":"https://doi.org/10.1109/icassp40776.2020.9052983","title":"Parallelizing Adam Optimizer with Blockwise Model-Update Filtering","display_name":"Parallelizing Adam Optimizer with Blockwise Model-Update Filtering","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015927205","doi":"https://doi.org/10.1109/icassp40776.2020.9052983","mag":"3015927205"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9052983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5100438001","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0003-2587-6028"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002693509","display_name":"Haisong Ding","orcid":"https://orcid.org/0000-0001-9811-8346"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haisong Ding","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039662070","display_name":"Qiang Huo","orcid":"https://orcid.org/0000-0003-2464-6482"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Huo","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100438001"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":1.0747,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.79285138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991000294685364,"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":0.9991000294685364,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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":0.9923999905586243,"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/computer-science","display_name":"Computer science","score":0.8787059783935547},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8255488276481628},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7000113725662231},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6063418388366699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5034019351005554},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4961608350276947},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46145543456077576},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4505019783973694},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42484956979751587},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42002102732658386},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32489314675331116},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.27083057165145874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8787059783935547},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8255488276481628},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7000113725662231},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6063418388366699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5034019351005554},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4961608350276947},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46145543456077576},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4505019783973694},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42484956979751587},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42002102732658386},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32489314675331116},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.27083057165145874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9052983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2336650964","https://openalex.org/W2405883473","https://openalex.org/W2407146636","https://openalex.org/W2517540742","https://openalex.org/W2570343428","https://openalex.org/W2622263826","https://openalex.org/W2787739670","https://openalex.org/W2787998955","https://openalex.org/W2899771611","https://openalex.org/W2903382683","https://openalex.org/W2957577340","https://openalex.org/W2962743428","https://openalex.org/W2963308316","https://openalex.org/W2963523217","https://openalex.org/W2963807318","https://openalex.org/W2963959597","https://openalex.org/W2964121744","https://openalex.org/W2968917279","https://openalex.org/W2973053654","https://openalex.org/W2977517840","https://openalex.org/W2994689640","https://openalex.org/W2996693845","https://openalex.org/W3015480556","https://openalex.org/W4301239768","https://openalex.org/W6703420464","https://openalex.org/W6713806900","https://openalex.org/W6726983090","https://openalex.org/W6748645090","https://openalex.org/W6757107679","https://openalex.org/W6767164110","https://openalex.org/W6768660345","https://openalex.org/W6768839291"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2499279132","https://openalex.org/W271331623","https://openalex.org/W1974690493"],"abstract_inverted_index":{"Recently":[0],"Adam":[1,15,43,74],"has":[2],"become":[3],"a":[4,17,56,64,78,113],"popular":[5],"stochastic":[6,21],"optimization":[7],"method":[8,123],"in":[9,16,124],"deep":[10],"learning":[11],"area.":[12],"To":[13],"parallelize":[14,42],"distributed":[18],"system,":[19],"synchronous":[20],"gradient":[22],"(SSG)":[23],"technique":[24],"is":[25,29],"widely":[26],"used,":[27],"which":[28],"inefficient":[30],"due":[31],"to":[32,41,59,67],"heavy":[33],"communication":[34],"cost.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39],"attempt":[40],"with":[44],"blockwise":[45],"model-update":[46,52],"filtering":[47],"(BMUF)":[48],"instead.":[49],"BMUF":[50,87],"synchronizes":[51],"periodically":[53],"and":[54,75,100,120,129],"introduces":[55],"block":[57],"momentum":[58],"improve":[60],"performance.":[61],"We":[62],"propose":[63],"novel":[65],"way":[66],"modify":[68],"the":[69],"estimated":[70],"moment":[71],"buffers":[72],"of":[73,126],"figure":[76],"out":[77],"simple":[79],"yet":[80],"effective":[81],"trick":[82],"for":[83],"hyper-parameter":[84],"setting":[85],"under":[86],"framework.":[88],"Experimental":[89],"results":[90],"on":[91],"large":[92,101],"scale":[93],"English":[94],"optical":[95],"character":[96],"recognition":[97,105,117,130],"(OCR)":[98],"task":[99,107],"vocabulary":[102],"continuous":[103],"speech":[104],"(LVCSR)":[106],"show":[108],"that":[109],"BMUF-Adam":[110],"achieves":[111],"almost":[112],"linear":[114],"speedup":[115],"without":[116],"accuracy":[118],"degradation":[119],"outperforms":[121],"SSG-based":[122],"terms":[125],"speedup,":[127],"scalability":[128],"accuracy.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}