{"id":"https://openalex.org/W2962883024","doi":"https://doi.org/10.1145/3339186.3339202","title":"Performance Optimizations and Analysis of Distributed Deep Learning with Approximated Second-Order Optimization Method","display_name":"Performance Optimizations and Analysis of Distributed Deep Learning with Approximated Second-Order Optimization Method","publication_year":2019,"publication_date":"2019-07-22","ids":{"openalex":"https://openalex.org/W2962883024","doi":"https://doi.org/10.1145/3339186.3339202","mag":"2962883024"},"language":"en","primary_location":{"id":"doi:10.1145/3339186.3339202","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3339186.3339202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 48th International Conference on Parallel Processing","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/A5040483976","display_name":"Yohei Tsuji","orcid":"https://orcid.org/0000-0001-8108-2324"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yohei Tsuji","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076237237","display_name":"Kazuki Osawa","orcid":"https://orcid.org/0000-0001-6390-9797"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuki Osawa","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101655156","display_name":"Yuichiro Ueno","orcid":"https://orcid.org/0000-0001-8763-2075"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuichiro Ueno","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050692022","display_name":"Akira Naruse","orcid":"https://orcid.org/0000-0002-3140-0854"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akira Naruse","raw_affiliation_strings":["NVIDIA, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024747717","display_name":"Rio Yokota","orcid":"https://orcid.org/0000-0001-7573-7873"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rio Yokota","raw_affiliation_strings":["Global Scientific Information and Computing Center, Tokyo Institute of Technology, AIST-Tokyo Tech RWBC-OIL, AIST, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Global Scientific Information and Computing Center, Tokyo Institute of Technology, AIST-Tokyo Tech RWBC-OIL, AIST, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100634486","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-1910-8532"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Matsuoka","raw_affiliation_strings":["RIKEN Center for Computational Science, Tokyo Institute of Technology, Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Tokyo Institute of Technology, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730","https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5040483976"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.7086,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74754413,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T12676","display_name":"Machine Learning and ELM","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9994999766349792,"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":0.8255884647369385},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.718887984752655},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6280474662780762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6026703119277954},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5652764439582825},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.49685218930244446},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48901399970054626},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.487385094165802},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.45956355333328247},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4498802125453949},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3652505874633789},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.1974441409111023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8255884647369385},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.718887984752655},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6280474662780762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6026703119277954},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5652764439582825},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49685218930244446},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48901399970054626},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.487385094165802},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.45956355333328247},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4498802125453949},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3652505874633789},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.1974441409111023},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3339186.3339202","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3339186.3339202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 48th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311508","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54"},{"id":"https://openalex.org/F4320322704","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1520168181","https://openalex.org/W1522301498","https://openalex.org/W1583837637","https://openalex.org/W1667652561","https://openalex.org/W2419597278","https://openalex.org/W2511730936","https://openalex.org/W2523060838","https://openalex.org/W2602856279","https://openalex.org/W2604738573","https://openalex.org/W2607662938","https://openalex.org/W2749988060","https://openalex.org/W2752512710","https://openalex.org/W2781206762","https://openalex.org/W2797230987","https://openalex.org/W2888206291","https://openalex.org/W2900167092","https://openalex.org/W2901541570","https://openalex.org/W2903482050","https://openalex.org/W2903697572","https://openalex.org/W2911682203","https://openalex.org/W2911880109","https://openalex.org/W2914304175","https://openalex.org/W2949427019","https://openalex.org/W2949650786","https://openalex.org/W2953328958","https://openalex.org/W2955454939","https://openalex.org/W2964309400","https://openalex.org/W2998508934","https://openalex.org/W3101543398"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128","https://openalex.org/W4390846322","https://openalex.org/W4285818394"],"abstract_inverted_index":{"Faster":[0],"training":[1,33,110,133,150],"of":[2,34,57,91,153],"deep":[3,17,20,35],"neural":[4,36],"networks":[5],"is":[6,71,144],"desired":[7],"to":[8,30,87,94,106,116,120,130,135,139],"speed":[9,107],"up":[10,108],"the":[11,32,39,58,68,74,89,96,109,121,137],"research":[12],"and":[13,22,93],"development":[14],"cycle":[15],"in":[16,76,151],"learning.":[18],"Distributed":[19],"learning":[21],"second-order":[23,47],"optimization":[24,48,85],"methods":[25],"are":[26,104],"two":[27,59],"different":[28],"techniques":[29,86],"accelerate":[31,95],"networks.":[37],"In":[38,78],"previous":[40],"work,":[41,80],"researchers":[42],"show":[43],"that":[44],"an":[45],"approximated":[46],"method,":[49],"called":[50],"K-FAC,":[51],"can":[52],"mitigate":[53],"each":[54],"other":[55],"drawbacks":[56],"techniques.":[60],"However,":[61],"there":[62],"was":[63],"no":[64],"detailed":[65],"discussion":[66],"on":[67],"performance,":[69],"which":[70],"critical":[72],"for":[73,148],"usage":[75],"practice.":[77],"this":[79],"we":[81,103,124],"propose":[82],"several":[83],"performance":[84,101,122,128,134],"reduce":[88],"overheads":[90],"K-FAC":[92,143],"overall":[97],"training.":[98],"Applying":[99],"all":[100],"optimizations,":[102,123],"able":[105],"1.64":[111],"times":[112],"per":[113],"iteration":[114],"compared":[115],"a":[117,126],"baseline.":[118],"Additional":[119],"construct":[125],"simple":[127],"model":[129,132],"predict":[131],"help":[136],"users":[138],"determine":[140],"whether":[141],"distributed":[142],"appropriate":[145],"or":[146],"not":[147],"their":[149],"terms":[152],"wall-time.":[154]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}