{"id":"https://openalex.org/W3037045207","doi":"https://doi.org/10.1109/tpami.2020.3004354","title":"Scalable and Practical Natural Gradient for Large-Scale Deep Learning","display_name":"Scalable and Practical Natural Gradient for Large-Scale Deep Learning","publication_year":2020,"publication_date":"2020-06-23","ids":{"openalex":"https://openalex.org/W3037045207","doi":"https://doi.org/10.1109/tpami.2020.3004354","mag":"3037045207","pmid":"https://pubmed.ncbi.nlm.nih.gov/32750792"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2020.3004354","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2020.3004354","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/9639876/09123671.pdf","source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/34/9639876/09123671.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Kazuki Osawa","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan","[Department of Computer Science, Tokyo Institute of Technology, 13290 Meguro-ku, Tokyo Japan 152-8550 (e-mail: oosawa.k.ad@m.titech.ac.jp)]"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"[Department of Computer Science, Tokyo Institute of Technology, 13290 Meguro-ku, Tokyo Japan 152-8550 (e-mail: oosawa.k.ad@m.titech.ac.jp)]","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","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":false,"raw_author_name":"Yohei Tsuji","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan","Dept. of Mathematical and Computing Science, Tokyo Institute of Technology, 13290 Meguro-ku, Tokyo Japan 152-8550 (e-mail: tsuji.y.ae@m.titech.ac.jp)"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Dept. of Mathematical and Computing Science, Tokyo Institute of Technology, 13290 Meguro-ku, Tokyo Japan 152-8550 (e-mail: tsuji.y.ae@m.titech.ac.jp)","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"]},{"id":"https://openalex.org/I4210088813","display_name":"Oiles (japan)","ror":"https://ror.org/0042cyg15","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210088813"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuichiro Ueno","raw_affiliation_strings":["AIST, AIST-Tokyo Tech RWBC-OIL, Tokyo, Japan","Tokyo Institute of Technology, Tokyo, Japan","Department of Computer Science, Tokyo Institute of Technology, 13290 Meguro-ku, Tokyo Japan 152-8550 (e-mail: ueno.y.ai@m.titech.ac.jp)"],"affiliations":[{"raw_affiliation_string":"AIST, AIST-Tokyo Tech RWBC-OIL, Tokyo, Japan","institution_ids":["https://openalex.org/I4210088813"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, 13290 Meguro-ku, Tokyo Japan 152-8550 (e-mail: ueno.y.ai@m.titech.ac.jp)","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050692022","display_name":"Akira Naruse","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akira Naruse","raw_affiliation_strings":["NVIDIA, Tokyo, Japan","Developer Technology, NVIDIA Corp, 196328 Minato-ku, Tokyo Japan (e-mail: anaruse@nvidia.com)"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Tokyo, Japan","institution_ids":[]},{"raw_affiliation_string":"Developer Technology, NVIDIA Corp, 196328 Minato-ku, Tokyo Japan (e-mail: anaruse@nvidia.com)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001103949","display_name":"Chuan-Sheng Foo","orcid":"https://orcid.org/0000-0002-4748-5792"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chuan-Sheng Foo","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","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"]},{"id":"https://openalex.org/I4210088813","display_name":"Oiles (japan)","ror":"https://ror.org/0042cyg15","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210088813"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rio Yokota","raw_affiliation_strings":["AIST, AIST-Tokyo Tech RWBC-OIL, Tokyo, Japan","Tokyo Institute of Technology, Tokyo, Japan","[GSIC, Tokyo Institute of Technology, 13290 Meguro-ku, Tokyo Japan 152-8550 (e-mail: rioyokota@gsic.titech.ac.jp)]"],"affiliations":[{"raw_affiliation_string":"AIST, AIST-Tokyo Tech RWBC-OIL, Tokyo, Japan","institution_ids":["https://openalex.org/I4210088813"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"[GSIC, Tokyo Institute of Technology, 13290 Meguro-ku, Tokyo Japan 152-8550 (e-mail: rioyokota@gsic.titech.ac.jp)]","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076237237"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":2.061,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.89163917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"44","issue":"1","first_page":"404","last_page":"415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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":0.9969000220298767,"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":0.746035099029541},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7442009449005127},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6920725703239441},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.61380934715271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6023786664009094},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5933248996734619},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5175230503082275},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.500852108001709},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.49147069454193115},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4658660888671875},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.45658746361732483},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4497957229614258},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44425514340400696},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4348587393760681},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34163698554039},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12044000625610352}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.746035099029541},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7442009449005127},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6920725703239441},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.61380934715271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6023786664009094},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5933248996734619},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5175230503082275},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.500852108001709},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.49147069454193115},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4658660888671875},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.45658746361732483},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4497957229614258},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44425514340400696},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4348587393760681},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34163698554039},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12044000625610352},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2020.3004354","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2020.3004354","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/9639876/09123671.pdf","source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:32750792","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32750792","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":{"id":"doi:10.1109/tpami.2020.3004354","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2020.3004354","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/9639876/09123671.pdf","source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G1694798417","display_name":"\u76f8\u7d9a\u306e\u73fe\u5b9f\u3068\u6c11\u6cd5\u4e0a\u306e\u554f\u984c\u70b9","funder_award_id":"18001","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G193038087","display_name":null,"funder_award_id":"JST CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G2492590789","display_name":null,"funder_award_id":"JP18H03248","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G2792802287","display_name":null,"funder_award_id":"KAKENHI","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G3176941833","display_name":"\u8fd1\u4e16\u8d8a\u524d\u306b\u304a\u3051\u308b\u8fb2\u6c11\u5c64\u5206\u89e3\u306e\u7814\u7a76","funder_award_id":"19012","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3282004645","display_name":null,"funder_award_id":"JPMJCR","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G3283080113","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320311508","funder_display_name":"National Institute of Advanced Industrial Science and Technology"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3612518180","display_name":null,"funder_award_id":"JPMJCR19F5","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G3959150894","display_name":"Tissiochemisty \u306e\u5c0f\u578b\u8a66\u9a13\u88c5\u7f6e\u306e\u7814\u7a76","funder_award_id":"80012","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4227499671","display_name":null,"funder_award_id":"KAKENHI Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4690090395","display_name":"\u30d9\u30a4\u30ba\u7684\u5927\u898f\u6a21\u6df1\u5c64\u5b66\u7fd2\u306e\u305f\u3081\u306e\u81ea\u7136\u52fe\u914d\u8fd1\u4f3c\u6cd5","funder_award_id":"19J13477","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5786340949","display_name":null,"funder_award_id":"KAKENHI Grant Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5835976563","display_name":null,"funder_award_id":"18H03248","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7752643416","display_name":null,"funder_award_id":"Japan","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8886816395","display_name":"\u9020\u8840\u5668\u816b\u760d\u6027\u75be\u60a3\u306e\u5316\u5b66\u7642\u6cd5, \u6b8a\u306b\u305d\u306e\u526f\u4f5c\u7528\u9632\u6b62\u306b\u95a2\u3059\u308b\u7814\u7a76","funder_award_id":"90122","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3037045207.pdf","grobid_xml":"https://content.openalex.org/works/W3037045207.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1970789124","https://openalex.org/W2108598243","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2474694648","https://openalex.org/W2622263826","https://openalex.org/W2626017178","https://openalex.org/W2757910899","https://openalex.org/W2769856846","https://openalex.org/W2884711234","https://openalex.org/W2888206291","https://openalex.org/W2901541570","https://openalex.org/W2920582597","https://openalex.org/W2920668770","https://openalex.org/W2926655273","https://openalex.org/W2948321964","https://openalex.org/W2951443179","https://openalex.org/W2951882630","https://openalex.org/W2955454939","https://openalex.org/W2962883024","https://openalex.org/W2967791890","https://openalex.org/W2970154823","https://openalex.org/W2998508940","https://openalex.org/W4288284572","https://openalex.org/W4289300273","https://openalex.org/W6608133726","https://openalex.org/W6683107984","https://openalex.org/W6693969136","https://openalex.org/W6713134421","https://openalex.org/W6721263324","https://openalex.org/W6726983090","https://openalex.org/W6739622702","https://openalex.org/W6739785051","https://openalex.org/W6743802245","https://openalex.org/W6743885270","https://openalex.org/W6744513255","https://openalex.org/W6745136726","https://openalex.org/W6746514494","https://openalex.org/W6746868464","https://openalex.org/W6748315838","https://openalex.org/W6749538638","https://openalex.org/W6753209298","https://openalex.org/W6753753558","https://openalex.org/W6753958361","https://openalex.org/W6755501240","https://openalex.org/W6756439839","https://openalex.org/W6756592394","https://openalex.org/W6759786419","https://openalex.org/W6761074043","https://openalex.org/W6763143685","https://openalex.org/W6764038303","https://openalex.org/W6765175657","https://openalex.org/W6766729739"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W4287755480","https://openalex.org/W3113607506","https://openalex.org/W2964170259","https://openalex.org/W3002546633","https://openalex.org/W4206119629","https://openalex.org/W2765682467","https://openalex.org/W2785875001","https://openalex.org/W4382937879","https://openalex.org/W2948488743"],"abstract_inverted_index":{"Large-scale":[0],"distributed":[1],"training":[2,64,118],"of":[3,17,48,135,145,155,164,169],"deep":[4],"neural":[5],"networks":[6],"results":[7],"in":[8,20,138,166],"models":[9,65,75],"with":[10,77,82,92,147,158],"worse":[11],"generalization":[12,72],"performance":[13,73],"as":[14,97,116,150,152],"a":[15,60,93,106,119,131,142],"result":[16],"the":[18,21,34],"increase":[19],"effective":[22],"mini-batch":[23,90,143,162],"size.":[24],"Previous":[25],"approaches":[26],"attempt":[27],"to":[28,69,74,88,99,130],"address":[29],"this":[30],"problem":[31],"by":[32],"varying":[33],"learning":[35],"rate":[36],"and":[37,42,54],"batch":[38,49],"size":[39,144,163],"over":[40],"epochs":[41],"layers,":[43],"or":[44],"ad":[45],"hoc":[46],"modifications":[47],"normalization.":[50],"We":[51,102,127],"propose":[52],"scalable":[53],"practical":[55],"natural":[56],"gradient":[57],"descent":[58],"(SP-NGD),":[59],"principled":[61],"approach":[62],"for":[63,122],"that":[66],"allows":[67],"them":[68],"attain":[70],"similar":[71],"trained":[76],"first-order":[78,100,112],"optimization":[79],"methods,":[80],"but":[81],"accelerated":[83],"convergence.":[84],"Furthermore,":[85],"SP-NGD":[86,104],"scales":[87],"large":[89,161],"sizes":[91],"negligible":[94],"computational":[95],"overhead":[96],"compared":[98],"methods.":[101],"evaluated":[103],"on":[105,125],"benchmark":[107],"task":[108],"where":[109],"highly":[110],"optimized":[111],"methods":[113],"are":[114],"available":[115],"references:":[117],"ResNet-50":[120],"model":[121],"image":[123],"classification":[124],"ImageNet.":[126],"demonstrate":[128],"convergence":[129],"top-1":[132],"validation":[133],"accuracy":[134,154],"75.4":[136],"percent":[137,157],"5.5":[139],"minutes":[140],"using":[141],"32,768":[146],"1,024":[148],"GPUs,":[149],"well":[151],"an":[153,159],"74.9":[156],"extremely":[160],"131,072":[165],"873":[167],"steps":[168],"SP-NGD.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}