{"id":"https://openalex.org/W3000400623","doi":null,"title":"Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments","display_name":"Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments","publication_year":2019,"publication_date":"2019-09-25","ids":{"openalex":"https://openalex.org/W3000400623","mag":"3000400623"},"language":"en","primary_location":{"id":"mag:3000400623","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=BJepq2VtDB","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5032957280","display_name":"Boris Ginsburg","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013846372","display_name":"Patrice Castonguay","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrice Castonguay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088392468","display_name":"Oleksii Hrinchuk","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oleksii Hrinchuk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048403564","display_name":"Oleksii Kuchaiev","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oleksii Kuchaiev","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026088310","display_name":"Vitaly Lavrukhin","orcid":"https://orcid.org/0009-0006-7866-8301","observed_orcids":["https://orcid.org/0009-0006-7866-8301"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vitaly Lavrukhin","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0006-7866-8301","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"R. Bret Leary","orcid":"https://orcid.org/0000-0003-3771-8465","observed_orcids":["https://orcid.org/0000-0003-3771-8465"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R. Bret Leary","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3771-8465","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762970","display_name":"Jason Li","orcid":"https://orcid.org/0000-0002-1150-3549","observed_orcids":["https://orcid.org/0000-0002-1150-3549","https://orcid.org/0000-0003-3644-0879"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jason Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1150-3549","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564876","display_name":"Huyen Nguyen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huyen Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354700","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0002-6064-0777","observed_orcids":["https://orcid.org/0000-0002-6064-0777"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6064-0777","affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Jonathan Cohen","orcid":"https://orcid.org/0000-0003-1004-5598","observed_orcids":["https://orcid.org/0000-0003-1004-5598"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Cohen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1004-5598","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3005,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60228201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9940999746322632,"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":0.9940999746322632,"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/T10320","display_name":"Neural Networks and Applications","score":0.0026000000070780516,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0003000000142492354,"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/deep-neural-network-training","display_name":"deep neural network training","score":0.75},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"stochastic gradient descent","score":0.8100000023841858},{"id":"https://openalex.org/keywords/layer-normalization","display_name":"layer normalization","score":0.3869999945163727},{"id":"https://openalex.org/keywords/gradient-normalization","display_name":"gradient normalization","score":0.3319999873638153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5082247257232666},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4864058792591095},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.4428524971008301},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.40261366963386536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.390891969203949},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3902495801448822},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36028197407722473},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35976845026016235},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2869786024093628},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13918793201446533},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3000400623","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=BJepq2VtDB","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1494198834","https://openalex.org/W1988720110","https://openalex.org/W2117539524","https://openalex.org/W2146502635","https://openalex.org/W2302255633","https://openalex.org/W2518108298","https://openalex.org/W2525332836","https://openalex.org/W2622263826","https://openalex.org/W2626778328","https://openalex.org/W2757910899","https://openalex.org/W2763421725","https://openalex.org/W2785523195","https://openalex.org/W2785921341","https://openalex.org/W2797328513","https://openalex.org/W2806311723","https://openalex.org/W2908510526","https://openalex.org/W2949935872","https://openalex.org/W2949979820","https://openalex.org/W2963208657","https://openalex.org/W2964121744","https://openalex.org/W2973215447","https://openalex.org/W3000779003"],"related_works":["https://openalex.org/W4415798220","https://openalex.org/W3005708742","https://openalex.org/W6885045674","https://openalex.org/W7108228100","https://openalex.org/W2945697643","https://openalex.org/W6960096091","https://openalex.org/W6922711340","https://openalex.org/W2997791832","https://openalex.org/W2095684152","https://openalex.org/W7133231841"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-01-23T00:00:00"}
