{"id":"https://openalex.org/W2943296448","doi":null,"title":"NAMSG: An Efficient Method For Training Neural Networks.","display_name":"NAMSG: An Efficient Method For Training Neural Networks.","publication_year":2019,"publication_date":"2019-09-25","ids":{"openalex":"https://openalex.org/W2943296448","mag":"2943296448"},"language":"en","primary_location":{"id":"mag:2943296448","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1905.01422","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.01422","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003202344","display_name":"Yushu Chen","orcid":"https://orcid.org/0000-0003-0731-0813","observed_orcids":["https://orcid.org/0000-0003-0731-0813","https://orcid.org/0000-0001-5704-2955","https://orcid.org/0009-0005-0042-9653"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yushu Chen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0731-0813","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Jing","orcid":"https://orcid.org/0000-0002-2305-1201","observed_orcids":["https://orcid.org/0000-0002-2305-1201"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Jing","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2305-1201","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015849734","display_name":"Wenlai Zhao","orcid":"https://orcid.org/0000-0003-1036-4732","observed_orcids":["https://orcid.org/0000-0003-1036-4732"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenlai Zhao","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1036-4732","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100415118","display_name":"Zhiqiang Liu","orcid":"https://orcid.org/0000-0003-2135-8581","observed_orcids":["https://orcid.org/0000-0003-2135-8581","https://orcid.org/0009-0008-4100-6165"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiqiang Liu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2135-8581","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027613671","display_name":"Ouyi Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyi Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liang Qiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Qiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031545295","display_name":"Haohuan Fu","orcid":"https://orcid.org/0000-0002-6982-2235","observed_orcids":["https://orcid.org/0000-0002-6982-2235"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haohuan Fu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6982-2235","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081374149","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0003-0725-8971","observed_orcids":["https://orcid.org/0000-0003-0725-8971"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0725-8971","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101678397","display_name":"Guangwen Yang","orcid":"https://orcid.org/0000-0002-8673-8254","observed_orcids":["https://orcid.org/0000-0002-8673-8254"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guangwen Yang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8673-8254","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9994999766349792,"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":9.999999747378752e-05,"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/neural-network-training","display_name":"neural network training","score":0.8799999952316284},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"stochastic gradient descent","score":0.7369999885559082},{"id":"https://openalex.org/keywords/amsgrad","display_name":"AMSGrad","score":0.7820000052452087},{"id":"https://openalex.org/keywords/observation-points","display_name":"observation points","score":0.6700000166893005},{"id":"https://openalex.org/keywords/adaptive-step-size","display_name":"adaptive step size","score":0.652999997138977},{"id":"https://openalex.org/keywords/convergence-analysis","display_name":"convergence analysis","score":0.7049999833106995},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.8080000281333923},{"id":"https://openalex.org/keywords/strongly-convex-functions","display_name":"strongly convex functions","score":0.8849999904632568},{"id":"https://openalex.org/keywords/nonconvex-optimization","display_name":"non-convex optimization","score":0.781000018119812},{"id":"https://openalex.org/keywords/dynamical-systems","display_name":"dynamical systems","score":0.6039999723434448}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7723445892333984},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6742174625396729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6213656663894653},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5898067951202393},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5699384212493896},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5635069608688354},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5580026507377625},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.47102388739585876},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.4304999113082886},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4202621877193451},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40262192487716675},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2741014361381531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25935786962509155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20077857375144958},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2943296448","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1905.01422","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2943296448","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1905.01422","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W104184427","https://openalex.org/W114517082","https://openalex.org/W196761320","https://openalex.org/W1697075315","https://openalex.org/W1988720110","https://openalex.org/W1994616650","https://openalex.org/W2051669046","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2146502635","https://openalex.org/W2160815625","https://openalex.org/W2193413348","https://openalex.org/W2194775991","https://openalex.org/W2436219157","https://openalex.org/W2525332836","https://openalex.org/W2749988060","https://openalex.org/W2785523195","https://openalex.org/W2787481791","https://openalex.org/W2803640897","https://openalex.org/W2896101215","https://openalex.org/W2903382683","https://openalex.org/W2949117887","https://openalex.org/W2949935872","https://openalex.org/W2949966795","https://openalex.org/W2952230511","https://openalex.org/W2963208657","https://openalex.org/W2963941964","https://openalex.org/W2964121744","https://openalex.org/W2970803838","https://openalex.org/W2970948121","https://openalex.org/W3007473808"],"related_works":["https://openalex.org/W2994384873","https://openalex.org/W2737818580","https://openalex.org/W2996980088","https://openalex.org/W2920422870","https://openalex.org/W2947705626","https://openalex.org/W2916063822","https://openalex.org/W3097919408","https://openalex.org/W4391881209","https://openalex.org/W3087978365","https://openalex.org/W4220708349"],"abstract_inverted_index":{"We":[0,64],"introduce":[1],"NAMSG,":[2],"an":[3],"adaptive":[4],"first-order":[5],"algorithm":[6],"for":[7,40,114],"training":[8,77],"neural\nnetworks.":[9],"The":[10,106],"method":[11,107],"is":[12,97],"efficient":[13],"in":[14,30,45,102,123],"computation":[15],"and":[16,18,71,82,126,136],"memory,":[17],"is\nstraightforward":[19],"to":[20,32,86,99,129],"implement.":[21],"It":[22],"computes":[23],"the":[24,34,38,46,51,60,66,76,88,103],"gradients":[25],"at":[26],"configurable":[27],"remote\nobservation":[28],"points,":[29],"order":[31],"expedite":[33],"convergence":[35,67],"by":[36,55,74],"adjusting":[37],"step\nsize":[39],"directions":[41],"with":[42],"different":[43],"curvatures":[44],"stochastic":[47],"setting.":[48,105],"It\nalso":[49],"scales":[50],"updating":[52],"vector":[53],"elementwise":[54],"a":[56,84,111],"nonincreasing":[57],"preconditioner\nto":[58],"take":[59],"advantages":[61],"of":[62],"AMSGRAD.":[63,137],"analyze":[65],"properties":[68],"for\nboth":[69],"convex":[70,104,116],"nonconvex":[72],"problems":[73,125],"modeling":[75],"process":[78],"as":[79,133],"a\ndynamic":[80],"system,":[81],"provide":[83],"strategy":[85],"select":[87],"observation":[89],"factor":[90],"without\ngrid":[91],"search.":[92],"A":[93],"data-dependent":[94],"regret":[95],"bound":[96,113],"proposed":[98],"guarantee":[100],"the\nconvergence":[101],"can":[108],"further":[109],"achieve":[110],"$O(log(T))$\nregret":[112],"strongly":[115],"functions.":[117],"Experiments":[118],"demonstrate":[119],"that":[120],"NAMSG\nworks":[121],"well":[122],"practical":[124],"compares":[127],"favorably":[128],"popular":[130],"adaptive\nmethods,":[131],"such":[132],"ADAM,":[134],"NADAM,":[135]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-05-09T00:00:00"}