{"id":"https://openalex.org/W3170439183","doi":null,"title":"Decreasing scaling transition from adaptive gradient descent to stochastic gradient descent.","display_name":"Decreasing scaling transition from adaptive gradient descent to stochastic gradient descent.","publication_year":2021,"publication_date":"2021-06-12","ids":{"openalex":"https://openalex.org/W3170439183","mag":"3170439183"},"language":"en","primary_location":{"id":"mag:3170439183","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.06749","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/2106.06749","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kun Zeng","orcid":"https://orcid.org/0000-0002-6713-2871","observed_orcids":["https://orcid.org/0000-0002-6713-2871"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Zeng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6713-2871","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046859189","display_name":"Jinlan Liu","orcid":"https://orcid.org/0009-0005-2906-079X","observed_orcids":["https://orcid.org/0009-0005-2906-079X","https://orcid.org/0009-0005-6672-9325","https://orcid.org/0000-0002-6673-3763"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinlan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078998004","display_name":"Zhixia Jiang","orcid":"https://orcid.org/0000-0002-6773-1444","observed_orcids":["https://orcid.org/0000-0002-6773-1444"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhixia Jiang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6773-1444","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012826227","display_name":"Dongpo Xu","orcid":"https://orcid.org/0000-0002-9663-9743","observed_orcids":["https://orcid.org/0000-0002-9663-9743"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongpo Xu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9663-9743","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":0,"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":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":1.0,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","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/adaptive-gradient-descent","display_name":"adaptive gradient descent","score":0.9259999990463257},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"stochastic gradient descent","score":0.9959999918937683},{"id":"https://openalex.org/keywords/learning-rate-schedules","display_name":"learning rate scheduling","score":0.6650000214576721},{"id":"https://openalex.org/keywords/convergence-analysis","display_name":"convergence analysis","score":0.7680000066757202},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.9810000061988831},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.7829999923706055},{"id":"https://openalex.org/keywords/adam","display_name":"Adam","score":0.5870000123977661},{"id":"https://openalex.org/keywords/adagrad","display_name":"AdaGrad","score":0.703000009059906},{"id":"https://openalex.org/keywords/rmsprop","display_name":"RMSProp","score":0.8420000076293945},{"id":"https://openalex.org/keywords/amsgrad","display_name":"AMSGrad","score":0.9279999732971191}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8236466646194458},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.7651479244232178},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6229437589645386},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5445738434791565},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5246151685714722},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5119389295578003},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4943242073059082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46356141567230225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43261247873306274},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.398466557264328},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3200985789299011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18997138738632202},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12163689732551575},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07061523199081421},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.056756794452667236},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0508599579334259},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3170439183","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.06749","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:3170439183","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.06749","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1498436455","https://openalex.org/W1686475922","https://openalex.org/W2112796928","https://openalex.org/W2194775991","https://openalex.org/W2518108298","https://openalex.org/W2523246573","https://openalex.org/W2525778437","https://openalex.org/W2612983688","https://openalex.org/W2776855315","https://openalex.org/W2785523195","https://openalex.org/W2798579099","https://openalex.org/W2799116291","https://openalex.org/W2892559787","https://openalex.org/W2914360004","https://openalex.org/W2949935872","https://openalex.org/W2963208657","https://openalex.org/W2963446712","https://openalex.org/W2964121744","https://openalex.org/W2980844465","https://openalex.org/W2982064756","https://openalex.org/W2994406485","https://openalex.org/W2996449522","https://openalex.org/W2997976910","https://openalex.org/W3034547948","https://openalex.org/W3036735840","https://openalex.org/W3037546238","https://openalex.org/W3041090558","https://openalex.org/W3046881646","https://openalex.org/W3118608800","https://openalex.org/W3134477793"],"related_works":["https://openalex.org/W3201385174","https://openalex.org/W3171021120","https://openalex.org/W2893302333","https://openalex.org/W4290856730","https://openalex.org/W4282972963","https://openalex.org/W1813485996","https://openalex.org/W7082271911","https://openalex.org/W7036369000","https://openalex.org/W4225543905","https://openalex.org/W3006996801"],"abstract_inverted_index":{"Currently,":[0],"researchers":[1,51],"have":[2,22,52],"proposed":[3],"the":[4,27,30,34,45,54,64,92,96,109,137,146,151,161],"adaptive":[5,55,83,127],"gradient":[6,47,56,60,84,88,98,128,132],"descent":[7,57,61,85,89,129,133],"algorithm":[8,163],"and":[9,58,68,123,171,174],"its":[10],"variants,":[11],"such":[12],"as":[13,42,44],"AdaGrad,":[14],"RMSProp,":[15],"Adam,":[16],"AmsGrad,":[17],"etc.":[18],"Although":[19],"these":[20],"algorithms":[21],"a":[23,78,102,115,121,142,165],"faster":[24,166],"speed":[25],"in":[26,33],"early":[28],"stage,":[29],"generalization":[31],"ability":[32],"later":[35],"stage":[36,94],"of":[37,66,95,111,114,145,148,153],"training":[38,93],"is":[39,178],"often":[40],"not":[41],"good":[43,70],"stochastic":[46,59,87,97,131],"descent.":[48],"Recently,":[49],"some":[50],"combined":[53],"to":[62,86,130],"obtain":[63],"advantages":[65],"both":[67],"achieved":[69],"results.":[71],"Based":[72],"on":[73],"this":[74,181],"research,":[75],"we":[76,100,140],"propose":[77],"decreasing":[79],"scaling":[80],"transition":[81,125],"from":[82,126],"method(DSTAda).":[90],"For":[91],"descent,":[99],"use":[101],"learning":[103,117],"rate":[104],"that":[105,160],"decreases":[106],"linearly":[107],"with":[108],"number":[110],"iterations":[112],"instead":[113],"constant":[116],"rate.":[118],"We":[119],"achieve":[120],"smooth":[122],"stable":[124],"through":[134],"scaling.":[135],"At":[136],"same":[138],"time,":[139],"give":[141],"theoretical":[143],"proof":[144],"convergence":[147,167],"DSTAda":[149,162],"under":[150],"framework":[152],"online":[154],"learning.":[155],"Our":[156,176],"experimental":[157],"results":[158],"show":[159],"has":[164],"speed,":[168],"higher":[169],"accuracy,":[170],"better":[172],"stability":[173],"robustness.":[175],"implementation":[177],"available":[179],"at:":[180],"https":[182],"URL.":[183]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-06-22T00:00:00"}