{"id":"https://openalex.org/W3110645490","doi":null,"title":"Shuffling Gradient-Based Methods with Momentum.","display_name":"Shuffling Gradient-Based Methods with Momentum.","publication_year":2020,"publication_date":"2020-11-24","ids":{"openalex":"https://openalex.org/W3110645490","mag":"3110645490"},"language":"en","primary_location":{"id":"mag:3110645490","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.11884","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/2011.11884","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061659864","display_name":"Trang H. Tran","orcid":"https://orcid.org/0000-0002-9551-4738","observed_orcids":["https://orcid.org/0000-0002-9551-4738"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trang H. Tran","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9551-4738","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049043092","display_name":"Lam M. Nguyen","orcid":"https://orcid.org/0000-0001-6083-606X","observed_orcids":["https://orcid.org/0000-0001-6083-606X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lam M. Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056282016","display_name":"Quoc Tran-Dinh","orcid":"https://orcid.org/0000-0002-1077-2579","observed_orcids":["https://orcid.org/0000-0002-1077-2579","https://orcid.org/0000-0002-5866-0787"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quoc Tran-Dinh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5866-0787","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":4,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/momentum-method","display_name":"momentum methods","score":0.7900000214576721},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.7139999866485596},{"id":"https://openalex.org/keywords/learning-rate","display_name":"learning rate","score":0.46000000834465027}],"concepts":[{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.9268181920051575},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.7337308526039124},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.6330591440200806},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5792562961578369},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5648093223571777},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5342748761177063},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5252556204795837},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4845384955406189},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4214501976966858},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40086114406585693},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.32175734639167786},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.14576882123947144},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09216657280921936},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08582639694213867},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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:3110645490","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.11884","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:3110645490","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.11884","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":24,"referenced_works":["https://openalex.org/W1955857676","https://openalex.org/W1988720110","https://openalex.org/W1994616650","https://openalex.org/W2073750241","https://openalex.org/W2076428552","https://openalex.org/W2107438106","https://openalex.org/W2112796928","https://openalex.org/W2146502635","https://openalex.org/W2153635508","https://openalex.org/W2436219157","https://openalex.org/W2518108298","https://openalex.org/W2523246573","https://openalex.org/W2544860310","https://openalex.org/W2557191228","https://openalex.org/W2594182398","https://openalex.org/W2750384547","https://openalex.org/W2886837499","https://openalex.org/W2903382683","https://openalex.org/W2918941755","https://openalex.org/W2936995161","https://openalex.org/W2952215077","https://openalex.org/W2963933775","https://openalex.org/W2964121744","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W3168795298","https://openalex.org/W6922539420","https://openalex.org/W3206197352","https://openalex.org/W4377235420","https://openalex.org/W4400386618","https://openalex.org/W4414688567","https://openalex.org/W4400381486","https://openalex.org/W4416609219","https://openalex.org/W4392781349","https://openalex.org/W4415048749"],"abstract_inverted_index":{"We":[0,53,135,151],"combine":[1],"two":[2],"advanced":[3],"ideas":[4],"widely":[5],"used":[6],"in":[7],"optimization":[8],"for":[9,63,70],"machine":[10],"learning:":[11],"shuffling":[12,21,72,107,166],"strategy":[13,73,88,108],"and":[14,66,79,128,147,161],"momentum":[15,25,42,121],"technique":[16],"to":[17,26,119],"develop":[18,112],"a":[19,28,59,85,99],"novel":[20],"gradient-based":[22],"method":[23,38],"with":[24,164],"approximate":[27],"stationary":[29],"point":[30],"of":[31,101,141,174],"non-convex":[32],"finite-sum":[33],"minimization":[34],"problems.":[35],"While":[36],"our":[37,56,95,153],"is":[39,46,89,109,117],"inspired":[40],"by":[41,98],"techniques,":[43],"its":[44],"update":[45],"fundamentally":[47],"different":[48],"from":[49],"existing":[50,120,165],"momentum-based":[51],"methods.":[52,122,167],"establish":[54],"that":[55,116],"algorithm":[57,115,124,143],"achieves":[58],"state-of-the-art":[60],"convergence":[61,96,139],"rate":[62,97,140],"both":[64],"constant":[65],"diminishing":[67],"learning":[68],"rates":[69],"any":[71],"under":[74,144],"standard":[75,159],"assumptions":[76],"(i.e.,":[77],"L-smoothness":[78,146],"bounded":[80,148],"variance).":[81],"In":[82],"particular,":[83],"if":[84],"randomized":[86],"reshuffling":[87],"used,":[90],"we":[91,111],"can":[92],"further":[93],"improve":[94],"fraction":[100],"the":[102,106,126,137,145,175],"data":[103],"size.":[104],"When":[105],"fixed,":[110],"another":[113],"new":[114,176],"similar":[118],"This":[123],"covers":[125],"single-shuffling":[127],"incremental":[129],"gradient":[130,149],"schemes":[131],"as":[132],"special":[133],"cases.":[134],"prove":[136],"same":[138],"this":[142],"assumptions.":[150],"demonstrate":[152],"algorithms":[154],"via":[155],"numerical":[156],"simulations":[157],"on":[158],"datasets":[160],"compare":[162],"them":[163],"Our":[168],"tests":[169],"have":[170],"shown":[171],"encouraging":[172],"performance":[173],"algorithms.":[177]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-12-07T00:00:00"}