{"id":"https://openalex.org/W2997803752","doi":"https://doi.org/10.1109/tnnls.2021.3098222","title":"Stochastically Controlled Compositional Gradient for Composition Problems","display_name":"Stochastically Controlled Compositional Gradient for Composition Problems","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W2997803752","doi":"https://doi.org/10.1109/tnnls.2021.3098222","mag":"2997803752","pmid":"https://pubmed.ncbi.nlm.nih.gov/34383655"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3098222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3098222","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100324275","display_name":"Liu Liu","orcid":"https://orcid.org/0000-0002-4546-2183"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Liu Liu","raw_affiliation_strings":["School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4546-2183","affiliations":[{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396323","display_name":"Ji Liu","orcid":"https://orcid.org/0000-0002-5509-5065"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji Liu","raw_affiliation_strings":["Kuaishou Technology, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Seattle, WA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010841999","display_name":"Cho\u2010Jui Hsieh","orcid":"https://orcid.org/0000-0002-3520-9627"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cho-Jui Hsieh","raw_affiliation_strings":["Department of Computer Science, University of California at Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California at Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101409300","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0002-5979-578X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["JD Explore Academy, China","Digital Science Institute, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5979-578X","affiliations":[{"raw_affiliation_string":"JD Explore Academy, China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"Digital Science Institute, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.273,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59365107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"34","issue":"2","first_page":"611","last_page":"622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","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"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","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":0.9977999925613403,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7267179489135742},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6977030634880066},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.6430410146713257},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.6398863792419434},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6074452996253967},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6074284911155701},{"id":"https://openalex.org/keywords/proximal-gradient-methods","display_name":"Proximal Gradient Methods","score":0.5476504564285278},{"id":"https://openalex.org/keywords/convex-function","display_name":"Convex function","score":0.5292788147926331},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.49867844581604004},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4895973801612854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48562970757484436},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4730759561061859},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4548932909965515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4495594799518585},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.43526190519332886},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16450542211532593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13609212636947632},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.059206098318099976}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7267179489135742},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6977030634880066},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.6430410146713257},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6398863792419434},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6074452996253967},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6074284911155701},{"id":"https://openalex.org/C10494615","wikidata":"https://www.wikidata.org/wiki/Q17086765","display_name":"Proximal Gradient Methods","level":4,"score":0.5476504564285278},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.5292788147926331},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.49867844581604004},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4895973801612854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48562970757484436},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4730759561061859},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4548932909965515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4495594799518585},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.43526190519332886},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16450542211532593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13609212636947632},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.059206098318099976},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3098222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3098222","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34383655","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34383655","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 neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5711944514","display_name":null,"funder_award_id":"DP-180103424","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494085563","https://openalex.org/W1770943136","https://openalex.org/W1987083649","https://openalex.org/W2047152541","https://openalex.org/W2050728566","https://openalex.org/W2118545728","https://openalex.org/W2124541940","https://openalex.org/W2163786124","https://openalex.org/W2164278908","https://openalex.org/W2217490359","https://openalex.org/W2512803856","https://openalex.org/W2580133360","https://openalex.org/W2584304370","https://openalex.org/W2741379673","https://openalex.org/W2767614206","https://openalex.org/W2884414611","https://openalex.org/W2952594493","https://openalex.org/W2962890301","https://openalex.org/W2963231446","https://openalex.org/W2963313444","https://openalex.org/W2963607709","https://openalex.org/W3011766119","https://openalex.org/W3045864539","https://openalex.org/W4214717370","https://openalex.org/W6676105031","https://openalex.org/W6677553319","https://openalex.org/W6683161245","https://openalex.org/W6698038680","https://openalex.org/W6728561528","https://openalex.org/W6740708716","https://openalex.org/W6743395824","https://openalex.org/W6746752746","https://openalex.org/W6748386961","https://openalex.org/W6752063739","https://openalex.org/W6762741495","https://openalex.org/W6764647576","https://openalex.org/W6765176130","https://openalex.org/W6765940612","https://openalex.org/W6766285669","https://openalex.org/W6770416249"],"related_works":["https://openalex.org/W2811217697","https://openalex.org/W4385644471","https://openalex.org/W4295266778","https://openalex.org/W4224283687","https://openalex.org/W2564172750","https://openalex.org/W2041341337","https://openalex.org/W2075334256","https://openalex.org/W2026452100","https://openalex.org/W2372778757","https://openalex.org/W2112655684"],"abstract_inverted_index":{"We":[0],"consider":[1],"composition":[2,192],"problems":[3],"of":[4,41,86,104,119,145,152,227],"the":[5,38,92,102,105,116,143,146,149,153,187,225,228],"form":[6,138],"<inline-formula":[7,42,63,95,123,131,166,175,199,208],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[8,43,64,96,124,132,167,176,200,209],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[9,44,65,97,125,133,168,177,201,210],"<tex-math":[10,45,66,98,126,134,169,178,202,211],"notation=\"LaTeX\">$(1/n)\\sum":[11],"_{i=":[12],"1}^{n}":[13],"F_{i}":[14],"(1/m)\\sum":[15,48],"_{j":[16,49],"=":[17,50],"1}^{m}":[18],"G_{j}(x)$":[19],"</tex-math></inline-formula>":[20,52,68,100,129,137,173,183,206,213],",":[21,184],"which":[22,186],"are":[23,35],"important":[24],"for":[25,61],"machine":[26],"learning.":[27],"Although":[28],"gradient":[29,33,79,103],"descent":[30,34],"and":[31,101,130,174,219],"stochastic":[32,121],"straightforward":[36],"solutions,":[37],"essential":[39],"computation":[40],"notation=\"LaTeX\">$G":[46],"(x)=":[47],"1}^{m}{G_{j}(x)}$":[51],"in":[53,215],"each":[54],"single":[55],"iteration":[56],"is":[57,112],"expensive,":[58],"let":[59],"alone":[60],"large":[62],"notation=\"LaTeX\">$m$":[67],".":[69],"In":[70],"this":[71,156],"article,":[72],"we":[73,82,158],"devise":[74],"a":[75,160],"stochastically":[76,87],"controlled":[77,88],"compositional":[78],"algorithm.":[80],"Specifically,":[81],"introduce":[83],"two":[84,120],"variants":[85],"technique":[89],"to":[90,141],"estimate":[91],"inner":[93],"function":[94],"notation=\"LaTeX\">$G(x)$":[99],"objective":[106],"function,":[107],"respectively.":[108],"The":[109],"computational":[110],"cost":[111],"largely":[113],"reduced.":[114],"However,":[115],"natural":[117],"needs":[118],"subsets":[122],"notation=\"LaTeX\">${\\mathcal":[127,135],"D}_{1}$":[128],"D}_{2}$":[136],"direct":[139],"barriers":[140],"guarantee":[142],"convergence":[144,162],"algorithm,":[147],"especially":[148],"theoretical":[150],"proof":[151],"convergence.":[154],"To":[155],"end,":[157],"present":[159],"general":[161],"analysis":[163],"by":[164],"proving":[165],"notation=\"LaTeX\">$|{\\mathcal{":[170,179],"D}}_{1}|=\\min":[171],"\\{1/\\epsilon,m\\}$":[172],"D}}_{2}|=\\min":[180],"\\{1/\\epsilon,n":[181],"\\}$":[182],"through":[185],"proposed":[188,229],"method":[189,230],"significantly":[190],"improve":[191],"algorithms":[193],"under":[194],"low":[195],"target":[196],"accuracy":[197],"(i.e.,":[198],"notation=\"LaTeX\">$1/\\epsilon":[203],"\\ll":[204],"m$":[205],"or":[207],"notation=\"LaTeX\">$n$":[212],")":[214],"both":[216],"strongly":[217],"convex":[218],"nonconvex":[220],"settings.":[221],"Comprehensive":[222],"experiments":[223],"demonstrate":[224],"superiority":[226],"over":[231],"existing":[232],"methods.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}