{"id":"https://openalex.org/W2740525496","doi":"https://doi.org/10.24963/ijcai.2017/378","title":"Accelerated Doubly Stochastic Gradient Algorithm for Large-scale Empirical Risk Minimization","display_name":"Accelerated Doubly Stochastic Gradient Algorithm for Large-scale Empirical Risk Minimization","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2740525496","doi":"https://doi.org/10.24963/ijcai.2017/378","mag":"2740525496"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/378","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/378","pdf_url":"https://www.ijcai.org/proceedings/2017/0378.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0378.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103131429","display_name":"Zebang Shen","orcid":"https://orcid.org/0009-0003-2988-9712"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zebang Shen","raw_affiliation_strings":["Zhejiang University","College of Computer Science and Technology, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101960127","display_name":"Hui Qian","orcid":"https://orcid.org/0000-0003-2410-339X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Qian","raw_affiliation_strings":["Zhejiang University","College of Computer Science and Technology, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091792127","display_name":"Tongzhou Mu","orcid":"https://orcid.org/0000-0003-4384-2526"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongzhou Mu","raw_affiliation_strings":["Zhejiang University","College of Computer Science and Technology, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460283","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0003-4286-8468"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Zhejiang University","College of Computer Science and Technology, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2715","last_page":"2721"},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/empirical-risk-minimization","display_name":"Empirical risk minimization","score":0.6891671419143677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5823590755462646},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5762234330177307},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5657737255096436},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.555287778377533},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5198191404342651},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.49944329261779785},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4676218628883362},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.44151052832603455},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.42937377095222473},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36847031116485596},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3242976665496826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15498203039169312}],"concepts":[{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.6891671419143677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5823590755462646},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5762234330177307},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5657737255096436},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.555287778377533},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5198191404342651},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.49944329261779785},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4676218628883362},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.44151052832603455},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.42937377095222473},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36847031116485596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3242976665496826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15498203039169312},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2017/378","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/378","pdf_url":"https://www.ijcai.org/proceedings/2017/0378.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/378","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/378","pdf_url":"https://www.ijcai.org/proceedings/2017/0378.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G29416995","display_name":"\u57fa\u4e8e\u77e5\u8bc6\u56fe\u8c31\u7684\u5728\u7ebf\u4e2a\u6027\u5316\u5546\u54c1\u63a8\u8350\u6280\u672f\u7814\u7a76","funder_award_id":"61672449","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5028231298","display_name":null,"funder_award_id":"61672376","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8220011130","display_name":null,"funder_award_id":"61472347","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740525496.pdf","grobid_xml":"https://content.openalex.org/works/W2740525496.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W584312462","https://openalex.org/W1480376833","https://openalex.org/W1791038712","https://openalex.org/W1860742233","https://openalex.org/W1947202642","https://openalex.org/W1948582444","https://openalex.org/W1959112989","https://openalex.org/W1987371344","https://openalex.org/W1988720110","https://openalex.org/W2000769684","https://openalex.org/W2024484010","https://openalex.org/W2061228897","https://openalex.org/W2095984592","https://openalex.org/W2100556411","https://openalex.org/W2107438106","https://openalex.org/W2111453803","https://openalex.org/W2117686388","https://openalex.org/W2118545728","https://openalex.org/W2135046866","https://openalex.org/W2135482703","https://openalex.org/W2144115358","https://openalex.org/W2153635508","https://openalex.org/W2163786124","https://openalex.org/W2167302917","https://openalex.org/W2356529274","https://openalex.org/W2406665342","https://openalex.org/W2574803746","https://openalex.org/W2936995161","https://openalex.org/W2952215077","https://openalex.org/W2963156201","https://openalex.org/W2963541115","https://openalex.org/W3120421331","https://openalex.org/W4297750465","https://openalex.org/W6640718350","https://openalex.org/W6656719126","https://openalex.org/W6676611517","https://openalex.org/W6755811877","https://openalex.org/W6887714108"],"related_works":["https://openalex.org/W4296209631","https://openalex.org/W3097449145","https://openalex.org/W2561617217","https://openalex.org/W2025378473","https://openalex.org/W2155195660","https://openalex.org/W2060518740","https://openalex.org/W4367626110","https://openalex.org/W2052343155","https://openalex.org/W2262246290","https://openalex.org/W2103875979"],"abstract_inverted_index":{"Nowadays,":[0],"algorithms":[1],"with":[2,28],"fast":[3],"convergence,":[4],"small":[5,68],"memory":[6,79],"footprints,":[7],"and":[8,64,87,110],"low":[9],"per-iteration":[10],"complexity":[11],"are":[12,90,123],"particularly":[13],"favorable":[14],"for":[15,42,105,112],"artificial":[16],"intelligence":[17],"applications.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22],"propose":[23],"a":[24,29,47,59,67],"doubly":[25],"stochastic":[26],"algorithm":[27,56,99],"novel":[30],"accelerating":[31],"multi-momentum":[32],"technique":[33],"to":[34,93,125],"solve":[35],"large":[36],"scale":[37,121],"empirical":[38],"risk":[39],"minimization":[40],"problem":[41],"learning":[43],"tasks.":[44],"While":[45],"enjoying":[46],"provably":[48],"superior":[49],"convergence":[50],"rate,":[51],"in":[52,132],"each":[53],"iteration,":[54],"such":[55],"only":[57,101],"accesses":[58],"mini":[60],"batch":[61],"of":[62,70,78,129],"samples":[63],"meanwhile":[65],"updates":[66],"block":[69],"variable":[71],"coordinates,":[72],"which":[73],"substantially":[74],"reduces":[75],"the":[76,83,106,113,127],"amount":[77],"reference":[80],"when":[81],"both":[82],"massive":[84],"sample":[85],"size":[86],"ultra-high":[88],"dimensionality":[89],"involved.":[91],"Specifically,":[92],"obtain":[94],"an":[95],"\u03b5-accurate":[96],"solution,":[97],"our":[98,130],"requires":[100],"O(log(1/\u03b5)/sqrt(\u03b5))":[102],"overall":[103],"computation":[104],"general":[107],"convex":[108,115],"case":[109],"O((n+sqrt{n\u03ba})log(1/\u03b5))":[111],"strongly":[114],"case.":[116],"Empirical":[117],"studies":[118],"on":[119],"huge":[120],"datasets":[122],"conducted":[124],"illustrate":[126],"efficiency":[128],"method":[131],"practice.":[133]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}