{"id":"https://openalex.org/W2998037822","doi":"https://doi.org/10.24963/ijcai.2020/451","title":"pbSGD: Powered Stochastic Gradient Descent Methods for Accelerated Non-Convex Optimization","display_name":"pbSGD: Powered Stochastic Gradient Descent Methods for Accelerated Non-Convex Optimization","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W2998037822","doi":"https://doi.org/10.24963/ijcai.2020/451","mag":"2998037822"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/451","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/451","pdf_url":"https://www.ijcai.org/proceedings/2020/0451.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth 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/2020/0451.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109479866","display_name":"Beitong Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beitong Zhou","raw_affiliation_strings":["Huazhong University of Science and Technology","School of Artificial Intelligence and Automation, Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361920","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-7193-0622"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["University of Waterloo","Department of Applied Mathematics, University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"Department of Applied Mathematics, University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037718676","display_name":"Weigao Sun","orcid":"https://orcid.org/0000-0003-2551-924X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weigao Sun","raw_affiliation_strings":["Huazhong University of Science and Technology","School of Artificial Intelligence and Automation, Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103188029","display_name":"Ruijuan Chen","orcid":"https://orcid.org/0000-0003-0745-4032"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruijuan Chen","raw_affiliation_strings":["Huazhong University of Science and Technology","School of Artificial Intelligence and Automation, Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045155646","display_name":"Claire J. Tomlin","orcid":"https://orcid.org/0000-0003-3192-3185"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claire Tomlin","raw_affiliation_strings":["University of California, Berkeley","Department of Electrical Engineering and Computer Sciences, UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016488397","display_name":"Ye Yuan","orcid":"https://orcid.org/0000-0001-7858-0437"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Yuan","raw_affiliation_strings":["Huazhong University of Science and Technology","School of Artificial Intelligence and Automation, Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.38,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.84511886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3258","last_page":"3266"},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9990000128746033,"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/T12676","display_name":"Machine Learning and ELM","score":0.9979000091552734,"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/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.8105255365371704},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6614894866943359},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.6100254058837891},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.568733274936676},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5465991497039795},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5424867272377014},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5282432436943054},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.500070333480835},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.47719892859458923},{"id":"https://openalex.org/keywords/convex-function","display_name":"Convex function","score":0.45105424523353577},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.42028170824050903},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.4150359034538269},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37318092584609985},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34194785356521606},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.3407715857028961},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22904515266418457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22695693373680115},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.07463511824607849}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8105255365371704},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6614894866943359},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.6100254058837891},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.568733274936676},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5465991497039795},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5424867272377014},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5282432436943054},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.500070333480835},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.47719892859458923},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.45105424523353577},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.42028170824050903},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.4150359034538269},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37318092584609985},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34194785356521606},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.3407715857028961},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22904515266418457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22695693373680115},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.07463511824607849},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/451","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/451","pdf_url":"https://www.ijcai.org/proceedings/2020/0451.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/451","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/451","pdf_url":"https://www.ijcai.org/proceedings/2020/0451.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2998037822.pdf","grobid_xml":"https://content.openalex.org/works/W2998037822.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1697075315","https://openalex.org/W1980287119","https://openalex.org/W1988720110","https://openalex.org/W1994616650","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2146502635","https://openalex.org/W2401231614","https://openalex.org/W2549139847","https://openalex.org/W2619307294","https://openalex.org/W2619516334","https://openalex.org/W2785523195","https://openalex.org/W2808402975","https://openalex.org/W2886837499","https://openalex.org/W2893314716","https://openalex.org/W2911847432","https://openalex.org/W2911876570","https://openalex.org/W2936995161","https://openalex.org/W2946038967","https://openalex.org/W2950425432","https://openalex.org/W2963263347","https://openalex.org/W2963446712","https://openalex.org/W2963959597","https://openalex.org/W3103518151","https://openalex.org/W3118608800","https://openalex.org/W4297685247","https://openalex.org/W4300900294"],"related_works":["https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668","https://openalex.org/W3008318776","https://openalex.org/W1977633006","https://openalex.org/W4286899070","https://openalex.org/W2041416246"],"abstract_inverted_index":{"We":[0,56],"propose":[1,58],"a":[2,31,118,122],"novel":[3],"technique":[4],"for":[5,135,150,169],"improving":[6],"the":[7,27,44,87,162],"stochastic":[8,28],"gradient":[9,29,99,119],"descent":[10],"(SGD)":[11],"method":[12,24],"to":[13,30,50,54,109,132],"train":[14],"deep":[15,77],"networks,":[16],"which":[17,62],"we":[18,63,145],"term":[19,64],"pbSGD.":[20],"The":[21,66,156],"proposed":[22,88],"pbSGD":[23,52,59,89,115,152],"simply":[25],"raises":[26],"certain":[32],"power":[33,45],"elementwise":[34],"during":[35],"iterations":[36],"and":[37,80,90,106,112,130,153,171],"introduces":[38],"only":[39],"one":[40],"additional":[41],"parameter,":[42],"namely,":[43],"exponent":[46],"(when":[47],"it":[48,127],"equals":[49],"1,":[51],"reduces":[53],"SGD).":[55],"further":[57],"with":[60,104],"momentum,":[61],"pbSGDM.":[65],"main":[67],"results":[68,84],"of":[69,159,167],"this":[70],"paper":[71],"present":[72],"comprehensive":[73],"experiments":[74],"on":[75,174],"popular":[76],"learning":[78,141],"models":[79],"benchmark":[81],"datasets.":[82],"Empirical":[83],"show":[85,146],"that":[86],"pbSGDM":[91,154],"obtain":[92],"faster":[93],"initial":[94],"training":[95],"speed":[96],"than":[97],"adaptive":[98],"methods,":[100],"comparable":[101],"generalization":[102],"ability":[103],"SGD,":[105],"improved":[107],"robustness":[108],"hyper-parameter":[110],"selection":[111],"vanishing":[113],"gradients.":[114],"is":[116,128],"essentially":[117],"modifier":[120],"via":[121],"nonlinear":[123],"transformation.":[124],"As":[125],"such,":[126],"orthogonal":[129],"complementary":[131],"other":[133],"techniques":[134],"accelerating":[136],"gradient-based":[137],"optimization":[138],"such":[139],"as":[140],"rate":[142,148],"schedules.":[143],"Finally,":[144],"convergence":[147,160,168],"analysis":[149],"both":[151],"methods.":[155],"theoretical":[157,165],"rates":[158,166],"match":[161],"best":[163],"known":[164],"SGD":[170],"SGDM":[172],"methods":[173],"nonconvex":[175],"functions.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}