{"id":"https://openalex.org/W3007093918","doi":"https://doi.org/10.1137/21m1453311","title":"Scheduled Restart Momentum for Accelerated Stochastic Gradient Descent","display_name":"Scheduled Restart Momentum for Accelerated Stochastic Gradient Descent","publication_year":2022,"publication_date":"2022-05-31","ids":{"openalex":"https://openalex.org/W3007093918","doi":"https://doi.org/10.1137/21m1453311","mag":"3007093918"},"language":"en","primary_location":{"id":"doi:10.1137/21m1453311","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1453311","pdf_url":null,"source":{"id":"https://openalex.org/S152600803","display_name":"SIAM Journal on Imaging Sciences","issn_l":"1936-4954","issn":["1936-4954"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Imaging Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5100376439","display_name":"Bao Wang","orcid":"https://orcid.org/0000-0002-4848-4791"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bao Wang","raw_affiliation_strings":["Department of Mathematics and Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT 84112 USA"],"raw_orcid":"https://orcid.org/0000-0002-4848-4791","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT 84112 USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101399124","display_name":"Tan M. Nguyen","orcid":"https://orcid.org/0000-0002-6408-5416"},"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":"Tan Nguyen","raw_affiliation_strings":["Department of Mathematics, UCLA, Los Angeles, CA 90095 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, UCLA, Los Angeles, CA 90095 USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037318331","display_name":"Tao Sun","orcid":"https://orcid.org/0000-0001-5024-1900"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Sun","raw_affiliation_strings":["College of Computer, NUDT, China, 999078"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, NUDT, China, 999078","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090707978","display_name":"Andrea L. Bertozzi","orcid":"https://orcid.org/0000-0003-0396-7391"},"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":"Andrea L. Bertozzi","raw_affiliation_strings":["Department of Mathematics, UCLA, Los Angeles, CA 90095 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, UCLA, Los Angeles, CA 90095 USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072713767","display_name":"Richard G. Baraniuk","orcid":"https://orcid.org/0000-0002-0721-8999"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard G. Baraniuk","raw_affiliation_strings":["Department of ECE, Rice University, Houston, TX 77005 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of ECE, Rice University, Houston, TX 77005 USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002037883","display_name":"Stanley Osher","orcid":"https://orcid.org/0000-0002-7900-4658"},"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":"Stanley J. Osher","raw_affiliation_strings":["Department of Mathematics, UCLA, Los Angeles, CA 90095 USA"],"raw_orcid":"https://orcid.org/0000-0002-7900-4658","affiliations":[{"raw_affiliation_string":"Department of Mathematics, UCLA, Los Angeles, CA 90095 USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2306,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.89164247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"15","issue":"2","first_page":"738","last_page":"761"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9987999796867371,"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":0.8758252859115601},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.7620905041694641},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.6541004776954651},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5936267375946045},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5876433849334717},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5465055704116821},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5271168351173401},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.5095593929290771},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4775082468986511},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45640361309051514},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.45370855927467346},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.439706951379776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3521402180194855},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34252387285232544},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32444021105766296},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3228836953639984}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8758252859115601},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.7620905041694641},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6541004776954651},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5936267375946045},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5876433849334717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5465055704116821},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5271168351173401},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5095593929290771},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4775082468986511},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45640361309051514},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.45370855927467346},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.439706951379776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3521402180194855},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34252387285232544},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32444021105766296},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3228836953639984},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1137/21m1453311","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1453311","pdf_url":null,"source":{"id":"https://openalex.org/S152600803","display_name":"SIAM Journal on Imaging Sciences","issn_l":"1936-4954","issn":["1936-4954"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Imaging Sciences","raw_type":"journal-article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt20b6n3jn","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/20b6n3jn","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIAM Journal on Imaging Sciences, vol 15, iss 2","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1483339860","display_name":null,"funder_award_id":"FA9550-18-1-0478","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G2344778886","display_name":"BIGDATA: F:  Collaborative Research: Theory and Practice of Randomized Algorithms for Ultra-Large-Scale Signal Processing","funder_award_id":"1838177","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4504108201","display_name":null,"funder_award_id":"N00014-17-1","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5324172118","display_name":null,"funder_award_id":"DGE-1250104","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5846066211","display_name":null,"funder_award_id":"DE-SC0021142","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5930895032","display_name":null,"funder_award_id":"DMS-1952339","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5969984103","display_name":null,"funder_award_id":"IIS-1838177","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6098521345","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6326764571","display_name":null,"funder_award_id":"IIS-1730574","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G685404616","display_name":null,"funder_award_id":"CCF-1911094","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6856914370","display_name":"IGERT: Neuroengineering from Cells to Systems","funder_award_id":"1250104","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7058866341","display_name":null,"funder_award_id":"G001534-7500","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7698193007","display_name":"Computing Innovation Fellows 2020 Project","funder_award_id":"2030859","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7708612965","display_name":null,"funder_award_id":"DMS-1924935","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7840735550","display_name":null,"funder_award_id":"N00014-18-1-2047","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8252795151","display_name":null,"funder_award_id":"N00014-18-12571","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8359444094","display_name":null,"funder_award_id":"N00014-17-1-2551","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8618411326","display_name":"Collaborative Research: ATD: Robust, Accurate and Efficient Graph-Structured RNN for Spatio-Temporal Forecasting and Anomaly Detection","funder_award_id":"1924935","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W47642388","https://openalex.org/W104184427","https://openalex.org/W1522301498","https://openalex.org/W1556545893","https://openalex.org/W1800356822","https://openalex.org/W1986046400","https://openalex.org/W1987083649","https://openalex.org/W1988720110","https://openalex.org/W1991760653","https://openalex.org/W2024484010","https://openalex.org/W2030161963","https://openalex.org/W2045096911","https://openalex.org/W2064675550","https://openalex.org/W2089468765","https://openalex.org/W2100556411","https://openalex.org/W2108563286","https://openalex.org/W2117539524","https://openalex.org/W2124450277","https://openalex.org/W2124768887","https://openalex.org/W2127447444","https://openalex.org/W2146502635","https://openalex.org/W2166706236","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2528062157","https://openalex.org/W2557283755","https://openalex.org/W2559655401","https://openalex.org/W2596585349","https://openalex.org/W2602728306","https://openalex.org/W2604744755","https://openalex.org/W2612690371","https://openalex.org/W2739748921","https://openalex.org/W2767726060","https://openalex.org/W2768282280","https://openalex.org/W2769394111","https://openalex.org/W2785523195","https://openalex.org/W2808102858","https://openalex.org/W2884265051","https://openalex.org/W2896204105","https://openalex.org/W2903382683","https://openalex.org/W2948920178","https://openalex.org/W2962879692","https://openalex.org/W2963433607","https://openalex.org/W2963470657","https://openalex.org/W2963804082","https://openalex.org/W2963830794","https://openalex.org/W2964164027","https://openalex.org/W2970971581","https://openalex.org/W2994689640","https://openalex.org/W3029645440","https://openalex.org/W3118608800","https://openalex.org/W3157341860","https://openalex.org/W4212774754"],"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/W3007093918","https://openalex.org/W4362706668","https://openalex.org/W3008318776","https://openalex.org/W1977633006","https://openalex.org/W2041416246"],"abstract_inverted_index":{"Stochastic":[0],"gradient":[1,46,57,74],"descent":[2,58],"(SGD)":[3],"algorithms,":[4],"with":[5,47,194],"constant":[6,104],"momentum":[7,50,105,111,121],"and":[8,81,133,148,184],"its":[9],"variants":[10],"such":[11],"as":[12,175],"Adam,":[13],"are":[14],"the":[15,33,53,72,103,109,116,120,166,176,201],"optimization":[16,61],"methods":[17,37],"of":[18,35,56,131,163,168,206],"choice":[19],"for":[20,59,98,135,150,155],"training":[21,99,142,153,197],"deep":[22],"neural":[23],"networks":[24],"(DNNs).":[25],"There":[26],"is":[27,75,208],"great":[28],"interest":[29],"in":[30,106,112,141,152],"speeding":[31],"up":[32],"convergence":[34,54,78,147],"these":[36],"due":[38],"to":[39,122,125,200],"their":[40],"high":[41],"computational":[42],"expense.":[43],"Nesterov":[44],"accelerated":[45],"a":[48,63,94,126,129],"time-varying":[49],"(NAG)":[51],"improves":[52,146],"rate":[55,162],"convex":[60],"using":[62],"specially":[64],"designed":[65],"momentum;":[66],"however,":[67],"it":[68],"accumulates":[69],"error":[70,161,192],"when":[71],"stochastic":[73],"used,":[76],"slowing":[77],"at":[79,83,210],"best":[80],"diverging":[82],"worst.":[84],"In":[85],"this":[86],"paper,":[87],"we":[88,138],"propose":[89],"scheduled":[90],"restart":[91],"SGD":[92,107,202],"(SRSGD),":[93],"new":[95],"NAG-style":[96],"scheme":[97],"DNNs.":[100],"SRSGD":[101,144,158,186,207],"replaces":[102],"by":[108,118],"increasing":[110],"NAG":[113],"but":[114],"stabilizes":[115],"iterations":[117],"resetting":[119],"zero":[123],"according":[124],"schedule.":[127],"Using":[128],"variety":[130],"models":[132],"benchmarks":[134],"image":[136],"classification,":[137,157],"demonstrate":[139],"that,":[140],"DNNs,":[143],"significantly":[145,195],"generalization;":[149],"instance,":[151],"ResNet-200":[154],"ImageNet":[156],"achieves":[159],"an":[160],"20.93%":[164],"versus":[165],"benchmark":[167],"22.13%.":[169],"These":[170],"improvements":[171],"become":[172],"more":[173],"significant":[174],"network":[177],"grows":[178],"deeper.":[179],"Furthermore,":[180],"on":[181],"both":[182],"CIFAR":[183],"ImageNet,":[185],"reaches":[187],"similar":[188],"or":[189],"even":[190],"better":[191],"rates":[193],"fewer":[196],"epochs":[198],"compared":[199],"baseline.":[203],"Our":[204],"implementation":[205],"available":[209],"https://github.com/minhtannguyen/SRSGD.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}