{"id":"https://openalex.org/W2162160137","doi":"https://doi.org/10.1162/089976605774320539","title":"Learning Curves for Stochastic Gradient Descent in Linear Feedforward Networks","display_name":"Learning Curves for Stochastic Gradient Descent in Linear Feedforward Networks","publication_year":2005,"publication_date":"2005-09-28","ids":{"openalex":"https://openalex.org/W2162160137","doi":"https://doi.org/10.1162/089976605774320539","mag":"2162160137","pmid":"https://pubmed.ncbi.nlm.nih.gov/16212768"},"language":"en","primary_location":{"id":"doi:10.1162/089976605774320539","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089976605774320539","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","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/A5077337147","display_name":"Justin Werfel","orcid":"https://orcid.org/0000-0002-2567-1172"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Justin Werfel","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A.,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A.,","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977658","display_name":"Xiaohui Xie","orcid":"https://orcid.org/0000-0001-9413-4461"},"institutions":[{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I107606265"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaohui Xie","raw_affiliation_strings":["Broad Institute of Massachusetts Institute of Technology and Harvard University, Cambridge, MA 02141, U.S.A.,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Broad Institute of Massachusetts Institute of Technology and Harvard University, Cambridge, MA 02141, U.S.A.,","institution_ids":["https://openalex.org/I107606265","https://openalex.org/I136199984","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044273339","display_name":"H. Sebastian Seung","orcid":"https://orcid.org/0000-0002-8591-6733"},"institutions":[{"id":"https://openalex.org/I1344073410","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90","country_code":"US","type":"facility","lineage":["https://openalex.org/I1344073410"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"H. Sebastian Seung","raw_affiliation_strings":["Howard Hughes Medical Institute, Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A.,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Howard Hughes Medical Institute, Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A.,","institution_ids":["https://openalex.org/I1344073410","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044273339","https://openalex.org/A5077337147","https://openalex.org/A5101977658"],"corresponding_institution_ids":["https://openalex.org/I107606265","https://openalex.org/I1344073410","https://openalex.org/I136199984","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":3.6754,"has_fulltext":false,"cited_by_count":114,"citation_normalized_percentile":{"value":0.93405343,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"17","issue":"12","first_page":"2699","last_page":"2718"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9997000098228455,"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/T12676","display_name":"Machine Learning and ELM","score":0.9997000098228455,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9993000030517578,"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/T10320","display_name":"Neural Networks and Applications","score":0.9990000128746033,"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/perturbation","display_name":"Perturbation (astronomy)","score":0.7685247659683228},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5512661337852478},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5494838356971741},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5210984945297241},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.4381254017353058},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43158817291259766},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.41580086946487427},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4075724184513092},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3691818118095398},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32216453552246094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2820301055908203},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.18549653887748718},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14219778776168823}],"concepts":[{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.7685247659683228},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5512661337852478},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5494838356971741},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5210984945297241},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.4381254017353058},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43158817291259766},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.41580086946487427},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4075724184513092},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3691818118095398},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32216453552246094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2820301055908203},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.18549653887748718},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14219778776168823},{"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/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D013269","descriptor_name":"Stochastic Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013269","descriptor_name":"Stochastic Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013269","descriptor_name":"Stochastic Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1162/089976605774320539","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089976605774320539","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:16212768","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16212768","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":"Neural computation","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1022.3119","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1022.3119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://papers.nips.cc/paper/2511-learning-curves-for-stochastic-gradient-descent-in-linear-feedforward-networks.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.4184","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.4184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.broad.mit.edu/personal/xhx/publications/werfel_nc.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.3486","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.3486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://books.nips.cc/papers/files/nips16/NIPS2003_LT17.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1488975066","https://openalex.org/W1990359011","https://openalex.org/W2006598597","https://openalex.org/W2022733260","https://openalex.org/W2102489567","https://openalex.org/W2116424792","https://openalex.org/W2119717200","https://openalex.org/W2127621215","https://openalex.org/W2137902180","https://openalex.org/W2156084351"],"related_works":["https://openalex.org/W2895097035","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4362706668","https://openalex.org/W4231621013","https://openalex.org/W3171021120","https://openalex.org/W3008318776","https://openalex.org/W2041416246"],"abstract_inverted_index":{"Gradient-following":[0],"learning":[1,52,69,109,137,181],"methods":[2,26],"can":[3,156],"encounter":[4],"problems":[5],"of":[6,47,62,86,102,162,179],"implementation":[7],"in":[8,50,128,131,143],"many":[9],"applications,":[10],"and":[11,37,153,188,192],"stochastic":[12,133],"variants":[13],"are":[14,168,193],"sometimes":[15],"used":[16,27,130],"to":[17,67,83,99,160],"overcome":[18],"these":[19,173],"difficulties.":[20],"We":[21,123],"analyze":[22],"three":[23],"online":[24],"training":[25],"with":[28],"a":[29,80,114],"linear":[30],"perceptron:":[31],"direct":[32,76,163],"gradient":[33,77,164],"descent,":[34],"node":[35,71,154],"perturbation,":[36,112],"weight":[38,63,89,145],"perturbation.":[39],"Learning":[40],"speed":[41],"is":[42,65,73,91],"defined":[43],"as":[44,184],"the":[45,51,55,60,84,100,132,136,177,180,185,189],"rate":[46],"exponential":[48],"decay":[49],"curves.":[53,138],"When":[54],"scalar":[56],"parameter":[57],"that":[58,116,142,161],"controls":[59],"size":[61],"updates":[64,134],"chosen":[66],"maximize":[68],"speed,":[70],"perturbation":[72,90,106,146,155],"slower":[74,92],"than":[75,110],"descent":[78,165],"by":[79,94,113],"factor":[81,97,115],"equal":[82,98],"number":[85,101],"output":[87,170],"units;":[88],"still":[93],"an":[95],"additional":[96],"input":[103,186],"units.":[104,171],"Parallel":[105],"allows":[107],"faster":[108],"sequential":[111],"does":[117],"not":[118,194],"depend":[119,175],"on":[120,176],"network":[121],"size.":[122],"also":[124],"characterize":[125],"how":[126],"uncertainty":[127],"quantities":[129],"affects":[135],"This":[139],"study":[140],"suggests":[141],"practice,":[144],"may":[147],"be":[148],"slow":[149],"for":[150],"large":[151],"networks,":[152],"have":[157],"performance":[158],"comparable":[159],"when":[166],"there":[167],"few":[169],"However,":[172],"statements":[174],"specifics":[178],"problem,":[182],"such":[183],"distribution":[187],"target":[190],"function,":[191],"universally":[195],"applicable.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":7}],"updated_date":"2026-06-09T15:46:55.921056","created_date":"2025-10-10T00:00:00"}