{"id":"https://openalex.org/W3021335160","doi":"https://doi.org/10.1109/ciss48834.2020.1570627111","title":"Guaranteed Convergence of Training Convolutional Neural Networks via Accelerated Gradient Descent","display_name":"Guaranteed Convergence of Training Convolutional Neural Networks via Accelerated Gradient Descent","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3021335160","doi":"https://doi.org/10.1109/ciss48834.2020.1570627111","mag":"3021335160"},"language":"en","primary_location":{"id":"doi:10.1109/ciss48834.2020.1570627111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss48834.2020.1570627111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 54th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-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/A5100328881","display_name":"Shuai Zhang","orcid":"https://orcid.org/0000-0002-4821-6404"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shuai Zhang","raw_affiliation_strings":["Dept. of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377219","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0003-0928-9691"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["Dept. of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100321843","display_name":"Sijia Liu","orcid":"https://orcid.org/0000-0003-2817-6991"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sijia Liu","raw_affiliation_strings":["MIT-IBM Watson AI Lab, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050344371","display_name":"Pin\u2010Yu Chen","orcid":"https://orcid.org/0000-0003-1039-8369"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pin-Yu Chen","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030156276","display_name":"Jinjun Xiong","orcid":"https://orcid.org/0000-0002-2620-4859"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinjun Xiong","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100328881"],"corresponding_institution_ids":["https://openalex.org/I165799507"],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75157635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"87","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","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/T12676","display_name":"Machine Learning and ELM","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/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":0.9988999962806702,"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/gradient-descent","display_name":"Gradient descent","score":0.7153952717781067},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6587719321250916},{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.6223187446594238},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5366477370262146},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5306825637817383},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5092276334762573},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5073792338371277},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4845966100692749},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4765791893005371},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4526790976524353},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41131314635276794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39009028673171997},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3526778221130371},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3384191393852234}],"concepts":[{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.7153952717781067},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6587719321250916},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.6223187446594238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5366477370262146},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5306825637817383},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5092276334762573},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5073792338371277},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4845966100692749},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4765791893005371},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4526790976524353},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41131314635276794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39009028673171997},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3526778221130371},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3384191393852234},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ciss48834.2020.1570627111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss48834.2020.1570627111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 54th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1498436455","https://openalex.org/W1550431896","https://openalex.org/W1568288633","https://openalex.org/W1811750039","https://openalex.org/W2112796928","https://openalex.org/W2117130368","https://openalex.org/W2144354855","https://openalex.org/W2163605009","https://openalex.org/W2257979135","https://openalex.org/W2502393534","https://openalex.org/W2591714514","https://openalex.org/W2618398196","https://openalex.org/W2625063094","https://openalex.org/W2732724430","https://openalex.org/W2758053331","https://openalex.org/W2766371994","https://openalex.org/W2768041186","https://openalex.org/W2777256551","https://openalex.org/W2801753252","https://openalex.org/W2803955134","https://openalex.org/W2808958252","https://openalex.org/W2895073990","https://openalex.org/W2914605961","https://openalex.org/W2949148114","https://openalex.org/W2952318479","https://openalex.org/W2962767131","https://openalex.org/W2963211922","https://openalex.org/W2963325933","https://openalex.org/W2963519230","https://openalex.org/W2963569411","https://openalex.org/W2963623651","https://openalex.org/W2963739978","https://openalex.org/W2963744427","https://openalex.org/W2963759574","https://openalex.org/W2963794891","https://openalex.org/W2963922413","https://openalex.org/W2963959597","https://openalex.org/W3021623424","https://openalex.org/W3024317845","https://openalex.org/W3137695714","https://openalex.org/W3141595720","https://openalex.org/W4285719527","https://openalex.org/W6604254268","https://openalex.org/W6629815555","https://openalex.org/W6632965665","https://openalex.org/W6638214083","https://openalex.org/W6681017033","https://openalex.org/W6684191040","https://openalex.org/W6725287276","https://openalex.org/W6726983090","https://openalex.org/W6733941281","https://openalex.org/W6734728544","https://openalex.org/W6738373677","https://openalex.org/W6739166439","https://openalex.org/W6740483536","https://openalex.org/W6744879188","https://openalex.org/W6745448519","https://openalex.org/W6745622407","https://openalex.org/W6746713790","https://openalex.org/W6751860949","https://openalex.org/W6752544856","https://openalex.org/W6754893189","https://openalex.org/W6759308816","https://openalex.org/W6763485134","https://openalex.org/W7034108470"],"related_works":["https://openalex.org/W3103325625","https://openalex.org/W4293226380","https://openalex.org/W1486898455","https://openalex.org/W3090727460","https://openalex.org/W2041905724","https://openalex.org/W4306313719","https://openalex.org/W2991463004","https://openalex.org/W2088588293","https://openalex.org/W4311726894","https://openalex.org/W2489520628"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"study":[4],"the":[5,19,34,41,60,73,82,89,110,118],"linear":[6,21],"regression":[7],"problem":[8,68,91],"of":[9,29],"training":[10,30],"an":[11],"one-hidden-layer":[12],"non-overlapping":[13],"convolutional":[14],"neural":[15],"networks":[16],"(ConvNNs)":[17],"with":[18,51,101],"rectified":[20],"unit":[22],"(ReLU)":[23],"activation":[24],"functions.":[25],"Given":[26],"a":[27,49,65,102],"set":[28],"data":[31],"that":[32,80],"contains":[33],"inputs":[35,83],"(feature":[36],"vectors)":[37],"and":[38,54,106,109],"outputs":[39,42],"(labels),":[40],"are":[43],"assumed":[44],"to":[45,58,85,117],"be":[46,93],"generated":[47],"from":[48],"ConvNN":[50],"unknown":[52],"weights,":[53],"our":[55],"goal":[56],"is":[57,72],"recover":[59],"ground-truth":[61,119],"weights":[62],"by":[63,95],"minimizing":[64],"non-convex":[66],"optimization":[67,90],"whose":[69],"object":[70],"function":[71],"empirical":[74],"loss":[75],"function.":[76],"We":[77],"have":[78],"proved":[79],"if":[81],"belong":[84],"Gaussian":[86],"distribution,":[87],"then":[88],"can":[92],"solved":[94],"accelerated":[96],"gradient":[97],"descent":[98],"(AGD)":[99],"algorithm":[100,114],"well-designed":[103],"initial":[104],"point":[105],"enough":[107],"samples,":[108],"iterates":[111],"via":[112],"AGD":[113],"converge":[115],"linearly":[116],"weights.":[120]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}