{"id":"https://openalex.org/W3106830411","doi":"https://doi.org/10.1145/3489048.3530965","title":"Asymptotic Convergence Rate of Dropout on Shallow Linear Neural Networks","display_name":"Asymptotic Convergence Rate of Dropout on Shallow Linear Neural Networks","publication_year":2022,"publication_date":"2022-06-02","ids":{"openalex":"https://openalex.org/W3106830411","doi":"https://doi.org/10.1145/3489048.3530965","mag":"3106830411"},"language":"en","primary_location":{"id":"doi:10.1145/3489048.3530965","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3489048.3530965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstract Proceedings of the 2022 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems","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/A5034616653","display_name":"Albert Senen\u2013Cerda","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Albert Senen-Cerda","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004989436","display_name":"Jaron Sanders","orcid":"https://orcid.org/0000-0003-0187-2065"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jaron Sanders","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034616653"],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":null,"apc_paid":null,"fwci":0.5305,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6896058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"105","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.996399998664856,"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/hessian-matrix","display_name":"Hessian matrix","score":0.8582340478897095},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.6665412783622742},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5850474238395691},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.5485979318618774},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5138604640960693},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.48661622405052185},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.47972503304481506},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.4713905453681946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46866998076438904},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.42684414982795715},{"id":"https://openalex.org/keywords/balanced-flow","display_name":"Balanced flow","score":0.4223664402961731},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3876194953918457},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32689395546913147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15008792281150818},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1436978578567505},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07597693800926208}],"concepts":[{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.8582340478897095},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.6665412783622742},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5850474238395691},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5485979318618774},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5138604640960693},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.48661622405052185},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.47972503304481506},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.4713905453681946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46866998076438904},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42684414982795715},{"id":"https://openalex.org/C167879884","wikidata":"https://www.wikidata.org/wiki/Q727568","display_name":"Balanced flow","level":2,"score":0.4223664402961731},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3876194953918457},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32689395546913147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15008792281150818},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1436978578567505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07597693800926208},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3489048.3530965","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3489048.3530965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstract Proceedings of the 2022 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/993c21a3-2063-4679-b136-ed65ac7fbedd","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/993c21a3-2063-4679-b136-ed65ac7fbedd","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Senen-Cerda, A & Sanders, J 2022, 'Asymptotic Convergence Rate of Dropout on Shallow Linear Neural Networks', pp. 105-106. https://doi.org/10.1145/3489048.3530965","raw_type":"conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W1499021337","https://openalex.org/W1576452626","https://openalex.org/W1591801644","https://openalex.org/W1608680948","https://openalex.org/W1826234144","https://openalex.org/W1904365287","https://openalex.org/W2095705004","https://openalex.org/W2136836265","https://openalex.org/W2152722485","https://openalex.org/W2163605009","https://openalex.org/W2164370980","https://openalex.org/W2294567968","https://openalex.org/W2582745083","https://openalex.org/W2594107056","https://openalex.org/W2746314669","https://openalex.org/W2803183915","https://openalex.org/W2806887204","https://openalex.org/W2911153392","https://openalex.org/W2928207644","https://openalex.org/W2952238132","https://openalex.org/W2962686221","https://openalex.org/W2962726660","https://openalex.org/W2963427613","https://openalex.org/W2963798770","https://openalex.org/W2963918617","https://openalex.org/W2964325005","https://openalex.org/W2964345061","https://openalex.org/W2979900602","https://openalex.org/W3005406397","https://openalex.org/W3007325053","https://openalex.org/W3034384909","https://openalex.org/W3057525668","https://openalex.org/W3100652838","https://openalex.org/W3106830411","https://openalex.org/W4288376397"],"related_works":["https://openalex.org/W2800988248","https://openalex.org/W4385064145","https://openalex.org/W4221162014","https://openalex.org/W2169345436","https://openalex.org/W2053964895","https://openalex.org/W2952728270","https://openalex.org/W4309210394","https://openalex.org/W2130502925","https://openalex.org/W3172664294","https://openalex.org/W3023967029"],"abstract_inverted_index":{"We":[0],"analyze":[1],"the":[2,79,86,89,103,111,117,119,123,126,143],"convergence":[3,100,112,144],"rate":[4,113],"of":[5,63,78,81,88,102,125],"gradient":[6,104],"flows":[7],"on":[8,70,110,116],"objective":[9],"functions":[10],"induced":[11],"by":[12],"Dropout":[13,38],"and":[14,73,106,122,146],"Dropconnect,":[15],"when":[16,149],"applying":[17],"them":[18],"to":[19,53,60,95,134,153],"shallow":[20],"linear":[21],"Neural":[22],"Networks":[23],"(NNs)":[24],"---which":[25],"can":[26],"also":[27],"be":[28],"viewed":[29],"as":[30,41,83,85],"doing":[31],"matrix":[32],"factorization":[33],"using":[34],"a":[35,67,75,98,108,154],"particular":[36],"regularizer.":[37],"algorithms":[39],"such":[40],"these":[42],"are":[43,93,138],"thus":[44],"regularization":[45],"techniques":[46],"that":[47,114],"use":[48],"{0,1}":[49],"-valued":[50],"random":[51],"variables":[52],"filter":[54],"weights":[55],"during":[56],"training":[57],"in":[58,139],"order":[59],"avoid":[61],"coadaptation":[62],"features.":[64],"By":[65],"leveraging":[66],"recent":[68],"result":[69],"nonconvex":[71],"optimization":[72],"conducting":[74],"careful":[76],"analysis":[77],"set":[80],"minimizers":[82],"well":[84],"Hessian":[87],"loss":[90],"function,":[91],"we":[92,129],"able":[94],"obtain":[96],"(i)":[97],"local":[99],"proof":[101],"flow":[105],"(ii)":[107],"bound":[109,133,145],"depends":[115],"data,":[118],"dropout":[120],"probability,":[121],"width":[124],"NN.":[127],"Finally,":[128],"compare":[130],"this":[131],"theoretical":[132],"numerical":[135],"simulations,":[136],"which":[137],"qualitative":[140],"agreement":[141],"with":[142],"match":[147],"it":[148],"starting":[150],"sufficiently":[151],"close":[152],"minimizer.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}