{"id":"https://openalex.org/W3217204128","doi":"https://doi.org/10.1109/tit.2022.3191747","title":"On the Rate of Convergence of a Classifier Based on a Transformer Encoder","display_name":"On the Rate of Convergence of a Classifier Based on a Transformer Encoder","publication_year":2022,"publication_date":"2022-07-22","ids":{"openalex":"https://openalex.org/W3217204128","doi":"https://doi.org/10.1109/tit.2022.3191747","mag":"3217204128"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2022.3191747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2022.3191747","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","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/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Iryna Gurevych","raw_affiliation_strings":["Ubiquitous Knowledge Processing (UKP) Laboratory, Technical University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing (UKP) Laboratory, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028420890","display_name":"Michael K\u00f6hler","orcid":"https://orcid.org/0000-0002-8372-9811"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Kohler","raw_affiliation_strings":["Fachbereich Mathematik, Technical University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Fachbereich Mathematik, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078696090","display_name":"G\u00f6zde G\u00fcl \u015eahin","orcid":"https://orcid.org/0000-0002-0332-1657"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gozde Gul Sahin","raw_affiliation_strings":["Ubiquitous Knowledge Processing (UKP) Laboratory, Technical University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing (UKP) Laboratory, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027450194"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.7954,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75467363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"68","issue":"12","first_page":"8139","last_page":"8155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.998199999332428,"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/T10320","display_name":"Neural Networks and Applications","score":0.998199999332428,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9842000007629395,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.9835000038146973,"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/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.673114001750946},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.655744731426239},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5667570233345032},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5416474938392639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5385284423828125},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45420122146606445},{"id":"https://openalex.org/keywords/margin-classifier","display_name":"Margin classifier","score":0.4355889558792114},{"id":"https://openalex.org/keywords/quadratic-classifier","display_name":"Quadratic classifier","score":0.4352206587791443},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36616379022598267},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10818672180175781}],"concepts":[{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.673114001750946},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.655744731426239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5667570233345032},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5416474938392639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5385284423828125},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45420122146606445},{"id":"https://openalex.org/C173102733","wikidata":"https://www.wikidata.org/wiki/Q6760396","display_name":"Margin classifier","level":3,"score":0.4355889558792114},{"id":"https://openalex.org/C52620605","wikidata":"https://www.wikidata.org/wiki/Q7268357","display_name":"Quadratic classifier","level":3,"score":0.4352206587791443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36616379022598267},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10818672180175781},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tit.2022.3191747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2022.3191747","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:133544","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/133544/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Artikel"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1484867920","https://openalex.org/W1542886316","https://openalex.org/W1564947197","https://openalex.org/W2006783977","https://openalex.org/W2012247578","https://openalex.org/W2170240176","https://openalex.org/W2528305538","https://openalex.org/W2559431973","https://openalex.org/W2596625124","https://openalex.org/W2626778328","https://openalex.org/W2742947407","https://openalex.org/W2884001105","https://openalex.org/W2895992958","https://openalex.org/W2896457183","https://openalex.org/W2946302218","https://openalex.org/W2950533765","https://openalex.org/W2952226704","https://openalex.org/W2963012544","https://openalex.org/W2963264710","https://openalex.org/W2980708516","https://openalex.org/W2982042286","https://openalex.org/W2995744795","https://openalex.org/W3000236721","https://openalex.org/W3049467969","https://openalex.org/W3099710307","https://openalex.org/W3102087799","https://openalex.org/W3104035369","https://openalex.org/W3183760470","https://openalex.org/W3201938571","https://openalex.org/W3204236384","https://openalex.org/W4249716558","https://openalex.org/W4286909008","https://openalex.org/W4322614761","https://openalex.org/W4385245566","https://openalex.org/W6685053522","https://openalex.org/W6739901393","https://openalex.org/W6748059092","https://openalex.org/W6755207826","https://openalex.org/W6755463368","https://openalex.org/W6764621852","https://openalex.org/W6769390014","https://openalex.org/W6771550025","https://openalex.org/W6772532777","https://openalex.org/W6796886481","https://openalex.org/W6798311916","https://openalex.org/W6801823388"],"related_works":["https://openalex.org/W2162083125","https://openalex.org/W1483596504","https://openalex.org/W2009506202","https://openalex.org/W58702947","https://openalex.org/W47559851","https://openalex.org/W2297694731","https://openalex.org/W204488290","https://openalex.org/W2096969571","https://openalex.org/W2040550925","https://openalex.org/W2112112609"],"abstract_inverted_index":{"Pattern":[0],"recognition":[1],"based":[2,15],"on":[3,16],"a":[4,17,54,58],"high-dimensional":[5],"predictor":[6],"is":[7,11,14,36,39,44,82],"considered.":[8],"A":[9],"classifier":[10,30,43],"defined":[12],"which":[13],"Transformer":[18,68],"encoder.":[19],"The":[20],"rate":[21],"of":[22,24,28,50,86],"convergence":[23],"the":[25,29,32,48,53,64,67,76],"misclassification":[26,34],"probability":[27,35,56],"towards":[31],"optimal":[33],"analyzed.":[37],"It":[38],"shown":[40],"that":[41],"this":[42,73],"able":[45],"to":[46],"circumvent":[47],"curse":[49],"dimensionality":[51],"provided":[52],"posteriori":[55],"satisfies":[57],"suitable":[59],"hierarchical":[60],"composition":[61],"model.":[62],"Furthermore,":[63],"difference":[65],"between":[66],"classifiers":[69],"theoretically":[70],"analyzed":[71],"in":[72,79,89],"paper":[74],"and":[75],"ones":[77],"used":[78],"practice":[80],"today":[81],"illustrated":[83],"by":[84],"means":[85],"classification":[87],"problems":[88],"natural":[90],"language":[91],"processing.":[92]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-02-26T08:16:20.718346","created_date":"2025-10-10T00:00:00"}