{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:52:26Z","timestamp":1768438346649,"version":"3.49.0"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/tit.2022.3191747","type":"journal-article","created":{"date-parts":[[2022,7,22]],"date-time":"2022-07-22T16:41:33Z","timestamp":1658508093000},"page":"8139-8155","source":"Crossref","is-referenced-by-count":6,"title":["On the Rate of Convergence of a Classifier Based on a Transformer Encoder"],"prefix":"10.1109","volume":"68","author":[{"given":"Iryna","family":"Gurevych","sequence":"first","affiliation":[{"name":"Ubiquitous Knowledge Processing (UKP) Laboratory, Technical University of Darmstadt, Darmstadt, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8372-9811","authenticated-orcid":false,"given":"Michael","family":"Kohler","sequence":"additional","affiliation":[{"name":"Fachbereich Mathematik, Technical University of Darmstadt, Darmstadt, Germany"}]},{"given":"Gozde Gul","family":"Sahin","sequence":"additional","affiliation":[{"name":"Ubiquitous Knowledge Processing (UKP) Laboratory, Technical University of Darmstadt, Darmstadt, Germany"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/b97848"},{"key":"ref11","first-page":"869","article-title":"Deep neural networks learn non-smooth functions effectively","author":"imaizumi","year":"2019","journal-title":"Proc 22nd Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmva.2014.08.008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2634401"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1214\/19-AOS1912"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1214\/20-AOS2034"},{"key":"ref16","article-title":"Universal approximation under constraints is possible with transformers","author":"kratsios","year":"2021","journal-title":"arXiv 2110 03303"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmva.2020.104695"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmva.2020.104696"},{"key":"ref19","article-title":"Deep network approximation for smooth functions","author":"lu","year":"2020","journal-title":"arXiv 2001 03040"},{"key":"ref28","first-page":"1","article-title":"Are transformers universal approximators of sequence-to-sequence functions?","author":"yun","year":"2019","journal-title":"Proc Workshop Mach Learn Guarantees (NeurIPS)"},{"key":"ref4","article-title":"The smoking gun: Statistical theory improves neural network estimates","author":"braun","year":"2021","journal-title":"arXiv 2107 09550"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"ref3","first-page":"1","article-title":"Nearly-tight VC-dimension bounds for piecewise linear neural networks","volume":"20","author":"bartlett","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref6","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref29","first-page":"649","article-title":"Character-level convolutional networks for text classification","volume":"28","author":"zhang","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"413","article-title":"Rates of convergence of nearest neighbor procedures","author":"cover","year":"1968","journal-title":"Proc Hawaii Int Conf Syst Sci"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0711-5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/BF00531618"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1214\/18-AOS1747"},{"key":"ref9","article-title":"Random feature neural networks learn black-scholes type PDEs without curse of dimensionality","author":"gonon","year":"2021","journal-title":"arXiv 2106 08900"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511624216"},{"key":"ref20","first-page":"1875","article-title":"Nonparametric regression using deep neural networks with ReLU activation function (with discussion)","volume":"48","author":"schmidt-hieber","year":"2020","journal-title":"Ann Statist"},{"key":"ref22","article-title":"Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: Optimal rate and curse of dimensionality","author":"suzuki","year":"2018","journal-title":"arXiv 1810 08033"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"ref24","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"arXiv 1706 03762"},{"key":"ref23","article-title":"Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space","author":"suzuki","year":"2019","journal-title":"arXiv 1910 12799"},{"key":"ref26","first-page":"13005","article-title":"The phase diagram of approximation rates for deep neural networks","volume":"33","author":"yarotsky","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.07.002"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/18\/9961124\/09837831.pdf?arnumber=9837831","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:11:42Z","timestamp":1670872302000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9837831\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":29,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tit.2022.3191747","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"value":"0018-9448","type":"print"},{"value":"1557-9654","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}