{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T15:29:33Z","timestamp":1759937373854,"version":"3.43.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12301651","62376104","62306338","12426512","62122035","61972188"],"award-info":[{"award-number":["12301651","62376104","62306338","12426512","62122035","61972188"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for the Central Universities of China","doi-asserted-by":"publisher","award":["2662024XXPY001"],"award-info":[{"award-number":["2662024XXPY001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tnnls.2025.3526235","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T13:55:47Z","timestamp":1737554147000},"page":"14596-14610","source":"Crossref","is-referenced-by-count":2,"title":["Generalization Bounds of Deep Neural Networks With \u03c4-Mixing Samples"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4046-9650","authenticated-orcid":false,"given":"Liyuan","family":"Liu","sequence":"first","affiliation":[{"name":"College of Informatics, Huazhong Agricultural University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3308-9174","authenticated-orcid":false,"given":"Yaohui","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Engineering, Huazhong Agricultural University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8444-9782","authenticated-orcid":false,"given":"Weifu","family":"Li","sequence":"additional","affiliation":[{"name":"College of Informatics, Huazhong Agricultural University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1054-4197","authenticated-orcid":false,"given":"Yingjie","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, China University of Petroleum (East China), Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7165-3143","authenticated-orcid":false,"given":"Bin","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9084-5482","authenticated-orcid":false,"given":"Hong","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Informatics, Huazhong Agricultural University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Estimating the generalization performance of a SVM efficiently","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Joachims","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/307400.307435"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007618624809"},{"key":"ref5","first-page":"499","article-title":"Stability and generalization","volume":"2","author":"Bousquet","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979228"},{"key":"ref7","article-title":"Understanding training and generalization in deep learning by Fourier analysis","author":"John Xu","year":"2018","journal-title":"arXiv:1808.04295"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5268-1"},{"key":"ref9","article-title":"Approximation and estimation for high-dimensional deep learning networks","author":"Barron","year":"2018","journal-title":"arXiv:1809.03090"},{"key":"ref10","first-page":"1","article-title":"Spectrally-normalized margin bounds for neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bartlett"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaz007"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1214\/18-aos1747"},{"key":"ref13","first-page":"1376","article-title":"Norm-based capacity control in neural networks","volume-title":"Proc. Conf. Learn. Theory","author":"Neyshabur"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1214\/19-aos1875"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339576"},{"key":"ref16","first-page":"943","article-title":"The geometrical ergodicity of nonlinear autoregressive models","volume":"6","author":"An","year":"1996","journal-title":"Statistica Sinica"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5104-z"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconom.2005.03.004"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1214\/19-AOS1840"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5588-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3371025"},{"key":"ref22","article-title":"Generalization error bounds on deep learning with Markov datasets","author":"Truong","year":"2021","journal-title":"arXiv:2201.11059"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1015362183"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1080\/07350015.2021.1899933"},{"key":"ref25","first-page":"1","article-title":"Theoretical analysis of deep neural networks for temporally dependent observations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10959-004-0578-x"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconom.2022.07.001"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1080\/10485252.2023.2241572"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s00180-023-01434-5"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027613"},{"key":"ref31","first-page":"1","article-title":"Generalization and estimation error bounds for model-based neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Shultzman"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3150\/18-bej1095"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1022677271"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2868980"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2951788"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01585"},{"issue":"312","key":"ref37","first-page":"1","article-title":"Nystr\u00f6m regularization for time series forecasting","volume":"23","author":"Sun","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3103\/S1066530709010049"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s004400050094"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s00440-004-0394-3"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1137\/1109020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.26637\/mjm904\/009"},{"issue":"1","key":"ref43","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1214\/20-EJS1758"},{"key":"ref45","first-page":"1802","article-title":"Parameter-free online convex optimization with sub-exponential noise","volume-title":"Proc. Conf. Learn. Theory","author":"Jun"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2003.813564"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511618796"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1006\/jcom.2002.0635"},{"key":"ref49","first-page":"1","article-title":"Multiplicative noise and heavy tails in stochastic optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hodgkinson"},{"key":"ref50","first-page":"1","article-title":"The heavy-tail phenomenon in SGD","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gurbuzbalaban"},{"key":"ref51","article-title":"On the noisy gradient descent that generalizes as SGD","author":"Wu","year":"2019","journal-title":"arXiv:1906.07405"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.2307\/3213710"},{"volume-title":"Mixing: Properties and Examples","year":"2012","author":"Doukhan","key":"ref53"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.2478\/demo-2013-0004"},{"key":"ref55","first-page":"1","article-title":"Inductive biases and variable creation in self-attention mechanisms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Edelman"},{"key":"ref56","first-page":"1","article-title":"Transformers as algorithms: Generalization and stability in in-context learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref57","article-title":"A mathematical theory of attention","author":"Vuckovic","year":"2020","journal-title":"arXiv:2007.02876"},{"key":"ref58","first-page":"1","article-title":"Signal propagation in transformers: Theoretical perspectives and the role of rank collapse","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Noci"},{"key":"ref59","article-title":"Are transformers universal approximators of sequence-to-sequence functions?","author":"Yun","year":"2019","journal-title":"arXiv:1912.10077"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11114436\/10848487.pdf?arnumber=10848487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:01:11Z","timestamp":1754503271000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848487\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":59,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3526235","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}