{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T06:45:21Z","timestamp":1769064321202,"version":"3.49.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Harvard FAS Dean\u2019s Fund for Promising Scholarship"},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1718698"],"award-info":[{"award-number":["CCF-1718698"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1910410"],"award-info":[{"award-number":["CCF-1910410"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/tit.2022.3217698","type":"journal-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:26:08Z","timestamp":1667517968000},"page":"1932-1964","source":"Crossref","is-referenced-by-count":42,"title":["Universality Laws for High-Dimensional Learning With Random Features"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5162-0459","authenticated-orcid":false,"given":"Hong","family":"Hu","sequence":"first","affiliation":[{"name":"John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5174-2595","authenticated-orcid":false,"given":"Yue M.","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Statistics and Data Science, University of Pennsylvania, Philadelphia, PA, USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1177","article-title":"Random features for large-scale kernel machines","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rahimi"},{"key":"ref2","first-page":"2253","article-title":"Toward deeper understanding of neural networks: The power of initialization and a dual view on expressivity","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Daniely"},{"key":"ref3","first-page":"2422","article-title":"SGD learns the conjugate kernel class of the network","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Daniely"},{"issue":"1","key":"ref4","first-page":"714","article-title":"On the equivalence between kernel quadrature rules and random feature expansions","volume":"18","author":"Bach","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","first-page":"8571","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jacot"},{"key":"ref6","article-title":"To understand deep learning we need to understand kernel learning","author":"Belkin","year":"2018","journal-title":"arXiv:1802.01396"},{"key":"ref7","article-title":"Random features for kernel approximation: A survey on algorithms, theory, and beyond","author":"Liu","year":"2020","journal-title":"arXiv:2004.11154"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1214\/17-AAP1328"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1214\/21-aos2133"},{"key":"ref10","article-title":"The generalization error of random features regression: Precise asymptotics and double descent curve","author":"Mei","year":"2019","journal-title":"arXiv:1908.05355"},{"key":"ref11","article-title":"The generalization error of max-margin linear classifiers: High-dimensional asymptotics in the overparametrized regime","author":"Montanari","year":"2019","journal-title":"arXiv:1911.01544"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1103\/physrevx.10.041044"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac3ae6"},{"key":"ref14","article-title":"The Gaussian equivalence of generative models for learning with shallow neural networks","author":"Goldt","year":"2020","journal-title":"arXiv:2006.14709"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1214\/20-aos1990"},{"key":"ref16","first-page":"1","article-title":"Generalization of two-layer neural networks: An asymptotic viewpoint","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ba"},{"key":"ref17","article-title":"A precise performance analysis of learning with random features","author":"Dhifallah","year":"2020","journal-title":"arXiv:2008.11904"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF02759761"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2840720"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-012-9135-7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iau005"},{"key":"ref22","article-title":"Random matrix theory proves that deep learning representations of GAN-data behave as Gaussian mixtures","author":"El Amine Seddik","year":"2020","journal-title":"arXiv:2001.08370"},{"key":"ref23","article-title":"On the inherent regularization effects of noise injection during training","author":"Dhifallah","year":"2021","journal-title":"arXiv:2102.07379"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac9825"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1142\/S201032631350010X"},{"key":"ref26","first-page":"2637","article-title":"Nonlinear random matrix theory for deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pennington"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1142\/0271"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF01494395"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s00440-016-0754-9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iax011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2112231"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006947"},{"key":"ref33","first-page":"3381","article-title":"A universal analysis of large-scale regularized least squares solutions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Panahi"},{"key":"ref34","first-page":"12372","article-title":"Universality in learning from linear measurements","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Abbasi"},{"key":"ref35","article-title":"Gaussian universality of linear classifiers with random labels in high-dimension","author":"Gerace","year":"2022","journal-title":"arXiv:2205.13303"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3714013"},{"key":"ref37","article-title":"High-dimensional asymptotics of feature learning: How one gradient step improves the representation","author":"Ba","year":"2022","journal-title":"arXiv:2205.01445"},{"key":"ref38","article-title":"Universality of empirical risk minimization","author":"Montanari","year":"2022","journal-title":"arXiv:2202.08832"},{"key":"ref39","article-title":"An equivalence principle for the spectrum of random inner-product kernel matrices","author":"Lu","year":"2022","journal-title":"arXiv:2205.06308"},{"key":"ref40","article-title":"Spectrum of inner-product kernel matrices in the polynomial regime and multiple descent phenomenon in kernel ridge regression","author":"Misiakiewicz","year":"2022","journal-title":"arXiv:2204.10425"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ad01b7"},{"key":"ref42","article-title":"Sharp asymptotics of kernel ridge regression beyond the linear regime","author":"Hu","year":"2022","journal-title":"arXiv:2205.06798"},{"key":"ref43","first-page":"583","article-title":"A bound for the error in the normal approximation to the distribution of a sum of dependent random variables","volume-title":"Proc. 6th Berkeley Symp. Math. Statist. Probab.","volume":"2","author":"Stein"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1142\/LNIMSNUS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15007-4"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199535255.001.0001"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1017\/9781108231596"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15202-3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-56468-0"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/18\/10046300\/9931146-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/18\/10046300\/09931146.pdf?arnumber=9931146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:18:45Z","timestamp":1705961925000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9931146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":49,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tit.2022.3217698","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"value":"0018-9448","type":"print"},{"value":"1557-9654","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}