{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:33:37Z","timestamp":1781886817065,"version":"3.54.5"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Commission","doi-asserted-by":"publisher","award":["JCYJ20220530143002005"],"award-info":[{"award-number":["JCYJ20220530143002005"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Ubiquitous Data Enabling Key Lab","award":["ZDSYS20220527171406015"],"award-info":[{"award-number":["ZDSYS20220527171406015"]}]},{"DOI":"10.13039\/100018913","name":"Tsinghua Shenzhen International Graduate School Startup fund","doi-asserted-by":"publisher","award":["QD2022024C"],"award-info":[{"award-number":["QD2022024C"]}],"id":[{"id":"10.13039\/100018913","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tai.2024.3409673","type":"journal-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T14:14:47Z","timestamp":1717596887000},"page":"5519-5529","source":"Crossref","is-referenced-by-count":11,"title":["Exploring Weight Distributions and Dependence in Neural Networks With $\\alpha$-Stable Distributions"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8035-6987","authenticated-orcid":false,"given":"Jipeng","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4706-3099","authenticated-orcid":false,"given":"Xueqiong","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tsinghua Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2608-8034","authenticated-orcid":false,"given":"Ercan Engin","family":"Kuruoglu","sequence":"additional","affiliation":[{"name":"Tsinghua Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"134","article-title":"For valid generalization the size of the weights is more important than the size of the network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"9","author":"Bartlett","year":"1996"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001421520212"},{"key":"ref3","first-page":"950","article-title":"A simple weight decay can improve generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"4","author":"Krogh","year":"1991"},{"key":"ref4","first-page":"1058","article-title":"Regularization of neural networks using DropConnect","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wan","year":"2013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2063-6_214"},{"key":"ref6","first-page":"29364","article-title":"Heavy tails in SGD and compressibility of overparametrized neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Barsbey","year":"2021"},{"key":"ref7","article-title":"Bayesian neural network priors revisited","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fortuin","year":"2021"},{"key":"ref8","volume-title":"Theorie de l\u2019addition des Variables Aleatoires [Combination Theory of Unpredictable Variables]","author":"L\u00e9vy","year":"1937"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-020-01708-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-5316(99)00070-X"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534068"},{"key":"ref12","first-page":"1192","article-title":"Revisiting weight initialization of deep neural networks","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Skorski","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.crma.2009.01.013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/03610926.2012.730167"},{"key":"ref15","first-page":"729","article-title":"Analytical representation for positive alpha-stable densities","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Hong Kong","author":"Kuruoglu","year":"2003"},{"key":"ref16","first-page":"163","article-title":"Optimization and global minimization methods suitable for neural networks","volume":"2","author":"Duch","year":"1998","journal-title":"Neural Comput. Surv."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1990.137819"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/72.143378"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/72.914538"},{"key":"ref20","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Glorot","year":"2010"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.05.054"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/377939.377946"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-021-10728-y"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/wcs.72"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.3.448"},{"key":"ref27","article-title":"Deep neural networks as Gaussian processes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","year":"2018"},{"key":"ref28","article-title":"Gaussian process behaviour in wide deep neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Matthews","year":"2018"},{"key":"ref29","article-title":"Deep convolutional networks as shallow Gaussian processes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Garriga-Alonso","year":"2018"},{"key":"ref30","volume-title":"Bayesian Learning for Neural Networks","volume":"118","author":"Neal","year":"2012"},{"key":"ref31","article-title":"Beyond Gaussian processes: On the distributions of infinite networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"18","author":"Der","year":"2005"},{"key":"ref32","first-page":"1137","article-title":"Stable behaviour of infinitely wide deep neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Peluchetti","year":"2020"},{"issue":"1","key":"ref33","first-page":"7479","article-title":"Implicit self-regularization in deep neural networks: Evidence from random matrix theory and implications for learning","volume":"22","author":"Martin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","first-page":"16305","article-title":"Rethinking the pruning criteria for convolutional neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Huang","year":"2021"},{"issue":"318","key":"ref35","first-page":"399","article-title":"On the Kolmogorov-Smirnov test for normality with mean and variance unknown","volume-title":"J. Amer. Statist. Assoc.","volume":"62","author":"Lilliefors","year":"1967"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-74690-6_24"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-52915-4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/78.950775"},{"key":"ref39","article-title":"Stable non-Gaussian random processes: Stochastic models with infinite variance","volume-title":"J. Amer. Statist. Assoc.","volume":"90","author":"Samorodnitsky","year":"1995"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.2001.0390"},{"key":"ref41","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky","year":"2012"},{"key":"ref42","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Representations (ICLR)","author":"Simonyan","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref47","article-title":"CASIAWebFace: Learning face representation from scratch","author":"Yi","year":"2014"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref50","first-page":"4629","article-title":"What are Bayesian neural network posteriors really like?\u201d","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Izmailov","year":"2021"},{"key":"ref51","article-title":"On the heavy-tailed theory of stochastic gradient descent for deep neural networks","author":"Simsekli","year":"2019"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/10751744\/10549953.pdf?arnumber=10549953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:14Z","timestamp":1755911354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10549953\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":51,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3409673","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}