{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T10:16:15Z","timestamp":1774260975852,"version":"3.50.1"},"reference-count":34,"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":[{"name":"Australian Research Council Project","award":["FL170100117"],"award-info":[{"award-number":["FL170100117"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tnnls.2023.3297113","type":"journal-article","created":{"date-parts":[[2023,8,16]],"date-time":"2023-08-16T17:32:47Z","timestamp":1692207167000},"page":"16683-16695","source":"Crossref","is-referenced-by-count":10,"title":["Going Deeper, Generalizing Better: An Information-Theoretic View for Deep Learning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1681-6608","authenticated-orcid":false,"given":"Jingwei","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, School of Engineering, The Hong Kong University of Science and Technology, Sai Kung, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9640-6472","authenticated-orcid":false,"given":"Tongliang","family":"Liu","sequence":"additional","affiliation":[{"name":"Sydney AI Centre, the chool of Computer Science, and the Faculty of Engineering, The Univerity of Sydney, Darlington, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Sydney AI Centre, the chool of Computer Science, and the Faculty of Engineering, The Univerity of Sydney, Darlington, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"231","article-title":"A unified bias-variance decomposition","volume-title":"Proc. 17th Int. Conf. Mach. Learn.","author":"Domingos"},{"key":"ref2","article-title":"Neural network with unbounded activation functions is universal approximator","author":"Sonoda","year":"2015","journal-title":"arXiv:1505.03654"},{"key":"ref3","first-page":"2635","article-title":"Learnability, stability and uniform convergence","volume":"11","author":"Shalev-Shwartz","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0745-0_2"},{"key":"ref5","first-page":"295","article-title":"Computing with infinite networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Williams"},{"key":"ref6","first-page":"336","article-title":"Computing with finite and infinite networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Winther"},{"key":"ref7","volume-title":"Bayesian Learning for Neural Networks","volume":"118","author":"Neal","year":"2012"},{"key":"ref8","article-title":"Deep neural networks as Gaussian processes","author":"Lee","year":"2018","journal-title":"arXiv:1711.00165"},{"key":"ref9","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":"ref10","article-title":"Gradient descent provably optimizes over-parameterized neural networks","author":"Du","year":"2018","journal-title":"arXiv:1810.02054"},{"key":"ref11","first-page":"8157","article-title":"Learning overparameterized neural networks via stochastic gradient descent on structured data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref12","article-title":"Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks","author":"Arora","year":"2019","journal-title":"arXiv:1901.08584"},{"key":"ref13","first-page":"1675","article-title":"Gradient descent finds global minima of deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du"},{"key":"ref14","article-title":"Learning and generalization in overparameterized neural networks, going beyond two layers","author":"Allen-Zhu","year":"2018","journal-title":"arXiv:1811.04918"},{"key":"ref15","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Allen-Zhu"},{"key":"ref16","article-title":"Stochastic gradient descent optimizes over-parameterized deep ReLU networks","author":"Zou","year":"2018","journal-title":"arXiv:1811.08888"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.spa.2019.06.003"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1806579115"},{"key":"ref19","first-page":"3036","article-title":"On the global convergence of gradient descent for over-parameterized models using optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chizat"},{"key":"ref20","first-page":"11611","article-title":"Uniform convergence may be unable to explain generalization in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nagarajan"},{"key":"ref21","first-page":"19","article-title":"Algorithmic stability and uniform generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alabdulmohsin"},{"key":"ref22","article-title":"How much does your data exploration overfit? Controlling bias via information usage","author":"Russo","year":"2015","journal-title":"arXiv:1511.05219"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2016.7606789"},{"key":"ref24","first-page":"2524","article-title":"Information-theoretic analysis of generalization capability of learning algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Xu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437571"},{"key":"ref26","first-page":"1","article-title":"Chaining mutual information and tightening generalization bounds","volume":"31","author":"Asadi","year":"2018","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref27","first-page":"2299","article-title":"Estimating information flow in deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goldfeld"},{"key":"ref28","article-title":"Opening the black box of deep neural networks via information","author":"Shwartz-Ziv","year":"2017","journal-title":"arXiv:1703.00810"},{"key":"ref29","first-page":"3438","article-title":"Invariance principle meets information bottleneck for out-of-distribution generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ahuja"},{"key":"ref30","first-page":"11608","article-title":"Using sliced mutual information to study memorization and generalization in deep neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Wongso"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/047174882x"},{"key":"ref32","first-page":"1067","article-title":"Gradient descent can take exponential time to escape saddle points","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Du","year":"2017"},{"key":"ref33","volume-title":"Foundations of Machine Learning","author":"Mohri","year":"2012"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160360204"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10737991\/10221723.pdf?arnumber=10221723","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T16:49:44Z","timestamp":1732726184000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10221723\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":34,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3297113","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}