{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:40:48Z","timestamp":1773376848474,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T00:00:00Z","timestamp":1720310400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T00:00:00Z","timestamp":1720310400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CNS-1955997,CCF-2046018,DMS-2210368,CCF-2308446"],"award-info":[{"award-number":["CNS-1955997,CCF-2046018,DMS-2210368,CCF-2308446"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"AFOSR","doi-asserted-by":"publisher","award":["FA9550-23-1-0301"],"award-info":[{"award-number":["FA9550-23-1-0301"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,7]]},"DOI":"10.1109\/isit57864.2024.10619279","type":"proceedings-article","created":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T13:25:01Z","timestamp":1724073901000},"page":"2688-2693","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Generalization Bounds for Deep Neural Networks"],"prefix":"10.1109","author":[{"given":"Haiyun","family":"He","sequence":"first","affiliation":[{"name":"Cornell University,Center for Applied Mathematics,Ithaca,NY,USA"}]},{"given":"Christina Lee","family":"Yu","sequence":"additional","affiliation":[{"name":"School of ORIE, Cornell University,Ithaca,NY,USA"}]},{"given":"Ziv","family":"Goldfeld","sequence":"additional","affiliation":[{"name":"School of ECE, Cornell University,Ithaca,NY,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaz007"},{"key":"ref2","first-page":"5949","article-title":"Exploring generalization in deep learning","volume":"30","author":"Neyshabur","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","first-page":"888","article-title":"Fisher-Rao metric, geometry, and complexity of neural networks","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics","author":"Liang","year":"2019"},{"key":"ref4","first-page":"254","article-title":"Stronger generalization bounds for deep nets via a compression approach","volume-title":"International Conference on Machine Learning","author":"Arora","year":"2018"},{"key":"ref5","article-title":"Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data","volume-title":"Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence, UAI 2017","author":"Dziugaite","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279989"},{"key":"ref7","first-page":"164","article-title":"PAC-Bayesian model averaging","volume-title":"Proceedings of the 12th Annual Conference on Computational Learning Theory","year":"1999"},{"key":"ref8","article-title":"A PAC-Bayesian approach to spectrally-normalized margin bounds for neural networks","volume-title":"International Conference on Learning Representations","author":"Neyshabur","year":"2018"},{"key":"ref9","article-title":"Non-vacuous generalization bounds at the imagenet scale: a PAC-Bayesian compression approach","volume-title":"International Conference on Learning Representations","author":"Zhou","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.1.1"},{"key":"ref11","first-page":"1019","article-title":"Sharp minima can generalize for deep nets","volume-title":"International Conference on Machine Learning","author":"Dinh","year":"2017"},{"key":"ref12","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"International Conference on Learning Representations","author":"Keskar","year":"2017"},{"key":"ref13","article-title":"Towards understanding generalization of deep learning: Perspective of loss landscapes","volume-title":"ICML 2017 Workshop on Principled Approaches to Deep Learning","author":"Wu","year":"2017"},{"issue":"1","key":"ref14","first-page":"2822","article-title":"The implicit bias of gradient descent on separable data","volume":"19","author":"Soudry","year":"2018","journal-title":"The Journal of Machine Learning Research"},{"key":"ref15","article-title":"A Bayesian perspective on generalization and stochastic gradient descent","volume-title":"International Conference on Learning Representations","author":"Smith","year":"2018"},{"key":"ref16","author":"Chatterjee","year":"2022","journal-title":"On the generalization mystery in deep learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73074-5_5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1017\/9781009025096.003"},{"key":"ref20","article-title":"Information-theoretic analysis of generalization capability of learning algorithms","volume":"30","author":"Xu","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2945779"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2991139"},{"key":"ref23","first-page":"7234","article-title":"Chaining mutual information and tightening generalization bounds","author":"Asadi","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","first-page":"4212","article-title":"Chained generalisation bounds","volume-title":"Conference on Learning Theory","author":"Clerico","year":"2022"},{"key":"ref25","article-title":"Conditioning and processing: Techniques to improve information-theoretic generalization bounds","volume":"33","author":"Hafez-Kolahi","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","article-title":"Sharpened generalization bounds based on conditional mutual information and an application to noisy, iterative algorithms","author":"Haghifam","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","first-page":"3437","article-title":"Reasoning about generalization via conditional mutual information","volume-title":"Conference on Learning Theory","author":"Steinke","year":"2020"},{"key":"ref28","first-page":"24670","article-title":"Information-theoretic generalization bounds for black-box learning algorithms","volume":"34","author":"Harutyunyan","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2021.3085190"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/jsait.2024.3391900\/mm1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT45174.2021.9518043"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849359"},{"issue":"139","key":"ref33","first-page":"1","article-title":"Chaining meets chain rule: Multilevel entropic regularization and training of neural networks","volume":"21","author":"Asadi","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref34","author":"He","year":"2024","journal-title":"Information-theoretic generalization bounds for deep neural networks"},{"key":"ref35","first-page":"6306","article-title":"Neural discrete representation learning","volume":"30","author":"van den Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.2307\/1403865"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/058"},{"key":"ref38","first-page":"26:1","article-title":"Generalization bounds for noisy iterative algorithms using properties of additive noise channels","volume":"24","author":"Wang","year":"2023","journal-title":"Journal of machine learning research"}],"event":{"name":"2024 IEEE International Symposium on Information Theory (ISIT)","location":"Athens, Greece","start":{"date-parts":[[2024,7,7]]},"end":{"date-parts":[[2024,7,12]]}},"container-title":["2024 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10619013\/10619074\/10619279.pdf?arnumber=10619279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:28:42Z","timestamp":1773347322000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10619279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,7]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/isit57864.2024.10619279","relation":{},"subject":[],"published":{"date-parts":[[2024,7,7]]}}}