{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T21:47:13Z","timestamp":1778881633049,"version":"3.51.4"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825094","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"3831-3837","source":"Crossref","is-referenced-by-count":7,"title":["Mitigating Gradient Overlap in Deep Residual Networks with Gradient Normalization for Improved Non-Convex Optimization"],"prefix":"10.1109","author":[{"given":"Juyoung","family":"Yun","sequence":"first","affiliation":[{"name":"Stony Brook University,Department of Computer Science,New York,United States,11794"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajpath.2020.03.012"},{"key":"ref3","article-title":"Resnet and its application to medical image processing: Research progress and challenges","volume-title":"Computer Methods and Programs in Biomedicine","volume":"240","author":"Xu","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIHI57871.2023.10489521"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3613917.3613922"},{"key":"ref6","first-page":"342","article-title":"The shattered gradients problem: if resnets are the answer, then what is the question?","volume-title":"Proceedings of the 34th International Conference on Machine Learning","volume":"70","author":"Balduzzi"},{"key":"ref7","article-title":"Znorm: Z-score gradient normalization for deep neural networks","author":"Yun","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref10","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"International Conference on Learning Representations (ICLR)","author":"Simonyan"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref15","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref16","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","author":"Duchi","year":"2011"},{"key":"ref17","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","author":"Tieleman","year":"2012"},{"key":"ref18","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"Ioffe"},{"key":"ref19","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref21","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","volume-title":"Advances in Neural Information Processing Systems","author":"Salimans"},{"key":"ref22","article-title":"Micro-batch training with batch-channel normalization and weight standardization","author":"Qiao","year":"2019"},{"key":"ref23","article-title":"On the difficulty of training recurrent neural networks","author":"Pascanu","year":"2013"},{"key":"ref24","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref25","article-title":"Stochgradadam: Accelerating neural networks training with stochastic gradient sampling","volume":"v3","author":"Yun","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_37"},{"key":"ref27","first-page":"6391","article-title":"Visualizing the loss landscape of neural nets","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Li"},{"key":"ref28","first-page":"342","article-title":"The shattered gradients problem: if resnets are the answer, then what is the question?","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"Balduzzi"},{"key":"ref29","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009","journal-title":"Tech. Rep."},{"key":"ref30","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","author":"Tieleman","year":"2012"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","location":"Washington, DC, USA","start":{"date-parts":[[2024,12,15]]},"end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825094.pdf?arnumber=10825094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:14:13Z","timestamp":1737101653000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825094\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825094","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}