{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T16:58:55Z","timestamp":1791046735905,"version":"4.1.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892245","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"01-08","source":"Crossref","is-referenced-by-count":6,"title":["Perturbed Gradients Updating within Unit Space for Deep Learning"],"prefix":"10.1109","author":[{"given":"Ching-Hsun","family":"Tseng","sequence":"first","affiliation":[{"name":"The University of Manchester,Department of Computer Science,Manchester,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsueh-Cheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Taiwan Semi-condoctor Manufacturing Co., Ltd,Department of Computer-Intergrated Manufacturing,Hinschu,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shin-Jye","family":"Lee","sequence":"additional","affiliation":[{"name":"Institute of Management of Technology National Yang Ming Chiao Tung University,Hinschu,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Zeng","sequence":"additional","affiliation":[{"name":"The University of Manchester,Department of Computer Science,Manchester,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref38","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref33","article-title":"Visualizing the loss landscape of neural nets","author":"li","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref32","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref31","first-page":"13","author":"tibshirani","year":"2016","journal-title":"Duality Uses and Correspondences"},{"key":"ref30","first-page":"13153","article-title":"A simple baseline for bayesian uncertainty in deep learning","volume":"32","author":"maddox","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"An image is worth 16&#x00D7;16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref34","article-title":"UPANets: Learning from the Universal Pixel Attention Networks","author":"tseng","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref10","article-title":"Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data","author":"dziugaite","year":"0","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"Generalization bounds for deep convolutional neural networks","author":"long","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref12","article-title":"Deterministic PAC-bayesian generalization bounds for deep networks via generalizing noise-resilience","author":"nagarajan","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref13","article-title":"Exploring generalization in deep learning","volume":"30","author":"neyshabur","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Data-dependent sample complexity of deep neural networks via lipschitz augmentation","volume":"32","author":"wei","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"foret","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref16","first-page":"529","article-title":"Simplifying neural nets by discovering flat minima","author":"hochreiter","year":"1995","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"1019","article-title":"Sharp minima can generalize for deep nets","author":"dinh","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00806"},{"key":"ref19","article-title":"Averaging weights leads to wider optima and better generalization","author":"izmailov","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref28","first-page":"7015","article-title":"SWALP: Stochastic weight averaging in low precision training","author":"yang","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref4","article-title":"Deep learning without poor local minima","author":"kawaguchi","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref27","article-title":"Deep learning with elastic averaging SGD","volume":"28","author":"zhang","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/9781108690935"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab39d9"},{"key":"ref29","article-title":"There are many consistent explanations of unlabeled data: Why you should average","author":"athiwaratkun","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref5","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"keskar","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Fantastic generalization measures and where to find them","author":"jiang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Path-sgd: Path-normalized optimization in deep neural networks","author":"neyshabur","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref2","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","author":"g\u00e9ron","year":"2019","journal-title":"Hands-On Machine Learning with Scikit-Learn Keras and TensorFlow Concepts Tools and Techniques to Build Intelligent Systems"},{"key":"ref1","first-page":"177","article-title":"Large-scale machine learning with stochastic gradient descent","author":"bottou","year":"0","journal-title":"Proceedings of COMPSTAT'2010"},{"key":"ref20","article-title":"A primer on PAC-Bayesian learning","author":"guedj","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref22","first-page":"2","article-title":"Neural networks for machine learning lecture 6a overview of mini-batch gradient descent","volume":"14","author":"hinton","year":"2012","journal-title":"CITE"},{"key":"ref21","first-page":"17176","article-title":"Directional convergence and alignment in deep learning","volume":"33","author":"ji","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","article-title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","author":"kwon","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90014-2"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.115.128101"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","location":"Padua, Italy","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892245.pdf?arnumber=9892245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:27:07Z","timestamp":1667525227000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892245\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892245","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}