{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:18:40Z","timestamp":1740169120091,"version":"3.37.3"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2017R1A2B4006023","NRF-2018R1A4A1059731"],"award-info":[{"award-number":["NRF-2017R1A2B4006023","NRF-2018R1A4A1059731"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2938200","type":"journal-article","created":{"date-parts":[[2019,8,29]],"date-time":"2019-08-29T20:07:40Z","timestamp":1567109260000},"page":"122889-122899","source":"Crossref","is-referenced-by-count":1,"title":["Adaptive Regularization via Residual Smoothing in Deep Learning Optimization"],"prefix":"10.1109","volume":"7","author":[{"given":"Junghee","family":"Cho","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junseok","family":"Kwon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-3939","authenticated-orcid":false,"given":"Byung-Woo","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"xiao","year":"2017","journal-title":"ArXiv 1708 07747"},{"key":"ref30","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc NIPS"},{"key":"ref37","first-page":"4148","article-title":"The marginal value of adaptive gradient methods in machine learning","author":"wilson","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref10","first-page":"1","article-title":"Online to offline conversions, universality and adaptive minibatch sizes","author":"levy","year":"2017","journal-title":"Proc NIPS"},{"key":"ref11","first-page":"1","article-title":"Semi-supervised learning by entropy minimization","author":"grandvalet","year":"2004","journal-title":"Proc NIPS"},{"key":"ref12","first-page":"1","article-title":"Soft q-learning with mutual-information regularization","author":"grau-moya","year":"2019","journal-title":"Proc ICLR"},{"key":"ref13","first-page":"1","article-title":"Variational dropout and the local reparameterization trick","author":"kingma","year":"2015","journal-title":"Proc NIPS"},{"key":"ref14","first-page":"1","article-title":"Regularizing deep neural networks by noise: Its interpretation and optimization","author":"noh","year":"2017","journal-title":"Proc NIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.514"},{"key":"ref17","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref18","first-page":"1","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"Proc ICML"},{"key":"ref19","article-title":"Stochastic pooling for regularization of deep convolutional neural networks","author":"zeiler","year":"2013","journal-title":"arXiv 1301 3557"},{"key":"ref28","article-title":"Mollifying networks","author":"gulcehre","year":"2016","journal-title":"arXiv 1608 04980"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3306240"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-14612-6_4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691321"},{"key":"ref6","first-page":"1","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc AAAI"},{"key":"ref29","article-title":"Learning multiple layers of features from tiny images","volume":"1","author":"krizhevsky","year":"2009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref8","first-page":"1","article-title":"Unsupervised deep learning for optical flow estimation","author":"ren","year":"2017","journal-title":"Proc AAAI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2794218"},{"key":"ref20","first-page":"8","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"Proc ICLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_23"},{"key":"ref21","first-page":"1","article-title":"Swapout: Learning an ensemble of deep architectures","author":"singh","year":"2016","journal-title":"Proc NIPS"},{"key":"ref24","first-page":"1","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.63"},{"key":"ref26","first-page":"7694","article-title":"Understanding batch normalization","author":"bjorck","year":"2018","journal-title":"Proc NIPS"},{"key":"ref25","first-page":"1","article-title":"Towards understanding regularization in batch normalization","author":"luo","year":"2019","journal-title":"Proc ICLR"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08819936.pdf?arnumber=8819936","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:31:14Z","timestamp":1641987074000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8819936\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2938200","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2019]]}}}