{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:23:12Z","timestamp":1784247792402,"version":"3.55.0"},"reference-count":55,"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"],"award-info":[{"award-number":["NRF-2017R1A2B4006023"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2018R1A4A1059731"],"award-info":[{"award-number":["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.2019.2937139","type":"journal-article","created":{"date-parts":[[2019,8,23]],"date-time":"2019-08-23T15:59:08Z","timestamp":1566575948000},"page":"118857-118865","source":"Crossref","is-referenced-by-count":50,"title":["Adaptive Weight Decay for Deep Neural Networks"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6858-3551","authenticated-orcid":false,"given":"Kensuke","family":"Nakamura","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-3939","authenticated-orcid":false,"given":"Byung-Woo","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"699","article-title":"Variance reduction for faster non-convex optimization","author":"allen-zhu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","first-page":"5980","article-title":"A simple stochastic variance reduced algorithm with fast convergence rates","volume":"80","author":"zhou","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn Res (PMLR)"},{"key":"ref33","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","author":"johnson","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","first-page":"2663","article-title":"A stochastic gradient method with an exponential convergence rate for finite training sets","volume":"2","author":"le roux","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref31","first-page":"1019","article-title":"Sharp minima can generalize for deep nets","volume":"70","author":"dinh","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref30","first-page":"1","article-title":"Entropy-SGD: Biasing gradient descent into wide valleys","author":"chaudhari","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref37","first-page":"6028","article-title":"Stochastic variance-reduced Hamilton Monte Carlo methods","volume":"80","author":"zou","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn Res (PMLR)"},{"key":"ref36","first-page":"1990","article-title":"Adaptive variance reducing for stochastic gradient descent","author":"shen","year":"2016","journal-title":"Proc IJCAI"},{"key":"ref35","first-page":"46","article-title":"Fast stochastic alternating direction method of multipliers","author":"zhong","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref34","first-page":"1","article-title":"On the theory of variance reduction for stochastic gradient Monte Carlo","author":"chatterji","year":"2018","journal-title":"Proc ICML"},{"key":"ref28","first-page":"5109","article-title":"Regularizing deep neural networks by noise: Its interpretation and optimization","author":"noh","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.1.1"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref20","first-page":"1","article-title":"Don’t decay the learning rate, increase the batch size","author":"smith","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref22","first-page":"26","article-title":"Lecture 6.5-RMSPROP: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"Neural Netw Mach Learning"},{"key":"ref21","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":"ref24","first-page":"3084","article-title":"Adaptive dropout for training deep neural networks","author":"ba","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref26","article-title":"Generalized dropout","author":"srinivas","year":"2016","journal-title":"arXiv 1611 06791"},{"key":"ref25","first-page":"2575","article-title":"Variational dropout and the local reparameterization trick","author":"kingma","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","first-page":"2574","article-title":"Adaptive sampling probabilities for non-smooth optimization","author":"namkoong","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref55","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90047-9"},{"key":"ref53","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref52","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"xiao","year":"2017","journal-title":"ArXiv 1708 07747"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015332"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49430-8_3"},{"key":"ref40","first-page":"2043","article-title":"Asynchronous mini-batch gradient descent with variance reduction for non-convex optimization","author":"huo","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref12","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2016","journal-title":"arXiv 1611 03530"},{"key":"ref13","first-page":"7654","article-title":"The anisotropic noise in stochastic gradient descent: Its behavior of escaping from sharp minima and regularization effects","author":"zhu","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","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":"ref15","first-page":"950","article-title":"A simple weight decay can improve generalization","author":"krogh","year":"1992","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref17","first-page":"276","article-title":"Layer-wise weight decay for deep neural networks","author":"ishii","year":"2017","journal-title":"Proc Pacific-Rim Symp Image Video Technol"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_26"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-8365-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref5","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1137\/16M1080173","article-title":"Optimization methods for large-scale machine learning","volume":"60","author":"bottou","year":"2018","journal-title":"SIAM Rev"},{"key":"ref49","article-title":"Let’s make block coordinate descent go fast: Faster greedy rules, message-passing, active-set complexity, and superlinear convergence","author":"nutini","year":"2017","journal-title":"arXiv 1712 08859"},{"key":"ref9","first-page":"1","article-title":"Learning representations by back-propagating errors","volume":"5","author":"rumelhart","year":"1988","journal-title":"Modeling Cognition"},{"key":"ref46","first-page":"1168","article-title":"Unbounded Bayesian optimization via regularization","author":"shahriari","year":"2016","journal-title":"Proc Artif Intell Statist"},{"key":"ref45","first-page":"2171","article-title":"Scalable Bayesian optimization using deep neural networks","author":"snoek","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","first-page":"72","article-title":"Accelerated coordinate descent with adaptive coordinate frequencies","author":"glasmachers","year":"2013","journal-title":"Proc Asian Conf Mach Learn"},{"key":"ref47","first-page":"342","article-title":"The shattered gradients problem: If resnets are the answer, then what is the question?","volume":"70","author":"balduzzi","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn Res (PMLR)"},{"key":"ref42","first-page":"823","article-title":"Two problems with back propagation and other steepest descent learning procedures for networks","author":"sutton","year":"1986","journal-title":"Proc 8th Annu Conf Cogn Sci Soc"},{"key":"ref41","first-page":"3727","article-title":"Zeroth-order stochastic variance reduction for nonconvex optimization","author":"liu","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ITA.2018.8503173"},{"key":"ref43","first-page":"543","article-title":"A method for unconstrained convex minimization problem with the rate of convergence o (1\/\n$\\text{k}^{\\wedge}~2$\n)","volume":"269","author":"nesterov","year":"1983","journal-title":"Doklady an USSR"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08811458.pdf?arnumber=8811458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:31:07Z","timestamp":1641987067000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8811458\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2937139","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}