{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T19:41:54Z","timestamp":1791315714792,"version":"4.3.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0101400"],"award-info":[{"award-number":["2018AAA0101400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91720000"],"award-info":[{"award-number":["91720000"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009592","name":"Beijing Municipal Science and Technology Commission","doi-asserted-by":"publisher","award":["Z181100008918007"],"award-info":[{"award-number":["Z181100008918007"]}],"id":[{"id":"10.13039\/501100009592","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1109\/tnnls.2019.2957003","type":"journal-article","created":{"date-parts":[[2019,12,31]],"date-time":"2019-12-31T06:53:36Z","timestamp":1577775216000},"page":"4649-4659","source":"Crossref","is-referenced-by-count":54,"title":["Accelerating Minibatch Stochastic Gradient Descent Using Typicality Sampling"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7181-2159","authenticated-orcid":false,"given":"Xinyu","family":"Peng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9428-1960","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9185-3989","authenticated-orcid":false,"given":"Fei-Yue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/34.291440"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/72.991427"},{"key":"ref33","article-title":"Adaptive gradient methods with dynamic bound of learning rate","author":"luo","year":"2019","journal-title":"arXiv 1904 09237"},{"key":"ref32","article-title":"On the convergence of Adam and beyond","author":"reddi","year":"2019","journal-title":"arXiv 1904 09237"},{"key":"ref31","first-page":"643","article-title":"Gradient methods for minimizing functionals","volume":"3","author":"polyak","year":"1963","journal-title":"Zhurnal Wychislitelnoy Matematiki i Matematicheskoy Fiziki"},{"key":"ref30","first-page":"962","article-title":"Importance sampling for minibatches","volume":"19","author":"csiba","year":"2018","journal-title":"J Mach Learn Res"},{"key":"ref37","author":"dua","year":"2017","journal-title":"UCI Machine Learning Repository"},{"key":"ref36","first-page":"567","article-title":"Stochastic dual coordinate ascent methods for regularized loss minimization","volume":"14","author":"shalev-shwartz","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref35","first-page":"487","article-title":"Data mining cluster analysis: Basic concepts and algorithms","author":"tan","year":"2013","journal-title":"Introduction to Data Mining"},{"key":"ref34","volume":"5","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref10","article-title":"Accurate, large minibatch SGD: Training imagenet in 1 Hour","author":"goyal","year":"2017","journal-title":"arXiv 1706 02677"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref12","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","author":"johnson","year":"2013","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref13","first-page":"2663","article-title":"A stochastic gradient method with an exponential convergence _rate for finite training sets","volume":"4","author":"roux","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623612"},{"key":"ref15","first-page":"257","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref16","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv 1212 5701"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref18","first-page":"1","article-title":"Incorporating Nesterov momentum into Adam","author":"dozat","year":"2016","journal-title":"Proc ICLR Workshop"},{"key":"ref19","author":"lohr","year":"2009","journal-title":"Sampling Design and Analysis"},{"key":"ref28","first-page":"2","author":"heinonen","year":"2005","journal-title":"Lectures on Lipschitz analysis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref27","volume":"305","author":"hiriart-urruty","year":"2013","journal-title":"Convex Analysis and Minimization Algorithms Fundamentals"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/130908257"},{"key":"ref5","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"collobert","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref8","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref7","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref9","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv 1609 03499"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref22","article-title":"Online batch selection for faster training of neural networks","author":"loshchilov","year":"2016","journal-title":"arXiv 1511 06343"},{"key":"ref21","first-page":"1189","article-title":"Self-paced learning for latent variable models","author":"kumar","year":"2010","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref24","article-title":"MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels","author":"jiang","year":"2017","journal-title":"arXiv 1712 05055"},{"key":"ref41","author":"chen","year":"2015","journal-title":"The UCR time series classification archive"},{"key":"ref23","article-title":"Variance reduction in SGD by distributed importance sampling","author":"alain","year":"2015","journal-title":"arXiv 1511 06481"},{"key":"ref26","article-title":"Accelerating minibatch stochastic gradient descent using stratified sampling","author":"zhao","year":"2014","journal-title":"arXiv 1405 3080"},{"key":"ref25","article-title":"Learning what data to learn","author":"fan","year":"2017","journal-title":"arXiv 1702 08635"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9244673\/08945166.pdf?arnumber=8945166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:19:55Z","timestamp":1651079995000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8945166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11]]},"references-count":41,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2019.2957003","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11]]}}}