{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:47:25Z","timestamp":1783183645139,"version":"3.54.6"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/cdc.2017.8264077","type":"proceedings-article","created":{"date-parts":[[2018,1,23]],"date-time":"2018-01-23T15:30:57Z","timestamp":1516721457000},"page":"2880-2887","source":"Crossref","is-referenced-by-count":81,"title":["Mini-batch gradient descent: Faster convergence under data sparsity"],"prefix":"10.1109","author":[{"given":"Sarit","family":"Khirirat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamid Reza","family":"Feyzmahdavian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mikael","family":"Johansson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/140961791"},{"key":"ref11","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","author":"niu","year":"2011","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref12","first-page":"2595","article-title":"Parallelized stochastic gradient descent","author":"zinkevich","year":"2010","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2525015"},{"key":"ref14","first-page":"2737","article-title":"Asynchronous parallel stochastic gradient for nonconvex optimization","author":"lian","year":"2015","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref15","first-page":"165","article-title":"Optimal distributed online prediction using mini-batches","volume":"13","author":"dekel","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref16","author":"mania","year":"2015","journal-title":"Perturbed iterate analysis for asynchronous stochastic optimization"},{"key":"ref17","author":"pan","year":"2016","journal-title":"Cyclades Conflict-free asynchronous machine learning"},{"key":"ref18","author":"leblond","year":"2016","journal-title":"Asaga Asynchronous parallel saga"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref4","first-page":"161","article-title":"The tradeoffs of large scale learning","author":"bousquet","year":"2008","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref3","first-page":"627","article-title":"Trust region Newton method for logistic regression","volume":"9","author":"lin","year":"2008","journal-title":"The Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1007\/978-3-642-35289-8_25","article-title":"Stochastic gradient descent tricks","author":"bottou","year":"2012","journal-title":"Neural Networks Tricks of the Trade"},{"key":"ref5","first-page":"1","article-title":"Incremental gradient, subgradient, and proximal methods for convex optimization: A survey","volume":"2010","author":"bertsekas","year":"2011","journal-title":"Optimization for Machine Learning"},{"key":"ref8","first-page":"1017","article-title":"Stochastic gradient descent, weighted sampling, and the randomized kaczmarz algorithm","author":"needell","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2012.09.004"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2329397"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2011.09.043"},{"key":"ref20","author":"khirirat","year":"2016","journal-title":"Randomized first-order methods for convex optimization"},{"key":"ref22","article-title":"Making large scale SVM learning practical","author":"joachims","year":"1999","journal-title":"Technical report of university of Dortmund"},{"key":"ref21","author":"hsu","year":"2003","journal-title":"A Practical Guide to Support Vector Classification"},{"key":"ref23","first-page":"1458","article-title":"Convergence rates of inexact proximal-gradient methods for convex optimization","author":"schmidt","year":"2011","journal-title":"Advances in Neural Information Processing Systems (NIPS)"}],"event":{"name":"2017 IEEE 56th Annual Conference on Decision and Control (CDC)","location":"Melbourne, Australia","start":{"date-parts":[[2017,12,12]]},"end":{"date-parts":[[2017,12,15]]}},"container-title":["2017 IEEE 56th Annual Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8253407\/8263624\/08264077.pdf?arnumber=8264077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,9]],"date-time":"2019-10-09T14:29:20Z","timestamp":1570631360000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8264077\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cdc.2017.8264077","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}