{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:41:59Z","timestamp":1740109319544,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T00:00:00Z","timestamp":1626048000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T00:00:00Z","timestamp":1626048000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Japan Digital Design"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1007\/s10115-021-01593-1","type":"journal-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T20:02:47Z","timestamp":1626120167000},"page":"2513-2539","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sharp characterization of optimal minibatch size for stochastic finite sum convex optimization"],"prefix":"10.1007","volume":"63","author":[{"given":"Atsushi","family":"Nitanda","sequence":"first","affiliation":[]},{"given":"Tomoya","family":"Murata","sequence":"additional","affiliation":[]},{"given":"Taiji","family":"Suzuki","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,7,12]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Allen-Zhu Z (2017) Katyusha: the first direct acceleration of stochastic gradient methods. In: Proceedings of annual ACM SIGACT symposium on theory of computing 49, pp 1200\u20131205. ACM","key":"1593_CR1","DOI":"10.1145\/3055399.3055448"},{"key":"1593_CR2","first-page":"608","volume":"30","author":"T Murata","year":"2017","unstructured":"Murata T, Suzuki T (2017) Doubly accelerated stochastic variance reduced dual averaging method for regularized empirical risk minimization. Adv Neural Inf Process Syst 30:608\u2013617","journal-title":"Adv Neural Inf Process Syst"},{"key":"1593_CR3","first-page":"1574","volume":"27","author":"A Nitanda","year":"2014","unstructured":"Nitanda A (2014) Stochastic proximal gradient descent with acceleration techniques. Adv Neural Inf Process Syst 27:1574\u20131582","journal-title":"Adv Neural Inf Process Syst"},{"key":"1593_CR4","first-page":"3059","volume":"27","author":"Q Lin","year":"2014","unstructured":"Lin Q, Lu Z, Xiao L (2014) An accelerated proximal coordinate gradient method. Adv Neural Inf Process Syst 27:3059\u20133067","journal-title":"Adv Neural Inf Process Syst"},{"key":"1593_CR5","first-page":"1647","volume":"24","author":"A Cotter","year":"2011","unstructured":"Cotter A, Shamir O, Srebro N, Sridharan K (2011) Better mini-batch algorithms via accelerated gradient methods. Adv Neural Inf Process Syst 24:1647\u20131655","journal-title":"Adv Neural Inf Process Syst"},{"key":"1593_CR6","first-page":"378","volume":"26","author":"S Shalev-Shwartz","year":"2013","unstructured":"Shalev-Shwartz S, Zhang T (2013) Accelerated mini-batch stochastic dual coordinate ascent. Adv Neural Inf Process Syst 26:378\u2013385","journal-title":"Adv Neural Inf Process Syst"},{"unstructured":"Kai Z, Liang H (2013) Minibatch and parallelization for online large margin structured learning. In: Proceedings of the 2013 Conference of the North American chapter of the association for computational linguistics: human language technologies, pp 370\u2013379","key":"1593_CR7"},{"unstructured":"Martin T, Singh BA, Peter R, Nati S (2013) Mini-batch primal and dual methods for svms. In: ICML (3), pp 1022\u20131030","key":"1593_CR8"},{"unstructured":"Mu L, Tong Z, Yuqiang C, Alexander\u00a0JS (2014) Efficient mini-batch training for stochastic optimization. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pp 661\u2013670. ACM","key":"1593_CR9"},{"unstructured":"Peilin Z, Tong Z (2014) Accelerating minibatch stochastic gradient descent using stratified sampling. arXiv preprintarXiv:1405.3080","key":"1593_CR10"},{"issue":"2","key":"1593_CR11","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1109\/JSTSP.2015.2505682","volume":"10","author":"Kone\u010dn\u1ef3 Jakub","year":"2016","unstructured":"Jakub Kone\u010dn\u1ef3, Jie Liu, Peter Richt\u00e1rik, Martin Tak\u00e1\u010d (2016) Mini-batch semi-stochastic gradient descent in the proximal setting. IEEE J Select Top Signal Process 10(2):242\u2013255","journal-title":"IEEE J Select Top Signal Process"},{"unstructured":"Martin T, Peter R, Nathan S (2015) Distributed mini-batch sdca. arXiv preprintarXiv:1507.08322","key":"1593_CR12"},{"key":"1593_CR13","first-page":"12","volume":"1050","author":"J Prateek","year":"2016","unstructured":"Prateek J, Sham KM, Rahul K, Praneeth N, Aaron S (2016) Parallelizing stochastic approximation through mini-batching and tail-averaging. Stat 1050:12","journal-title":"Stat"},{"unstructured":"Nicolas\u00a0LR, Mark S, Francis\u00a0RB (2012) A stochastic gradient method with an exponential convergence rate for finite training sets. In: Advances in neural information processing systems, pp 2663\u20132671","key":"1593_CR14"},{"key":"1593_CR15","first-page":"315","volume":"26","author":"R Johnson","year":"2013","unstructured":"Johnson R, Zhang T (2013) Accelerating stochastic gradient descent using predictive variance reduction. Adv Neural Inf Process Syst 26:315\u2013323","journal-title":"Adv Neural Inf Process Syst"},{"key":"1593_CR16","first-page":"1646","volume":"27","author":"A Defazio","year":"2014","unstructured":"Defazio A, Bach F, Lacoste-Julien S (2014) Saga: A fast incremental gradient method with support for non-strongly convex composite objectives. Adv Neural Inf Process Syst 27:1646\u20131654","journal-title":"Adv Neural Inf Process Syst"},{"key":"1593_CR17","first-page":"3384","volume":"28","author":"H Lin","year":"2015","unstructured":"Lin H, Mairal J, Harchaoui Z (2015) A universal catalyst for first-order optimization. Adv Neural Inf Process Syst 28:3384\u20133392","journal-title":"Adv Neural Inf Process Syst"},{"unstructured":"Frostig R, Ge R, Kakade S, Sidford A (2015) Un-regularizing: Approximate proximal point and faster stochastic algorithms for empirical risk minimization. In: Proceedings of International Conference on Machine Learning vol 32, pp 2540\u20132548","key":"1593_CR18"},{"key":"1593_CR19","first-page":"3639","volume":"29","author":"EW Blake","year":"2016","unstructured":"Blake EW, Srebro N (2016) Tight complexity bounds for optimizing composite objectives. Adv Neural Inf Process Syst 29:3639\u20133647","journal-title":"Adv Neural Inf Process Syst"},{"key":"1593_CR20","first-page":"3540","volume":"29","author":"Y Arjevani","year":"2016","unstructured":"Arjevani Y, Shamir O (2016) Dimension-free iteration complexity of finite sum optimization problems. Adv Neural Inf Process Syst 29:3540\u20133548","journal-title":"Adv Neural Inf Process Syst"},{"unstructured":"Mark S, Le RN (2013) Fast convergence of stochastic gradient descent under a strong growth condition. arXiv preprintarXiv:1308.6370","key":"1593_CR21"},{"unstructured":"Lam MN, Liu J, Scheinberg K, Tak\u00e1\u010d M (2017) Sarah: A novel method for machine learning problems using stochastic recursive gradient. In: Proceedings of international conference on machine learning vol 34, pp 2613\u20132621","key":"1593_CR22"},{"key":"1593_CR23","first-page":"165","volume":"13","author":"D Ofer","year":"2012","unstructured":"Ofer D, Ran G-B, Ohad S, Lin X (2012) Optimal distributed online prediction using mini-batches. J Mach Learn Res 13:165\u2013202","journal-title":"J Mach Learn Res"},{"unstructured":"Nidham G, Robert MG, Joseph S (2019) Optimal mini-batch and step sizes for saga. arXiv preprintarXiv:1902.00071","key":"1593_CR24"},{"key":"1593_CR25","volume-title":"Introductory lectures on convex optimization: a basic course","author":"N Yurii","year":"2004","unstructured":"Yurii N (2004) Introductory lectures on convex optimization: a basic course. Kluwer Academic Publishers, New York"},{"issue":"2","key":"1593_CR26","doi-asserted-by":"publisher","first-page":"1426","DOI":"10.14778\/1687553.1687569","volume":"2","author":"B Panda","year":"2009","unstructured":"Panda B, Joshua SH, Basu S, Roberto JB (2009) Planet: massively parallel learning of tree ensembles with mapreduce. Proc VLDB Endow 2(2):1426\u20131437","journal-title":"Proc VLDB Endow"},{"unstructured":"Chi Z, Feifei L, Jeffrey J (2012) Efficient parallel knn joins for large data in mapreduce. In: Proceedings of the 15th international conference on extending database technology, pp 38\u201349","key":"1593_CR27"},{"unstructured":"Tianyang S, Chengchun S, Feng L, Yu H, Lili M, Yitong F (2009) An efficient hierarchical clustering method for large datasets with map-reduce. In: 2009 International conference on parallel and distributed computing, applications and technologies, pp 494\u2013499","key":"1593_CR28"},{"unstructured":"Yaobin H, Haoyu T, Wuman L, Huajian M, Di M, Shengzhong F, Jianping F (2011) Mr-dbscan: an efficient parallel density-based clustering algorithm using mapreduce. In: 2011 IEEE 17th international conference on parallel and distributed systems, pp 473\u2013480","key":"1593_CR29"},{"doi-asserted-by":"crossref","unstructured":"Weizhong Z, Huifang M, Qing H (2009) Parallel k-means clustering based on mapreduce. In: IEEE international conference on cloud computing, pp 674\u2013679","key":"1593_CR30","DOI":"10.1007\/978-3-642-10665-1_71"},{"issue":"5","key":"1593_CR31","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1007\/s11280-013-0236-2","volume":"17","author":"J Xin","year":"2014","unstructured":"Xin J, Wang Z, Chen C, Ding L, Wang G, Zhao Y (2014) Elm: distributed extreme learning machine with mapreduce. World Wide Web 17(5):1189\u20131204","journal-title":"World Wide Web"},{"key":"1593_CR32","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1016\/j.neucom.2014.03.076","volume":"149","author":"B Wang","year":"2015","unstructured":"Wang B, Huang S, Qiu J, Yu L, Wang G (2015) Parallel online sequential extreme learning machine based on mapreduce. Neurocomputing 149:224\u2013232","journal-title":"Neurocomputing"},{"key":"1593_CR33","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1016\/j.neucom.2014.01.070","volume":"149","author":"X Bi","year":"2015","unstructured":"Bi X, Zhao X, Wang G, Zhang P, Wang C (2015) Distributed extreme learning machine with kernels based on mapreduce. Neurocomputing 149:456\u2013463","journal-title":"Neurocomputing"},{"issue":"9","key":"1593_CR34","doi-asserted-by":"publisher","first-page":"2269","DOI":"10.1007\/s00500-015-1938-4","volume":"21","author":"FO \u00c7atak","year":"2017","unstructured":"\u00c7atak FO (2017) Classification with boosting of extreme learning machine over arbitrarily partitioned data. Soft Comput 21(9):2269\u20132281","journal-title":"Soft Comput"},{"unstructured":"Xi C, Qihang L, Javier P (2012) Optimal regularized dual averaging methods for stochastic optimization. In: Advances in neural information processing systems, pp 395\u2013403","key":"1593_CR35"},{"unstructured":"Hongzhou L, Julien M, Zaid H (2017) Catalyst acceleration for first-order convex optimization: from theory to practice. arXiv preprintarXiv:1712.05654","key":"1593_CR36"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-021-01593-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-021-01593-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-021-01593-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T03:31:21Z","timestamp":1629689481000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-021-01593-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,12]]},"references-count":36,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["1593"],"URL":"https:\/\/doi.org\/10.1007\/s10115-021-01593-1","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"type":"print","value":"0219-1377"},{"type":"electronic","value":"0219-3116"}],"subject":[],"published":{"date-parts":[[2021,7,12]]},"assertion":[{"value":"1 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}