{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:21:24Z","timestamp":1750220484113,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,22]],"date-time":"2021-10-22T00:00:00Z","timestamp":1634860800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,22]]},"DOI":"10.1145\/3501409.3501616","type":"proceedings-article","created":{"date-parts":[[2022,1,2]],"date-time":"2022-01-02T06:18:12Z","timestamp":1641104292000},"page":"1171-1176","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A novel variance redbuction algorithm based on batch subtraction update"],"prefix":"10.1145","author":[{"given":"Jie","family":"Song","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, Hefei, China"}]},{"given":"Yong","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, Hefei, China"}]},{"given":"Bin","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2021,12,31]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Pro-ceedings of the 24th Annual Conference on Neural Information Processing Systems, Vancou-ver, Dec 6--9, 2010","author":"Zinkevich","year":"2010","unstructured":"Zinkevich M, Weimer M, Smola A J, et al. Parallelized stochastic gradient descent[C]. Pro-ceedings of the 24th Annual Conference on Neural Information Processing Systems, Vancou-ver, Dec 6--9, 2010. Red Hook: Curran Associates, 2010: 2595--2603"},{"issue":"1","key":"e_1_3_2_1_2_1","first-page":"1235","article-title":"Mllib: machine learning in Apache Spark[J]","volume":"17","author":"Xiangrui Meng","year":"2015","unstructured":"Meng Xiangrui, Bradley J K, Yavuz B, et al. Mllib: machine learning in Apache Spark[J]. Journal of Machine Learning Research, 2015, 17(1): 1235--1241","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_3_1","first-page":"II-1139","volume-title":"Proceedings of the 30th International Conference on International Conference on Machine Learning","volume":"2013","author":"Sutskever Ilya","unstructured":"Ilya Sutskever, James Martens, George Dahl, etc. On the importance of initialization and mo-mentum in deep learning[C]. Proceedings of the 30th International Conference on International Conference on Machine Learning Volume 28June 2013 Pages III-1139-III-114"},{"key":"e_1_3_2_1_4_1","first-page":"2121","article-title":"Adaptive Subgradient Methods for Online Learning and Stochastic Optimization[C]","author":"Duchi John","year":"2011","unstructured":"John Duchi, Elad Hazan, Yoram Singer. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization[C]. The Journal of Machine Learning Research July 2011, 2121--2159","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_2_1_5_1","volume-title":"Divide the gradient by a running average of its recent magnitude[OL]","author":"Prop Lecture","year":"2012","unstructured":"Tieleman, T., Hinton, G.. Lecture 6.5-RMSProp: Divide the gradient by a running average of its recent magnitude[OL]. COURSERA: Neural Networks for Machine Learning 2012"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18178\/ijmlc.2019.9.3.797"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 27th Annual Conference on Neural Information Processing Systems, Lake Tahoe, Dec 5--8, 2013","author":"Johnson","year":"2013","unstructured":"Johnson R, Zhang Tong. Accelerating stochastic gradient descent using predictive variance reduction[C]. Proceedings of the 27th Annual Conference on Neural Information Processing Systems, Lake Tahoe, Dec 5--8, 2013. Red Hook: Curran Associates, 2013: 315--32"},{"issue":"7","key":"e_1_3_2_1_8_1","first-page":"1047","article-title":"Distributed stochastic variance reduction gradi-ent descent algorithm topkSVRG[J]","volume":"12","author":"Jianfei WANG","year":"2018","unstructured":"WANG Jianfei, KANG Liangyi, LIU Jie, et al. Distributed stochastic variance reduction gradi-ent descent algorithm topkSVRG[J]. Journal of Frontiers of Computer Science and Technology, 2018, 12(7):1047--1054","journal-title":"Journal of Frontiers of Computer Science and Technology"},{"key":"e_1_3_2_1_9_1","first-page":"1646","article-title":"A fast incremental gradient method with support for nonstrongly convex composite objectives[C]","volume":"27","author":"Saga S.","year":"2014","unstructured":"Defazio, A., Bach, F., and Lacoste-Julien, S. Saga: A fast incremental gradient method with support for nonstrongly convex composite objectives[C]. In Advances in Neural Information Processing Systems 27, pp. 1646--1654. 2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"Lei Lihua","year":"2017","unstructured":"Lihua Lei and Michael I Jordan. Less than a single pass: Stochastically controlled stochastic gradient method[C]. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) 2017, Fort Lauderdale, Florida, USA"},{"key":"e_1_3_2_1_11_1","volume-title":"INRIA, hal-0086005","author":"Schmidt Mark","year":"2013","unstructured":"Mark Schmidt, Nicolas Le Roux, and Francis Bach. Minimizing finite sums with the stochastic average gradient. Technical report, INRIA, hal-0086005, 2013"},{"key":"e_1_3_2_1_12_1","volume-title":"Processdings of the 36th International Conference on Machine Learning","author":"Gazagnadou Nidham","year":"2019","unstructured":"Nidham Gazagnadou, Robert M Gower, Joseph Salmon. Optimal Mini-Batch and Step Sizes for SASG[C]. Processdings of the 36th International Conference on Machine Learning, Long Beach, California, PMLR 97, 2019"},{"key":"e_1_3_2_1_13_1","unstructured":"Gower R M Richt\u00e1rik Peter Bach F. Stochastic Quasi-Gradient Methods: Variance Reduc-tion via Jacobian Sketching[J]. 2018"},{"issue":"1","key":"e_1_3_2_1_14_1","first-page":"2013","article-title":"Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization[J]","volume":"14","author":"Shalev-Shwartz","year":"2012","unstructured":"Shalev-Shwartz S, Zhang T. Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization[J]. Journal of Machine Learning Research, 2012, 14(1):2013","journal-title":"Journal of Machine Learning Research"},{"issue":"2","key":"e_1_3_2_1_15_1","first-page":"242","article-title":"Mini-Batch Semi-Stochastic Gradient Descent in the Prox-imal Setting[J]. Selected Topics in Signal Processing","volume":"10","author":"Konecny","year":"2016","unstructured":"Konecny J, Liu J, Richtarik P, et al. Mini-Batch Semi-Stochastic Gradient Descent in the Prox-imal Setting[J]. Selected Topics in Signal Processing, IEEE Journal of, 2016, 10(2):242--255","journal-title":"IEEE Journal of"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294995"},{"key":"e_1_3_2_1_17_1","volume-title":"Natasha 2: Faster Non-Convex Optimization Than SGD[C]. 32nd Confer-ence on Neural Information Processing Systems (NeurIPS","author":"Allen-Zhu Zeyuan","year":"2018","unstructured":"Zeyuan Allen-Zhu. Natasha 2: Faster Non-Convex Optimization Than SGD[C]. 32nd Confer-ence on Neural Information Processing Systems (NeurIPS 2018), Montr\u00e9al, Canada"},{"key":"e_1_3_2_1_18_1","volume-title":"Stochastic Variance Reduced Hamilton Monte Carlo Meth-ods[J]. arXiv","author":"Zou Difan","year":"1802","unstructured":"Difan Zou, Pan Xu, Quanquan Gu. Stochastic Variance Reduced Hamilton Monte Carlo Meth-ods[J]. arXiv: 1802.04791 v1 [stat.ML] 13 Feb 2018"},{"key":"e_1_3_2_1_19_1","volume-title":"Introduction to deep learning: theory and implementation based on Python [M]. Trans. Lu yujie","author":"Yi Saito Kang","year":"2018","unstructured":"Saito Kang Yi. Introduction to deep learning: theory and implementation based on Python [M]. Trans. Lu yujie. 1st edition. Posts and telecommunications press. July 2018","edition":"1"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"event":{"name":"EITCE 2021: 2021 5th International Conference on Electronic Information Technology and Computer Engineering","acronym":"EITCE 2021","location":"Xiamen China"},"container-title":["Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3501409.3501616","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3501409.3501616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:02Z","timestamp":1750193342000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3501409.3501616"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,22]]},"references-count":20,"alternative-id":["10.1145\/3501409.3501616","10.1145\/3501409"],"URL":"https:\/\/doi.org\/10.1145\/3501409.3501616","relation":{},"subject":[],"published":{"date-parts":[[2021,10,22]]},"assertion":[{"value":"2021-12-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}