{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T22:23:13Z","timestamp":1778106193805,"version":"3.51.4"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"2-4","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11971073"],"award-info":[{"award-number":["11971073"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11871115"],"award-info":[{"award-number":["11871115"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12171052"],"award-info":[{"award-number":["12171052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Glob Optim"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s10898-022-01205-4","type":"journal-article","created":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T22:03:18Z","timestamp":1656626598000},"page":"1009-1025","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["A mini-batch stochastic conjugate gradient algorithm with variance reduction"],"prefix":"10.1007","volume":"87","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8945-8613","authenticated-orcid":false,"given":"Caixia","family":"Kou","sequence":"first","affiliation":[]},{"given":"Han","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,7,1]]},"reference":[{"key":"1205_CR1","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.\u00a0E.: Imagenet classification with deep convolutional neural networks, In: Advances in neural information processing systems, pp. 1097\u20131105. (2012)"},{"issue":"1","key":"1205_CR2","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"GE Dahl","year":"2011","unstructured":"Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Transactions on audio, speech, and language processing 20(1), 30\u201342 (2011)","journal-title":"IEEE Transactions on audio, speech, and language processing"},{"issue":"6","key":"1205_CR3","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Yu, D., Dahl, G.E., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T.N., et al.: Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal processing magazine 29(6), 82\u201397 (2012)","journal-title":"IEEE Signal processing magazine"},{"key":"1205_CR4","doi-asserted-by":"crossref","unstructured":"Collobert, R., Weston, J.: A unified architecture for natural language processing: Deep neural networks with multitask learning,\u201d in Proceedings of the 25th international conference on Machine learning, pp. 160\u2013167. (2008)","DOI":"10.1145\/1390156.1390177"},{"key":"1205_CR5","doi-asserted-by":"crossref","unstructured":"Dahl, G.\u00a0E., Stokes, J.\u00a0W., Deng, L., Yu, D.: Large-scale malware classification using random projections and neural networks, In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, pp. 3422\u20133426. (2013)","DOI":"10.1109\/ICASSP.2013.6638293"},{"issue":"1847","key":"1205_CR6","first-page":"536","volume":"25","author":"A Cauchy","year":"1847","unstructured":"Cauchy, A.: M\u00e9thode g\u00e9n\u00e9rale pour la r\u00e9solution des systemes d\u2019\u00e9quations simultan\u00e9es. Comp. Rend. Sci. Paris. 25(1847), 536\u2013538 (1847)","journal-title":"Comp. Rend. Sci. Paris."},{"key":"1205_CR7","doi-asserted-by":"crossref","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method, The annals of mathematical statistics, pp. 400\u2013407, (1951)","DOI":"10.1214\/aoms\/1177729586"},{"key":"1205_CR8","doi-asserted-by":"crossref","unstructured":"Bottou, L.: Large-scale machine learning with stochastic gradient descent, Proc. COMPSTAT, pp. 177\u2013186, (2010)","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"1205_CR9","unstructured":"Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep learning. MIT press Cambridge, 1, (2016)"},{"issue":"5","key":"1205_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0041-5553(64)90137-5","volume":"4","author":"BT Polyak","year":"1964","unstructured":"Polyak, B.T.: Some methods of speeding up the convergence of iteration methods. USSR Computational Mathematics and Mathematical Physics 4(5), 1\u201317 (1964)","journal-title":"USSR Computational Mathematics and Mathematical Physics"},{"key":"1205_CR11","unstructured":"Nesterov, Y.: A method of solving a convex programming problem with convergence rate o (1\/k2), In Soviet Mathematics Doklady, (1983)"},{"issue":"1","key":"1205_CR12","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/S0893-6080(98)00116-6","volume":"12","author":"N Qian","year":"1999","unstructured":"Qian, N.: On the momentum term in gradient descent learning algorithms. Neural Netw 12(1), 145\u2013151 (1999)","journal-title":"Neural Netw"},{"key":"1205_CR13","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Machine Learning Research, 12(7), (2011)"},{"key":"1205_CR14","unstructured":"Zeiler, M.\u00a0D.: Adadelta: an adaptive learning rate method, arXiv preprint arXiv:1212.5701, (2012)"},{"issue":"2","key":"1205_CR15","first-page":"26","volume":"4","author":"T Tieleman","year":"2012","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude,. COURSERA: Neural networks for machine learning 4(2), 26\u201331 (2012)","journal-title":"COURSERA: Neural networks for machine learning"},{"key":"1205_CR16","unstructured":"Kingma, D., Ba, J.: Adam: A method for stochastic optimization, Computer ence, (2014)"},{"key":"1205_CR17","unstructured":"Hager, W.W., Zhang, H.: A survey of nonlinear conjugate gradient methods. Pacific Journal of Optimization, 2(1), 35\u201358 (2006)"},{"key":"1205_CR18","unstructured":"Roux, N.\u00a0L., Schmidt, M., Bach, F.\u00a0R.: A stochastic gradient method with an exponential convergence rate for finite training sets, in Advances in neural information processing systems, pp. 2663\u20132671, (2012)"},{"key":"1205_CR19","unstructured":"Johnson, R., Zhang, T.: Accelerating stochastic gradient descent using predictive variance reduction, In Advances in neural information processing systems, pp. 315\u2013323. (2013)"},{"key":"1205_CR20","unstructured":"Defazio, A., Bach, F., Lacoste-Julien, S.: Saga: A fast incremental gradient method with support for non-strongly convex composite objectives, in Advances in neural information processing systems, pp. 1646\u20131654. (2014)"},{"key":"1205_CR21","unstructured":"Nguyen, L.\u00a0M., Liu, J., Scheinberg, K., Tak\u00e1, M.: Sarah: A novel method for machine learning problems using stochastic recursive gradient, (2017)"},{"key":"1205_CR22","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1137\/0802003","volume":"2","author":"JC Gilbert","year":"1992","unstructured":"Gilbert, J.C., Nocedal, J.: Global convergence properties of conjugate gradient methods for optimization. SIAM J. Optim. 2, 21\u201342 (1992)","journal-title":"SIAM J. Optim."},{"key":"1205_CR23","unstructured":"Nocedal, J., Wright, S.: Numerical optimization. Springer Science & Business Media, (2006)"},{"issue":"2","key":"1205_CR24","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1093\/comjnl\/7.2.149","volume":"7","author":"R Fletcher","year":"1964","unstructured":"Fletcher, R., Reeves, C.M.: Function minimization by conjugate gradients. The computer journal 7(2), 149\u2013154 (1964)","journal-title":"The computer journal"},{"key":"1205_CR25","doi-asserted-by":"crossref","unstructured":"Polak, E., Ribiere, G.: Note sur la convergence de m\u00e9thodes de directions conjugu\u00e9es,\u201d ESAIM: Mathematical Modelling and Numerical Analysis-Mod\u00e9lisation Math\u00e9matique et Analyse Num\u00e9rique, 3(R1), pp. 35\u201343, (1969)","DOI":"10.1051\/m2an\/196903R100351"},{"issue":"4","key":"1205_CR26","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/0041-5553(69)90035-4","volume":"9","author":"BT Polyak","year":"1969","unstructured":"Polyak, B.T.: The conjugate gradient method in extreme problem. USSR Comp. Math. Math. Phys. 9(4), 94\u2013112 (1969)","journal-title":"USSR Comp. Math. Math. Phys."},{"key":"1205_CR27","doi-asserted-by":"crossref","unstructured":"Hestenes, M.R., Stiefel, E.: Methods of conjugate gradients for solving. Journal of research of the National Bureau of Standards 49(6), 409 (1952)","DOI":"10.6028\/jres.049.044"},{"issue":"1","key":"1205_CR28","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1137\/S1052623497318992","volume":"10","author":"YH Dai","year":"1999","unstructured":"Dai, Y.H., Yuan, Y.: A nonlinear conjugate gradient method with a strong global convergence property. Siam Journal on Optimization 10(1), 177\u2013182 (1999)","journal-title":"Siam Journal on Optimization"},{"issue":"1","key":"1205_CR29","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1137\/030601880","volume":"16","author":"WW Hager","year":"2005","unstructured":"Hager, W.W., Zhang, H.: A new conjugate gradient method with guaranteed descent and an efficient line search. SIAM Journal on Optimization 16(1), 170\u2013192 (2005)","journal-title":"SIAM Journal on Optimization"},{"issue":"1","key":"1205_CR30","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1137\/100813026","volume":"23","author":"YH Dai","year":"2013","unstructured":"Dai, Y.H., Kou, C.X.: A nonlinear conjugate gradient algorithm with an optimal property and an improved wolfe line search. Siam J Optim 23(1), 296\u2013320 (2013)","journal-title":"Siam J Optim"},{"key":"1205_CR31","unstructured":"Dai, Y.H., Yuan, Y.: Nonlinear conjugate gradient methods. Shanghai Science and Technology Publisher, (2000)"},{"issue":"4","key":"1205_CR32","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1016\/S0893-6080(05)80056-5","volume":"6","author":"MF M\u00f8ller","year":"1993","unstructured":"M\u00f8ller, M.F.: A scaled conjugate gradient algorithm for fast supervised learning. Neural networks 6(4), 525\u2013533 (1993)","journal-title":"Neural networks"},{"key":"1205_CR33","unstructured":"Le, Q.\u00a0V., Ngiam, J., Coates, A., Lahiri, A., Prochnow, B., Ng, A.\u00a0Y.: On optimization methods for deep learning, In ICML, (2011)"},{"key":"1205_CR34","unstructured":"Moritz, P., Nishihara, R., Jordan, M.\u00a0I.: A linearly convergent stochastic l-bfgs algorithm, Mathematics, (2015)"},{"key":"1205_CR35","doi-asserted-by":"crossref","unstructured":"Jin, X.B., Zhang, X.Y., Huang, K., Geng, G.G.: Stochastic conjugate gradient algorithm with variance reduction. IEEE transactions on neural networks and learning systems 30(5), 1360\u20131369 (2018)","DOI":"10.1109\/TNNLS.2018.2868835"}],"container-title":["Journal of Global Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10898-022-01205-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10898-022-01205-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10898-022-01205-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T19:55:14Z","timestamp":1698782114000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10898-022-01205-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,1]]},"references-count":35,"journal-issue":{"issue":"2-4","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["1205"],"URL":"https:\/\/doi.org\/10.1007\/s10898-022-01205-4","relation":{},"ISSN":["0925-5001","1573-2916"],"issn-type":[{"value":"0925-5001","type":"print"},{"value":"1573-2916","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,1]]},"assertion":[{"value":"1 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}