{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T20:44:49Z","timestamp":1780519489613,"version":"3.54.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T00:00:00Z","timestamp":1711497600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T00:00:00Z","timestamp":1711497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Guangxi Science and Technology Base and Talent Project","award":["AD22080047"],"award-info":[{"award-number":["AD22080047"]}]},{"name":"Guangxi Science and Technology Base and Talent Project","award":["AD22080047"],"award-info":[{"award-number":["AD22080047"]}]},{"name":"Guangxi Science and Technology Base and Talent Project","award":["AD22080047"],"award-info":[{"award-number":["AD22080047"]}]},{"name":"Guangxi Science and Technology Base and Talent Project","award":["AD22080047"],"award-info":[{"award-number":["AD22080047"]}]},{"name":"Innovation Funds of Chinese University","award":["2021BCF03001"],"award-info":[{"award-number":["2021BCF03001"]}]},{"name":"Innovation Funds of Chinese University","award":["2021BCF03001"],"award-info":[{"award-number":["2021BCF03001"]}]},{"name":"Innovation Funds of Chinese University","award":["2021BCF03001"],"award-info":[{"award-number":["2021BCF03001"]}]},{"name":"Innovation Funds of Chinese University","award":["2021BCF03001"],"award-info":[{"award-number":["2021BCF03001"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Stat Comput"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1007\/s11222-024-10409-5","type":"journal-article","created":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T06:01:53Z","timestamp":1711519313000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Stochastic three-term conjugate gradient method with variance technique for non-convex learning"],"prefix":"10.1007","volume":"34","author":[{"given":"Chen","family":"Ouyang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenkaixiang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruping","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gonglin","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiyan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,27]]},"reference":[{"key":"10409_CR1","doi-asserted-by":"crossref","unstructured":"Bottou, L.: Large-scale machine learning with stochastic gradient descent\/\/Proceedings of COMPSTAT\u20192010: 19th international conference on computational statistics Paris France, Aug 22-27, 2010 Keynote, Invited and Contributed Papers. Physica-Verlag HD, (2010): 177-186","DOI":"10.1007\/978-3-7908-2604-3_16"},{"issue":"2","key":"10409_CR2","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1137\/16M1080173","volume":"60","author":"L Bottou","year":"2018","unstructured":"Bottou, L., Curtis, F.E., Nocedal, J.: Optimization methods for large-scale machine learning. SIAM Rev. 60(2), 223\u2013311 (2018)","journal-title":"SIAM Rev."},{"issue":"25","key":"10409_CR3","first-page":"536","volume":"1847","author":"A Cauchy","year":"1847","unstructured":"Cauchy, A.: M\u00e9thode g\u00e9n\u00e9rale pour la r\u00e9solution des systemes d\u2019\u00e9quations simultan\u00e9es[J]. Comp. Rend. Sci. Paris 1847(25), 536\u2013538 (1847)","journal-title":"Comp. Rend. Sci. Paris"},{"issue":"1","key":"10409_CR4","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/s102550200010","volume":"18","author":"YH Dai","year":"2002","unstructured":"Dai, Y.H.: Conjugate gradient methods with Armijo-type line searches. Acta Math. Appl. Sin. 18(1), 123\u2013130 (2002)","journal-title":"Acta Math. Appl. Sin."},{"issue":"1","key":"10409_CR5","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 J. Optim. 10(1), 177\u2013182 (1999)","journal-title":"SIAM J. Optim."},{"key":"10409_CR6","unstructured":"Defazio, A., Bach, F., Lacoste-Julien S.: . SAGA: a fast incremental gradient method with support for non-strongly convex composite objectives. Adv. Neural Inform. Process. Syst. (2014), 27"},{"issue":"2","key":"10409_CR7","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. Comput. J. 7(2), 149\u2013154 (1964)","journal-title":"Comput. J."},{"key":"10409_CR8","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep learning. MIT press, (2016)"},{"issue":"1","key":"10409_CR9","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 J. Optim. 16(1), 170\u2013192 (2005)","journal-title":"SIAM J. Optim."},{"key":"10409_CR10","doi-asserted-by":"crossref","unstructured":"Huang, R., Qin, Y., Liu, K., Yuan, G. (2023). Biased stochastic conjugate gradient algorithm with adaptive step size for nonconvex problems. Expert Systems with Applications 121556","DOI":"10.1016\/j.eswa.2023.121556"},{"issue":"6","key":"10409_CR11","doi-asserted-by":"publisher","first-page":"5469","DOI":"10.1007\/s11071-022-08013-1","volume":"111","author":"XZ Jiang","year":"2023","unstructured":"Jiang, X.Z., Zhu, Y.H., Jian, J.B.: Two efficient nonlinear conjugate gradient methods with restart procedures and their applications in image restoration[J]. Nonlinear Dyn. 111(6), 5469\u20135498 (2023)","journal-title":"Nonlinear Dyn."},{"issue":"5","key":"10409_CR12","doi-asserted-by":"publisher","first-page":"1360","DOI":"10.1109\/TNNLS.2018.2868835","volume":"30","author":"XB Jin","year":"2018","unstructured":"Jin, X.B., Zhang, X.Y., Huang, K., et al.: Stochastic conjugate gradient algorithm with variance reduction. IEEE Trans. Neural Netw. Learn. Syst. 30(5), 1360\u20131369 (2018)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10409_CR13","unstructured":"Johnson, R., Zhang, T.: Accelerating stochastic gradient descent using predictive variance reduction. Adv. Neural Inform. Process. Syst. (2013), 26"},{"key":"10409_CR14","doi-asserted-by":"crossref","unstructured":"Karimi, H., Nutini, J., Schmidt, M. (2016). Linear convergence of gradient and proximal-gradient methods under the polyak\u2013ojasiewicz condition. In Machine learning and knowledge discovery in databases: European conference, ECML PKDD 2016, Riva del Garda, Italy, September 19-23, 2016, Proceedings, Part I 16 (pp. 795-811). Springer International Publishing","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"10409_CR15","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.neunet.2022.12.001","volume":"159","author":"H Kim","year":"2023","unstructured":"Kim, H., Wang, C., Byun, H., et al.: Variable three-term conjugate gradient method for training artificial neural networks. Neural Netw. 159, 125\u2013136 (2023)","journal-title":"Neural Netw."},{"key":"10409_CR16","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.neunet.2022.12.001","volume":"159","author":"H Kim","year":"2023","unstructured":"Kim, H., Wang, C., Byun, H., et al.: Variable three-term conjugate gradient method for training artificial neural networks. Neural Netw. 159, 125\u2013136 (2023)","journal-title":"Neural Netw."},{"key":"10409_CR17","unstructured":"Kingma D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, (2014)"},{"key":"10409_CR18","first-page":"1","volume":"87","author":"C Kou","year":"2022","unstructured":"Kou, C., Yang, H.: A mini-batch stochastic conjugate gradient algorithm with variance reduction. J. Glob. Optim. 87, 1\u201317 (2022)","journal-title":"J. Glob. Optim."},{"issue":"5","key":"10409_CR19","first-page":"566","volume":"6","author":"A Lydia","year":"2019","unstructured":"Lydia, A., Francis, S.: Adagrad-an optimizer for stochastic gradient descent. Int. J. Inf. Comput. Sci. 6(5), 566\u2013568 (2019)","journal-title":"Int. J. Inf. Comput. Sci."},{"key":"10409_CR20","unstructured":"Nguyen L.M., Liu, J., Scheinberg, K, et al. SARAH: a novel method for machine learning problems using stochastic recursive gradient\/\/International conference on machine learning. PMLR, 2017: 2613-2621"},{"key":"10409_CR21","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., Wu, J., Jiang, X., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10409_CR22","doi-asserted-by":"crossref","unstructured":"Polak, E., Ribiere, G.: Note sur la convergence de m\u00e9thodes de directions conjugu\u00e9es[J]. Revue fran\u00e7aise d\u2019informatique et de recherche op\u00e9rationnelle. S\u00e9rie rouge, 1969, 3(16): 35-43","DOI":"10.1051\/m2an\/196903R100351"},{"issue":"4","key":"10409_CR23","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 extremal problems. USSR Comput. Math. Math. Phys. 9(4), 94\u2013112 (1969)","journal-title":"USSR Comput. Math. Math. Phys."},{"key":"10409_CR24","unstructured":"Reddi, S.J, Kale, S., Kumar, S.: On the convergence of adam and beyond. arXiv preprint arXiv:1904.09237, (2019)"},{"key":"10409_CR25","doi-asserted-by":"crossref","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 1951: 400-407","DOI":"10.1214\/aoms\/1177729586"},{"key":"10409_CR26","doi-asserted-by":"crossref","unstructured":"Schmidt, M., Le Roux, N., Bach, F.: Minimizing finite sums with the stochastic average gradient. Math. Program. 162, 83\u2013112 (2017)","DOI":"10.1007\/s10107-016-1030-6"},{"issue":"3","key":"10409_CR27","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1007\/s11075-022-01448-y","volume":"93","author":"X Wang","year":"2023","unstructured":"Wang, X., Yuan, G., Pang, L.: A class of new three-term descent conjugate gradient algorithms for large-scale unconstrained optimization and applications to image restoration problems. Numer Algorithms 93(3), 949\u2013970 (2023)","journal-title":"Numer Algorithms"},{"key":"10409_CR28","doi-asserted-by":"crossref","unstructured":"Wang B, Ye Q. Improving deep neural networks\u2019 training for image classification with nonlinear conjugate gradient-style adaptive momentum. IEEE Trans. Neural Netw. Learn. Syst. 2023","DOI":"10.1109\/TNNLS.2023.3255783"},{"key":"10409_CR29","doi-asserted-by":"crossref","unstructured":"Wolfe, P.: Convergence conditions for ascent methods. SIAM Rev. 11(2), 226\u2013235 (1969)","DOI":"10.1137\/1011036"},{"key":"10409_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117719","volume":"206","author":"Z Yang","year":"2022","unstructured":"Yang, Z.: Adaptive stochastic conjugate gradient for machine learning. Expert Syst. Appl. 206, 117719 (2022)","journal-title":"Expert Syst. Appl."},{"key":"10409_CR31","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1016\/j.cam.2018.10.057","volume":"362","author":"G Yuan","year":"2019","unstructured":"Yuan, G., Wei, Z., Yang, Y.: The global convergence of the Polak-Ribi\u00e8re-Polyak conjugate gradient algorithm under inexact line search for nonconvex functions[J]. J. Comput. Appl. Math. 362, 262\u2013275 (2019)","journal-title":"J. Comput. Appl. Math."},{"issue":"8","key":"10409_CR32","doi-asserted-by":"publisher","first-page":"5867","DOI":"10.1007\/s00500-021-05580-0","volume":"25","author":"G Yuan","year":"2021","unstructured":"Yuan, G., Lu, J., Wang, Z.: The modified PRP conjugate gradient algorithm under a non-descent line search and its application in the Muskingum model and image restoration problems. Soft. Comput. 25(8), 5867\u20135879 (2021)","journal-title":"Soft. Comput."},{"key":"10409_CR33","doi-asserted-by":"publisher","first-page":"119818","DOI":"10.1109\/ACCESS.2021.3108418","volume":"9","author":"G Yuan","year":"2021","unstructured":"Yuan, G., Zhou, Y., Wang, L., et al.: Stochastic bigger subspace algorithms for nonconvex stochastic optimization. IEEE Access 9, 119818\u2013119829 (2021)","journal-title":"IEEE Access"},{"key":"10409_CR34","doi-asserted-by":"crossref","unstructured":"Yuan, G., Yang, H., Zhang, M.: Adaptive three-term PRP algorithms without gradient Lipschitz continuity condition for nonconvex functions. Num. Algorithms 91(1), 145\u2013160 (2022)","DOI":"10.1007\/s11075-022-01257-3"},{"issue":"6","key":"10409_CR35","doi-asserted-by":"publisher","first-page":"4691","DOI":"10.1007\/s12190-022-01724-z","volume":"68","author":"G Yuan","year":"2022","unstructured":"Yuan, G., Jian, A., Zhang, M., et al.: A modified HZ conjugate gradient algorithm without gradient Lipschitz continuous condition for non convex functions. J. Appl. Math. Comput. 68(6), 4691\u20134712 (2022)","journal-title":"J. Appl. Math. Comput."},{"key":"10409_CR36","unstructured":"Zeiler M D. Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701, 2012"},{"issue":"4","key":"10409_CR37","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1080\/10556780701223293","volume":"22","author":"L Zhang","year":"2007","unstructured":"Zhang, L., Zhou, W., Li, D.: Some descent three-term conjugate gradient methods and their global convergence. Optim. Methods Softw. 22(4), 697\u2013711 (2007)","journal-title":"Optim. Methods Softw."},{"key":"10409_CR38","first-page":"18795","volume":"33","author":"J Zhuang","year":"2020","unstructured":"Zhuang, J., Tang, T., Ding, Y., et al.: Adabelief optimizer: adapting stepsizes by the belief in observed gradients. Adv. Neural. Inf. Process. Syst. 33, 18795\u201318806 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Statistics and Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-024-10409-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11222-024-10409-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-024-10409-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,25]],"date-time":"2024-05-25T07:10:45Z","timestamp":1716621045000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11222-024-10409-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,27]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["10409"],"URL":"https:\/\/doi.org\/10.1007\/s11222-024-10409-5","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3823283\/v1","asserted-by":"object"}]},"ISSN":["0960-3174","1573-1375"],"issn-type":[{"value":"0960-3174","type":"print"},{"value":"1573-1375","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,27]]},"assertion":[{"value":"30 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 February 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"107"}}