{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T12:38:12Z","timestamp":1775911092740,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,8,19]],"date-time":"2022-08-19T00:00:00Z","timestamp":1660867200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,8,19]],"date-time":"2022-08-19T00:00:00Z","timestamp":1660867200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1007\/s11280-022-01086-3","type":"journal-article","created":{"date-parts":[[2022,8,19]],"date-time":"2022-08-19T09:03:51Z","timestamp":1660899831000},"page":"1323-1344","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Unbiased quasi-hyperbolic nesterov-gradient momentum-based optimizers for accelerating convergence"],"prefix":"10.1007","volume":"26","author":[{"given":"Weiwei","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaochun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,8,19]]},"reference":[{"key":"1086_CR1","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1613\/jair.735","volume":"12","author":"B Nebel","year":"2000","unstructured":"Nebel, B.: On the compilability and expressive power of propositional planning formalisms. J. Artif. Intell. Res. 12, 271\u2013315 (2000)","journal-title":"J. Artif. Intell. Res."},{"issue":"1","key":"1086_CR2","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1137\/15M1009597","volume":"26","author":"L Lessard","year":"2016","unstructured":"Lessard, L., Recht, B., Packard, A.K.: Analysis and design of optimization algorithms via integral quadratic constraints. SIAM J. Optim. 26(1), 57\u201395 (2016)","journal-title":"SIAM J. Optim."},{"issue":"5","key":"1086_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-019-8457-x","volume":"14","author":"H Zhong","year":"2020","unstructured":"Zhong, H., Chen, Z., Qin, C., Huang, Z., Zheng, V.W., Xu, T., Chen, E.: Adam revisited: a weighted past gradients perspective. Frontiers Comput. Sci. 14(5), 145309 (2020)","journal-title":"Frontiers Comput. Sci."},{"issue":"4","key":"1086_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11704-020-9203-0","volume":"15","author":"D Jin","year":"2021","unstructured":"Jin, D., He, J., Chai, B., He, D.: Semi-supervised community detection on attributed networks using non-negative matrix tri-factorization with node popularity. Frontiers of Computer Science 15(4), 1\u201311 (2021)","journal-title":"Frontiers of Computer Science"},{"issue":"4","key":"1086_CR5","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1007\/s11704-013-2360-7","volume":"7","author":"Y Ye","year":"2013","unstructured":"Ye, Y., Gong, S., Liu, C., Zeng, J., Jia, N., Zhang, Y.: Online belief propagation algorithm for probabilistic latent semantic analysis. Frontiers Comput. Sci. 7(4), 526\u2013535 (2013)","journal-title":"Frontiers Comput. Sci."},{"issue":"3","key":"1086_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-020-0298-0","volume":"16","author":"Z Tan","year":"2022","unstructured":"Tan, Z., Chen, S.: On the learning dynamics of two-layer quadratic neural networks for understanding deep learning. Frontiers Comput. Sci. 16(3), 163313 (2022)","journal-title":"Frontiers Comput. Sci."},{"issue":"462","key":"1086_CR7","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1198\/016214503000125","volume":"98","author":"P B\u00fchlmann","year":"2003","unstructured":"B\u00fchlmann, P., Yu, B.: Boosting with the l 2 loss: regression and classification. Journal of the American Statistical Association 98(462), 324\u2013339 (2003)","journal-title":"Journal of the American Statistical Association"},{"issue":"6","key":"1086_CR8","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","journal-title":"Commun. ACM"},{"key":"1086_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1086_CR10","unstructured":"Gehring, J., Auli, M., Grangier, D., Yarats, D., Dauphin, Y.N.: Convolutional sequence to sequence learning. In: Proceedings of the 34th International Conference on Machine Learning, ICML 2017, vol. 70, pp. 1243\u20131252 (2017)"},{"key":"1086_CR11","doi-asserted-by":"crossref","unstructured":"Dong, Q., Niu, S., Yuan, T., Li, Y.: Disentangled graph recurrent network for document ranking. Data Sci. Eng. 7(1), 30\u201343 (2022)","DOI":"10.1007\/s41019-022-00179-3"},{"issue":"1","key":"1086_CR12","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/s41019-019-00113-0","volume":"5","author":"J He","year":"2020","unstructured":"He, J., Liu, H., Zheng, Y., Tang, S., He, W., Du, X.: Bi-labeled LDA: inferring interest tags for non-famous users in social network. Data Sci. Eng. 5(1), 27\u201347 (2020)","journal-title":"Data Sci. Eng."},{"issue":"4","key":"1086_CR13","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/s41019-021-00168-y","volume":"6","author":"H Abburi","year":"2021","unstructured":"Abburi, H., Parikh, P., Chhaya, N., Varma, V.: Fine-grained multi-label sexism classification using a semi-supervised multi-level neural approach. Data Sci. Eng. 6(4), 359\u2013379 (2021)","journal-title":"Data Sci. Eng."},{"issue":"2","key":"1086_CR14","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1007\/s11704-018-8148-z","volume":"14","author":"H Xue","year":"2020","unstructured":"Xue, H., Xu, H., Chen, X., Wang, Y.: A primal perspective for indefinite kernel SVM problem. Frontiers Comput. Sci. 14(2), 349\u2013363 (2020)","journal-title":"Frontiers Comput. Sci."},{"key":"1086_CR15","unstructured":"Jain, P., Kakade, S.M., Kidambi, R., Netrapalli, P., Sidford, A.: Accelerating stochastic gradient descent. arXiv preprint\u00a0arXiv:1704.08227 (2017)"},{"key":"1086_CR16","doi-asserted-by":"crossref","unstructured":"Cyrus, S., Hu, B., Scoy, B.V., Lessard, L.: A robust accelerated optimization algorithm for strongly convex functions. In: 2018 Annual American Control Conference, ACC 2018, pp. 1376\u20131381 (2018)","DOI":"10.23919\/ACC.2018.8430824"},{"issue":"1","key":"1086_CR17","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/LCSYS.2017.2722406","volume":"2","author":"BV Scoy","year":"2018","unstructured":"Scoy, B.V., Freeman, R.A., Lynch, K.M.: The fastest known globally convergent first-order method for minimizing strongly convex functions. IEEE Control. Syst. Lett. 2(1), 49\u201354 (2018)","journal-title":"IEEE Control. Syst. Lett."},{"key":"1086_CR18","doi-asserted-by":"crossref","unstructured":"Kidambi, R., Netrapalli, P., Jain, P., Kakade, S.M.: On the insufficiency of existing momentum schemes for stochastic optimization. In: 6th International Conference on Learning Representations, ICLR 2018 (2018)","DOI":"10.1109\/ITA.2018.8503173"},{"key":"1086_CR19","doi-asserted-by":"crossref","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. The annals of mathematical statistics, 400\u2013407 (1951)","DOI":"10.1214\/aoms\/1177729586"},{"issue":"5","key":"1086_CR20","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"},{"issue":"1","key":"1086_CR21","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 Networks 12(1), 145\u2013151 (1999)","journal-title":"Neural Networks"},{"key":"1086_CR22","unstructured":"Ruder, S.: An overview of gradient descent optimization algorithms. arXiv preprint\u00a0arXiv:1609.04747 (2016)"},{"key":"1086_CR23","doi-asserted-by":"crossref","unstructured":"Zhou, B., Liu, J., Sun, W., Chen, R., Tomlin, C.J., Yuan, Y.: pbsgd: Powered stochastic gradient descent methods for accelerated non-convex optimization. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020, pp. 3258\u20133266 (2020)","DOI":"10.24963\/ijcai.2020\/451"},{"key":"1086_CR24","doi-asserted-by":"crossref","unstructured":"Luo, L., Huang, W., Zeng, Q., Nie, Z., Sun, X.: Learning personalized end-to-end goal-oriented dialog. In: The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, pp. 6794\u20136801 (2019)","DOI":"10.1609\/aaai.v33i01.33016794"},{"key":"1086_CR25","doi-asserted-by":"crossref","unstructured":"Wu, Y., He, K.: Group normalization. In: Computer Vision -ECCV 2018. Lecture Notes in Computer Science, vol. 11217, pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"1086_CR26","unstructured":"Ma, J., Yarats, D.: Quasi-hyperbolic momentum and adam for deep learning. In: 7th International Conference on Learning Representations, ICLR 2019 (2019)"},{"key":"1086_CR27","unstructured":"Nesterov, Y.E.: A method for solving the convex programming problem with convergence rate o (1\/k2). Dokl. Akad. Nauk Sssr. 269, 543\u2013547 (1983)"},{"key":"1086_CR28","unstructured":"Reddi, S.J., Kale, S., Kumar, S.: On the convergence of adam and beyond. In: 6th International Conference on Learning Representations, ICLR 2018 (2018)"},{"issue":"2","key":"1086_CR29","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":"5","key":"1086_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3234150","volume":"51","author":"S Pouyanfar","year":"2019","unstructured":"Pouyanfar, S., Sadiq, S., Yan, Y., Tian, H., Tao, Y., Reyes, M.E.P., Shyu, M., Chen, S., Iyengar, S.S.: A survey on deep learning: Algorithms, techniques, and applications. ACM Comput. Surv. 51(5), 1\u201336 (2019)","journal-title":"ACM Comput. Surv."},{"key":"1086_CR31","doi-asserted-by":"crossref","unstructured":"Ben-Tal, A., Nemirovskii, A.: Lectures on Modern Convex Optimization - Analysis, Algorithms, and Engineering Applications. MPS-SIAM series on optimization, (2001)","DOI":"10.1137\/1.9780898718829"},{"key":"1086_CR32","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015 (2015)"},{"key":"1086_CR33","unstructured":"Dozat, T.: Incorporating nesterov momentum into adam. In: International Conference on Learning Representations Workshop (2016)"},{"key":"1086_CR34","unstructured":"Zeiler, M.D.: ADADELTA: an adaptive learning rate method. CoRR (2012)"},{"key":"1086_CR35","unstructured":"Baydin, A.G., Cornish, R., Mart\u00ednez-Rubio, D., Schmidt, M., Wood, F.: Online learning rate adaptation with hypergradient descent. In: 6th International Conference on Learning Representations, ICLR 2018 (2018)"},{"key":"1086_CR36","unstructured":"Vapnik, V.N.: Adaptive and learning systems for signal processing communications, and control. Statistical learning theory (1998)"},{"issue":"11","key":"1086_CR37","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"1086_CR38","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. In: Tech Report (2009)"},{"issue":"3","key":"1086_CR39","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.S., Berg, A.C., Fei-Fei, L.: Imagenet large scale visual recognition challenge. IJCV 115(3), 211\u2013252 (2015)","journal-title":"IJCV"},{"key":"1086_CR40","unstructured":"Wright, R.E.: Logistic regression. (1995)"},{"key":"1086_CR41","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations, ICLR 2015 (2015)"}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-022-01086-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11280-022-01086-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-022-01086-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T14:34:51Z","timestamp":1690382091000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11280-022-01086-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,19]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["1086"],"URL":"https:\/\/doi.org\/10.1007\/s11280-022-01086-3","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"value":"1386-145X","type":"print"},{"value":"1573-1413","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,19]]},"assertion":[{"value":"24 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval and Consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and Animal Ethics"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}