{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T12:38:13Z","timestamp":1775911093203,"version":"3.50.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2020,1,3]],"date-time":"2020-01-03T00:00:00Z","timestamp":1578009600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,3]],"date-time":"2020-01-03T00:00:00Z","timestamp":1578009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Front. Comput. Sci."],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1007\/s11704-019-8457-x","type":"journal-article","created":{"date-parts":[[2020,1,3]],"date-time":"2020-01-03T05:28:33Z","timestamp":1578029313000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Adam revisited: a weighted past gradients perspective"],"prefix":"10.1007","volume":"14","author":[{"given":"Hui","family":"Zhong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zaiyi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuan","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zai","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent W.","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,1,3]]},"reference":[{"issue":"3","key":"8457_CR1","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins H, Monro S. A stochastic approximation method. The Annals of Mathematical Statistics, 1951, 22(3): 400\u2013407","journal-title":"The Annals of Mathematical Statistics"},{"issue":"Jul","key":"8457_CR2","first-page":"2121","volume":"12","author":"J C Duchi","year":"2011","unstructured":"Duchi J C, Hazan E, Singer Y. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 2011, 12(Jul): 2121\u20132159","journal-title":"Journal of Machine Learning Research"},{"issue":"2","key":"8457_CR3","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, 2012, 4(2): 26\u201331","journal-title":"COURSERA: Neural Networks for Machine Learning"},{"key":"8457_CR4","unstructured":"Zeiler M D. Adadelta: an adaptive learning rate method. 2012, arXiv preprint arXiv:1212.5701"},{"key":"8457_CR5","unstructured":"Kingma D P, Ba J. Adam: a method for stochastic optimization. In: Proceedings of International Conference on Learning Representations. 2015"},{"key":"8457_CR6","doi-asserted-by":"crossref","unstructured":"Yin Y, Huang Z, Chen E, Liu Q, Zhang F, Xie X, Hu G. Transcribing content from structural images with spotlight mechanism. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2018, 2643\u20132652","DOI":"10.1145\/3219819.3219962"},{"key":"8457_CR7","unstructured":"Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems. 2012, 1097\u20131105"},{"key":"8457_CR8","doi-asserted-by":"crossref","unstructured":"Su Y, Liu Q, Liu Q, Huang Z, Yin Y, Chen E, Ding C, Wei S, Hu G. Exercise-enhanced sequential modeling for student performance prediction. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence. 2018, 2435\u20132443","DOI":"10.1609\/aaai.v32i1.11864"},{"key":"8457_CR9","doi-asserted-by":"crossref","unstructured":"Liu Q, Huang Z, Huang Z, Liu C, Chen E, Su Y, Hu G. Finding similar exercises in online education systems. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2018, 1821\u20131830","DOI":"10.1145\/3219819.3219960"},{"issue":"5","key":"8457_CR10","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","volume":"24","author":"G Salton","year":"1988","unstructured":"Salton G, Buckley C. Term-weighting approaches in automatic text retrieval. Information Processing & Management, 1988, 24(5): 513\u2013523","journal-title":"Information Processing & Management"},{"issue":"11","key":"8457_CR11","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. Proceedings of the IEEE, 1998, 86(11): 2278\u20132324","journal-title":"Proceedings of the IEEE"},{"issue":"3\u20134","key":"8457_CR12","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1561\/2400000013","volume":"2","author":"E Hazan","year":"2016","unstructured":"Hazan E. Introduction to online convex optimization. Foundations and Trends in Optimization, 2016, 2(3\u20134): 157\u2013325","journal-title":"Foundations and Trends in Optimization"},{"key":"8457_CR13","unstructured":"Reddi S J, Kale S, Kumar S. On the convergence of adam and beyond. In: Proceedings of International Conference on Learning Representations. 2018"},{"key":"8457_CR14","unstructured":"Mukkamala M C, Hein M. Variants of RMSProp and Adagrad with logarithmic regret bounds. In: Proceedings of the 34th International Conference on Machine Learning. 2017, 2545\u20132553"},{"key":"8457_CR15","unstructured":"Rakhlin A, Shamir O, Sridharan K. Making gradient descent optimal for strongly convex stochastic optimization. In: Proceedings of the 29th International Conference on Machine Learning. 2012, 1571\u20131578"},{"key":"8457_CR16","unstructured":"Shamir O, Zhang T. Stochastic gradient descent for non-smooth optimization: convergence results and optimal averaging schemes. In: Proceedings of the 30th International Conference on Machine Learning. 2013, 71\u201379"},{"key":"8457_CR17","unstructured":"Lacoste-Julien S, Schmidt M, Bach F. A simpler approach to obtaining an O(1\/t) convergence rate for the projected stochastic subgradient method. 2012, arXiv preprint arXiv:1212.2002"},{"key":"8457_CR18","unstructured":"Dean J, Corrado G, Monga R, Chen K, Devin M, Mao M, Ranzato M, Senior A, Tucker P, Yang K, Le Q V, Ng A Y. Large scale distributed deep networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems. 2012, 1223\u20131231"},{"key":"8457_CR19","unstructured":"Chen Z, Xu Y, Chen E, Yang T. SADAGRAD: strongly adaptive stochastic gradient methods. In: Proceedings of the 35th International Conference on Machine Learning. 2018, 912\u2013920"},{"key":"8457_CR20","doi-asserted-by":"crossref","unstructured":"Huang H, Wang C, Dong B. Nostalgic adam: weighing more of the past gradients when designing the adaptive learning rate. 2018, arXiv preprint arXiv:1805.07557","DOI":"10.24963\/ijcai.2019\/355"},{"key":"8457_CR21","unstructured":"Chen J, Gu Q. Closing the generalization gap of adaptive gradient methods in training deep neural networks. 2018, arXiv preprint arXiv:1806.06763"},{"key":"8457_CR22","unstructured":"Zinkevich M. Online convex programming and generalized infinitesimal gradient ascent. In: Proceedings of the 20th International Conference on Machine Learning. 2003, 928\u2013936"},{"issue":"9","key":"8457_CR23","doi-asserted-by":"publisher","first-page":"2050","DOI":"10.1109\/TIT.2004.833339","volume":"50","author":"N Cesa-Bianchi","year":"2004","unstructured":"Cesa-Bianchi N, Conconi A, Gentile C. On the generalization ability of on-line learning algorithms. IEEE Transactions on Information Theory, 2004, 50(9): 2050\u20132057","journal-title":"IEEE Transactions on Information Theory"},{"key":"8457_CR24","unstructured":"Bernstein J, Wang Y, Azizzadenesheli K, Anandkumar A. SIGNSGD: compressed optimisation for non-convex problems. In: Proceedings of the 35th International Conference on Machine Learning. 2018, 559\u2013568"},{"key":"8457_CR25","unstructured":"Dozat T. Incorporating nesterov momentum into adam. In: Proceedings of International Conference on Learning Representations, Workshop Track. 2016"},{"key":"8457_CR26","unstructured":"Krizhevsky A, Hinton G. Learning multiple layers of features from tiny images. Technical Report, Citeseer, 2009"},{"key":"8457_CR27","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. 2016, 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8457_CR28","unstructured":"Yang T, Yan Y, Yuan Z, Jin R. Why does stagewise training accelerate convergence of testing error over SGD? 2018, arXiv preprint arXiv:1812.03934"},{"key":"8457_CR29","unstructured":"Perez L, Wang J. The effectiveness of data augmentation in image classification using deep learning. 2017, arXiv preprint arXiv:1712.04621"},{"key":"8457_CR30","unstructured":"Glorot X, Bengio Y. Understanding the difficulty of training deep feed-forward neural networks. In: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics. 2010, 249\u2013256"},{"key":"8457_CR31","unstructured":"Nair V, Hinton G E. Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning. 2010, 807\u2013814"},{"issue":"1","key":"8457_CR32","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G E, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 2014, 15(1): 1929\u20131958","journal-title":"Journal of Machine Learning Research"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-019-8457-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11704-019-8457-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-019-8457-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T20:15:19Z","timestamp":1665346519000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11704-019-8457-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,3]]},"references-count":32,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2020,10]]}},"alternative-id":["8457"],"URL":"https:\/\/doi.org\/10.1007\/s11704-019-8457-x","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,3]]},"assertion":[{"value":"30 December 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"145309"}}