{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T20:24:45Z","timestamp":1784233485911,"version":"3.55.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T00:00:00Z","timestamp":1679875200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T00:00:00Z","timestamp":1679875200000},"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":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1007\/s11432-022-3539-8","type":"journal-article","created":{"date-parts":[[2023,3,31]],"date-time":"2023-03-31T16:02:54Z","timestamp":1680278574000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["State space representation and phase analysis of gradient descent optimizers"],"prefix":"10.1007","volume":"66","author":[{"given":"Biyuan","family":"Yao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guiqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,3,27]]},"reference":[{"key":"3539_CR1","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, 2017, 60: 84\u201390","journal-title":"Commun ACM"},{"key":"3539_CR2","volume-title":"Python Machine Learning Algorithm and Practice (in Chinese)","author":"Y L Sun","year":"2021","unstructured":"Sun Y L, Yu B G. Python Machine Learning Algorithm and Practice (in Chinese). Beijing: Publishing House of Electronics Industry, 2021"},{"key":"3539_CR3","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. Ann Math Statist, 1951, 22: 400\u2013407","journal-title":"Ann Math Statist"},{"key":"3539_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0041-5553(64)90137-5","volume":"4","author":"B T Polyak","year":"1964","unstructured":"Polyak B T. Some methods of speeding up the convergence of iteration methods. USSR Comput Math Math Phys, 1964, 4: 1\u201317","journal-title":"USSR Comput Math Math Phys"},{"key":"3539_CR5","first-page":"543","volume":"27","author":"Y E Nesterov","year":"1983","unstructured":"Nesterov Y E. A method for unconstrained convex minimization problem with the rate of convergence O(1\/k2). Doklady ANSSSR, 1983, 27: 543\u2013547","journal-title":"Doklady ANSSSR"},{"key":"3539_CR6","doi-asserted-by":"crossref","unstructured":"An W P, Wang H Q, Sun Q Y, et al. A PID controller approach for stochastic optimization of deep networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2018. 8522\u20138531","DOI":"10.1109\/CVPR.2018.00889"},{"key":"3539_CR7","doi-asserted-by":"publisher","first-page":"5079","DOI":"10.1109\/TNNLS.2019.2963066","volume":"31","author":"H Q Wang","year":"2020","unstructured":"Wang H Q, Luo Y, An W P, et al. PID controller-based stochastic optimization acceleration for deep neural networks. IEEE Trans Neural Netw Learn Syst, 2020, 31: 5079\u20135091","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"3539_CR8","doi-asserted-by":"publisher","first-page":"150102","DOI":"10.1007\/s11432-020-3163-0","volume":"64","author":"W Wu","year":"2021","unstructured":"Wu W, Jing X Y, Du W C, et al. Learning dynamics of gradient descent optimization in deep neural networks. Sci China Inf Sci, 2021, 64: 150102","journal-title":"Sci China Inf Sci"},{"key":"3539_CR9","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1214\/aoms\/1177728659","volume":"25","author":"J R Blum","year":"1954","unstructured":"Blum J R. Multidimensional stochastic approximation methods. Ann Math Statist, 1954, 25: 737\u2013744","journal-title":"Ann Math Statist"},{"key":"3539_CR10","volume-title":"Deep Learning Through Sparse and Low-Rank Modeling (in Chinese)","author":"Z Y Wang","year":"2021","unstructured":"Wang Z Y, Fu Y, Huang S T. Deep Learning Through Sparse and Low-Rank Modeling (in Chinese). Beijing: China Machine Press, 2021"},{"key":"3539_CR11","doi-asserted-by":"publisher","first-page":"4394","DOI":"10.1109\/TNNLS.2019.2952219","volume":"31","author":"Y W Lei","year":"2020","unstructured":"Lei Y W, Hu T, Li G Y, et al. Stochastic gradient descent for nonconvex learning without bounded gradient assumptions. IEEE Trans Neural Netw Learn Syst, 2020, 31: 4394\u20134400","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"3539_CR12","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1109\/78.295190","volume":"42","author":"I Engel","year":"1994","unstructured":"Engel I, Bershad N J. A transient learning comparison of Rosenblatt, backpropagation, and LMS algorithms for a single-layer perceptron for system identification. IEEE Trans Signal Process, 1994, 42: 1247\u20131251","journal-title":"IEEE Trans Signal Process"},{"key":"3539_CR13","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1162\/089976698300017007","volume":"10","author":"H H Yang","year":"1998","unstructured":"Yang H H, Amari S. Complexity issues in natural gradient descent method for training multilayer perceptrons. Neural Computation, 1998, 10: 2137\u20132157","journal-title":"Neural Computation"},{"key":"3539_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000006","volume":"2","author":"Y Bengio","year":"2009","unstructured":"Bengio Y. Learning deep architectures for AI. FNT Machine Learn, 2009, 2: 1\u2013127","journal-title":"FNT Machine Learn"},{"key":"3539_CR15","unstructured":"Li Y Z, Liang Y Y. Learning overparameterized neural networks via stochastic gradient descent on structured data. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, Paris, 2018. 8168\u20138177"},{"key":"3539_CR16","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1109\/JAS.2020.1003396","volume":"8","author":"X Luo","year":"2021","unstructured":"Luo X, Qin W, Dong A, et al. Efficient and high-quality recommendations via momentum-incorporated parallel stochastic gradient descent-based learning. IEEE CAA J Autom Sin, 2021, 8: 402\u2013411","journal-title":"IEEE CAA J Autom Sin"},{"key":"3539_CR17","unstructured":"Ruder S. An overview of gradient descent optimization algorithms. 2017. ArXiv:1609.04747"},{"key":"3539_CR18","unstructured":"Ding X H, Ding G G, Zhou X X, et al. Global sparse momentum SGD for pruning very deep neural networks. In: Proceedings of the 33rd Conference on Neural Information Processing Systems, Vancouver, 2019. 1\u201313"},{"key":"3539_CR19","unstructured":"Wang J Y, Tantia V, Ballas N, et al. SlowMo: improving communication-efficient distributed SGD with slow momentum. In: Proceedings of International Conference on Learning Representation, 2020. 1\u201327"},{"key":"3539_CR20","unstructured":"Jarek D. SGD momentum optimizer with step estimation by online parabola model. 2019. ArXiv:1907.07063"},{"key":"3539_CR21","unstructured":"Aleksandar B, Guy L, David B. Nesterov\u2019s accelerated gradient and momentum as approximations to regularised update descent. In: Proceedings of International Joint Conference on Neural Networks, Anchorage, 2017. 1899\u20131903"},{"key":"3539_CR22","unstructured":"Luo L C, Xiong Y H, Liu Y, et al. Adaptive gradient methods with dynamic bound of learning rate. In: Proceedings of International Conference on Learning Representation, New Orleans, 2019. 1\u201319"},{"key":"3539_CR23","first-page":"8194","volume":"18","author":"A Z Zeyuan","year":"2017","unstructured":"Zeyuan A Z. Katyusha: the first direct acceleration of stochastic gradient methods. J Mach Learning Res, 2017, 18: 8194\u20138244","journal-title":"J Mach Learning Res"},{"key":"3539_CR24","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1109\/LRA.2019.2891986","volume":"4","author":"X Luo","year":"2019","unstructured":"Luo X, Zhou M C. Effects of extended stochastic gradient descent algorithms on improving latent factor-based recommender systems. IEEE Robot Autom Lett, 2019, 4: 618\u2013624","journal-title":"IEEE Robot Autom Lett"},{"key":"3539_CR25","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1109\/TSMC.2018.2884191","volume":"51","author":"X Luo","year":"2021","unstructured":"Luo X, Wang D X, Zhou M C, et al. Latent factor-based recommenders relying on extended stochastic gradient descent algorithms. IEEE Trans Syst Man Cyber Syst, 2021, 51: 916\u2013926","journal-title":"IEEE Trans Syst Man Cyber Syst"},{"key":"3539_CR26","doi-asserted-by":"publisher","first-page":"4505","DOI":"10.1109\/TPAMI.2021.3068154","volume":"43","author":"Y W Lei","year":"2021","unstructured":"Lei Y W, Tang K. Learning rates for stochastic gradient descent with nonconvex objectives. IEEE Trans Pattern Anal Mach Intell, 2021, 43: 4505\u20134511","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3539_CR27","unstructured":"Amid E, Anil R, Fifty C, et al. Step-size adaptation using exponentiated gradient updates. 2022. ArXiv:2202.00145"},{"key":"3539_CR28","unstructured":"Andrychowicz M, Denil M, Colmenarejo G S, et al. Learning to learn by gradient descent by gradient descent. In: Proceedings of Advances in Neural Information Processing Systems, 2016. 1\u20139"},{"key":"3539_CR29","unstructured":"Xiong Y H, Lan L C, Chen X N, et al. Learning to schedule learning rate with graph neural networks. In: Proceedings of International Conference on Learning Representations, 2022. 1\u201321"},{"key":"3539_CR30","doi-asserted-by":"crossref","unstructured":"Shu J, Zhu Y W, Zhao Q, et al. MLR-SNet: transferable LR schedules for heterogeneous tasks. In: Proceedings of International Conference on Learning Representations, 2021. 1\u201325","DOI":"10.1109\/TPAMI.2022.3184315"},{"key":"3539_CR31","doi-asserted-by":"publisher","first-page":"33","DOI":"10.3182\/20120823-5-NL-3013.00064","volume":"45","author":"T Alamo","year":"2012","unstructured":"Alamo T, Ferramosca A, Gonz\u00e1lez A H, et al. A gradient-based strategy for integrating real time optimizer (RTO) with model predictive control (MPC). IFAC Proc Volumes, 2012, 45: 33\u201338","journal-title":"IFAC Proc Volumes"},{"key":"3539_CR32","doi-asserted-by":"publisher","first-page":"7634","DOI":"10.1109\/TCYB.2020.3036646","volume":"52","author":"J N Chen","year":"2022","unstructured":"Chen J N, Hua C C. Adaptive full-state-constrained control of nonlinear systems with deferred constraints based on nonbarrier Lyapunov function method. IEEE Trans Cybern, 2022, 52: 7634\u20137642","journal-title":"IEEE Trans Cybern"},{"key":"3539_CR33","doi-asserted-by":"publisher","first-page":"4238","DOI":"10.1109\/TNNLS.2017.2760979","volume":"29","author":"T H Lee","year":"2018","unstructured":"Lee T H, Trinh H M, Park J H. Stability analysis of neural networks with time-varying delay by constructing novel Lyapunov functionals. IEEE Trans Neural Netw Learn Syst, 2018, 29: 4238\u20134247","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"3539_CR34","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1016\/j.neunet.2020.06.013","volume":"129","author":"O Faydasicok","year":"2020","unstructured":"Faydasicok O. A new Lyapunov functional for stability analysis of neutral-type Hopfield neural networks with multiple delays. Neural Networks, 2020, 129: 288\u2013297","journal-title":"Neural Networks"},{"key":"3539_CR35","doi-asserted-by":"publisher","unstructured":"Yuan F Y, Liu Y J, Liu L, et al. Adaptive neural consensus tracking control for nonlinear multiagent systems using integral barrier Lyapunov functionals. IEEE Trans Neural Netw Learn Syst, 2021. doi: https:\/\/doi.org\/10.1109\/TNNLS.2021.3112763","DOI":"10.1109\/TNNLS.2021.3112763"},{"key":"3539_CR36","volume-title":"MATLAB\/Simulink and control system simulation (in Chinese)","author":"Z L Wang","year":"2019","unstructured":"Wang Z L, Wang S K, Chen G S, et al. MATLAB\/Simulink and control system simulation (in Chinese). Beijing: Publishing House of Electronics Industry, 2019"},{"key":"3539_CR37","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718669","volume-title":"Control Perspectives on Numerical Algorithms and Matrix Problems","author":"A Bhaya","year":"2006","unstructured":"Bhaya A, Kaszkurewicz E. Control Perspectives on Numerical Algorithms and Matrix Problems. Philadelphia: Society for Industrial and Applied Mathematics, 2006"},{"key":"3539_CR38","doi-asserted-by":"crossref","unstructured":"Chen Y Q, Wei Y H, Wang Y, et al. On the unified design of accelerated gradient descent. In: Proceedings of 2019 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, 2019","DOI":"10.1115\/DETC2019-97624"},{"key":"3539_CR39","doi-asserted-by":"publisher","unstructured":"Liu L, Liu J, Hsieh C J, et al. Stochastically controlled compositional gradient for composition problems. IEEE Trans Neural Netw Learn Syst, 2021, doi: https:\/\/doi.org\/10.1109\/TNNLS.2021.3098222","DOI":"10.1109\/TNNLS.2021.3098222"},{"key":"3539_CR40","volume-title":"Principle of Automatic Control (in Chinese)","author":"B G Xu","year":"2013","unstructured":"Xu B G. Principle of Automatic Control (in Chinese). Beijing: Publishing House of Electronics Industry, 2013"},{"key":"3539_CR41","volume-title":"Signals and Systems (in Chinese)","author":"A V Oppenheim","year":"2020","unstructured":"Oppenheim A V, Willsky A S, Nawab S H. Signals and Systems (in Chinese). 2nd ed. Beijing: Publishing House of Electronics Industry, 2020","edition":"2nd ed"},{"key":"3539_CR42","volume-title":"Higher Mathematics (in Chinese)","author":"Department of Mathematics, Tongji University","year":"2016","unstructured":"Department of Mathematics, Tongji University. Higher Mathematics (in Chinese). Beijing: Posts & Telecom Press, 2016"},{"key":"3539_CR43","volume-title":"Principle of Automatic Control (in Chinese)","author":"G S Gao","year":"2013","unstructured":"Gao G S, Yu W X. Principle of Automatic Control (in Chinese). Guangzhou: South China University of Technology Press, 2013"},{"key":"3539_CR44","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, et al. Gradient-based learning applied to document recognition. Proc IEEE, 1998, 86: 2278\u20132324","journal-title":"Proc IEEE"},{"key":"3539_CR45","unstructured":"Krizhevsky A, Hinton G. Learning Multiple Layers of Features From Tiny Images. Technical Report, University of Toronto, 2009"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-022-3539-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-022-3539-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-022-3539-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,19]],"date-time":"2024-05-19T20:28:08Z","timestamp":1716150488000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-022-3539-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,27]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["3539"],"URL":"https:\/\/doi.org\/10.1007\/s11432-022-3539-8","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,27]]},"assertion":[{"value":"24 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"142102"}}