{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:07:27Z","timestamp":1782403647198,"version":"3.54.5"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12071356"],"award-info":[{"award-number":["12071356"]}],"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":["12471095"],"award-info":[{"award-number":["12471095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004787","name":"Research Grants Council of Hong Kong","doi-asserted-by":"publisher","award":["22303723"],"award-info":[{"award-number":["22303723"]}],"id":[{"id":"10.13039\/501100004787","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tnnls.2025.3545420","type":"journal-article","created":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T13:39:12Z","timestamp":1742305152000},"page":"14963-14974","source":"Crossref","is-referenced-by-count":3,"title":["Convergence of Adaptive Stochastic Mirror Descent"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9676-2854","authenticated-orcid":false,"given":"Ting","family":"Hu","sequence":"first","affiliation":[{"name":"School of Management, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaotong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Management, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Ji","sequence":"additional","affiliation":[{"name":"Huawei Technologies Company Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5383-467X","authenticated-orcid":false,"given":"Yunwen","family":"Lei","sequence":"additional","affiliation":[{"name":"Department of Mathematics, The University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Large scale gan training for high fidelity natural image synthesis","volume-title":"International Conference on Learning Representations","author":"Brock"},{"key":"ref2","article-title":"Language models are few-shot learners","volume-title":"Advances in neural information processing systems","author":"Brown","year":"2020"},{"key":"ref3","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref4","article-title":"Why are adaptive methods good for attention models","volume-title":"Neural Information Processing Systems","author":"Zhang","year":"2020"},{"key":"ref5","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT, 2019","author":"Devlin"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207425"},{"key":"ref7","article-title":"Improving generalization performance by switching from Adam to SGD","author":"Keskar","year":"2017","journal-title":"CoRR, abs\/1712.07628"},{"key":"ref8","first-page":"8759C8770","article-title":"Uniform convergence of gradients for non-convex learning and optimization","author":"Foster","year":"2018","journal-title":"roc. Adv. Neural Inf. Process"},{"key":"ref9","article-title":"Stochastic composite mirror descent: Optimal bounds with high probabilities","volume-title":"Neural Information Processing Systems","author":"Lei","year":"2018"},{"key":"ref10","volume-title":"Problem Complexity and Method Efficiency in Optimization","author":"Nemirovskij","year":"1983"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2016.0817"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25040-3_39"},{"key":"ref13","article-title":"Adaptive first-order methods revisited: Convex optimization without Lipschitz requirements","author":"Antonakopoulos","year":"2021","journal-title":"arXiv.2107.08011"},{"key":"ref14","first-page":"413","article-title":"Dissecting Adam: The sign, magnitude and variance of stochastic gradients","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018","author":"Balles"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(02)00231-6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-08-02189-3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/0803026"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/452"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-008-9227-0"},{"key":"ref20","article-title":"A simple convergence proof of Adam and Adagrad","volume-title":"Transactions on Machine Learning Research","author":"D\u00e9fossez","year":"2022"},{"key":"ref21","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","article-title":"Composite objective mirror descent","volume-title":"Twenty Third Conference on Computational Learning Theory","author":"Duchi","year":"2010"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/22M1515197"},{"key":"ref24","article-title":"Improved convergence in high probability of clipped gradient methods with heavy tailed noise","volume-title":"Advances in Neural Information Processing Systems","author":"Nguyen","year":"2023"},{"key":"ref25","article-title":"Provable Adaptivity of Adam under Nonuniform Smoothness","author":"Wang","year":"2024","journal-title":"arXiv:2208.09900"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011182"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1287\/moor.18.1.202"},{"key":"ref28","article-title":"A novel convergence analysis for algorithms of the Adam family","volume-title":"Advances in Neural Information Processing Systems 34(NeurIPS)","author":"Guo","year":"2021"},{"key":"ref29","first-page":"3493","article-title":"Taming nonconvex stochastic mirror descent with general Bregman divergence","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Fatkhullin"},{"key":"ref30","first-page":"65","article-title":"Mirror descent strikes again: Optimal stochastic convex optimization under infinite noise variance","volume-title":"Conference on Learning Theory","author":"Vural"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-007-0149-x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/11776420_37"},{"key":"ref33","article-title":"High probability convergence of Adam under unbounded gradients and affine variance noise","author":"Hong","year":"2023","journal-title":"arXiv:2311.02000"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2019.01.002"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/355"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00930"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2018.05.005"},{"key":"ref39","article-title":"Convergence of Adam under relaxed assumptions","author":"Li","year":"2023","journal-title":"arXiv:2304.13972"},{"key":"ref40","first-page":"983","article-title":"On the convergence of stochastic gradient descent with adaptive stepsizes","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics","author":"Li"},{"key":"ref41","first-page":"18261","article-title":"An improved analysis of stochastic gradient descent with momentum","volume-title":"Advances in Neural Information Processing Systems 33 (NeurIPS)","author":"Liu","year":"2020"},{"key":"ref42","article-title":"Fixing weight decay regularization in Adam","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref43","article-title":"Adaptive gradient methods with dynamicbound of learning rate","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"Luo"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-018-01452-0"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BF00940283"},{"key":"ref46","article-title":"On the convergence of Adam and beyond","volume-title":"International Conference on Learning Representations","author":"Reddi"},{"key":"ref47","article-title":"RMSProp: Divide the gradient by a running average of its recent magnitude","author":"Tieleman","year":"2012","journal-title":"Coursera"},{"key":"ref48","first-page":"4148","article-title":"The marginal value of adaptive gradient methods in machine learning","volume-title":"Advances in Neural Information Processing Systems 30","author":"Wilson","year":"2017"},{"key":"ref49","first-page":"2543","article-title":"Dual averaging methods for regularized stochastic learning and online optimization","volume":"11","author":"Xiao","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref50","article-title":"Adaptive methods for nonconvex optimization","volume-title":"Advances in Neural Information Processing Systems 31(NeurIPS)","author":"Zaheer","year":"2018"},{"key":"ref51","article-title":"On the convergence of adaptive gradient methods for nonconvex optimization","author":"Zhou","year":"2018","journal-title":"arXiv.1808.05671."},{"key":"ref52","article-title":"Adashift: Decorrelation and convergence of adaptive learning rate methods","volume-title":"International Conference on Learning Representations","author":"Zhou"},{"key":"ref53","article-title":"Online convex programming and generalized infinitesimal gradient ascent","volume-title":"International Conference on Machine Learning","author":"Zinkevich"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01138"},{"key":"ref55","article-title":"RMSprop converges with proper hyper-parameter","volume-title":"International Conference on Learning Representations","author":"Shi"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2011.09.039"},{"key":"ref57","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv.1412.6980."}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11114436\/10931786.pdf?arnumber=10931786","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:00:56Z","timestamp":1754503256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10931786\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":57,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3545420","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}