{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T04:41:45Z","timestamp":1745469705623,"version":"3.40.4"},"reference-count":38,"publisher":"Informa UK Limited","issue":"3","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473292","62088101"],"award-info":[{"award-number":["62473292","62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Journal of Control and Decision"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1080\/23307706.2025.2469888","type":"journal-article","created":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T03:55:01Z","timestamp":1740714901000},"page":"421-433","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":0,"title":["On linear convergence of exponential sign-based gradient descent"],"prefix":"10.1080","volume":"12","author":[{"given":"Kangchen","family":"He","sequence":"first","affiliation":[{"name":"Tongji University","place":["Shanghai, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihai","family":"Qu","sequence":"additional","affiliation":[{"name":"Tongji University","place":["Shanghai, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiuxian","family":"Li","sequence":"additional","affiliation":[{"name":"Tongji University","place":["Shanghai, People's Republic of China"]},{"name":"Tongji University","place":["Shanghai, People's Republic of China"]},{"name":"Tongji University","place":["Shanghai, People's Republic of China"]},{"name":"Tongji University","place":["Shanghai, People's Republic of China"]},{"name":"Tongji University","place":["Shanghai, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Xu","sequence":"additional","affiliation":[{"name":"Tongji University","place":["Shanghai, People's Republic of China"]},{"name":"Tongji University","place":["Shanghai, People's Republic of China"]},{"name":"Tongji University","place":["Shanghai, People's Republic of China"]},{"name":"Tongji University","place":["Shanghai, People's Republic of China"]},{"name":"Tongji University","place":["Shanghai, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2025,2,27]]},"reference":[{"key":"e_1_3_2_2_1","unstructured":"Alistarh D. Grubic D. Li J. Tomioka R. & Vojnovic M. (2017). QSGD: Communication-efficient SGD via gradient quantization and encoding. In Advances in neural information processing systems 30. Curran Associates Inc."},{"key":"e_1_3_2_3_1","unstructured":"Balles L. Pedregosa F. & Roux N. L. (2020). The geometry of sign gradient descent. Preprint arXiv:2002.08056."},{"key":"e_1_3_2_4_1","unstructured":"Bernstein J. Wang Y. Azizzadenesheli K. & Anandkumar A. (2018). Compression by the signs: Distributed learning is a two-way street. In International Conference on Learning Representations. OpenReview.net."},{"key":"e_1_3_2_5_1","unstructured":"Bernstein J. Zhao J. Azizzadenesheli K. & Anandkumar A. (2019). signSGD with majority vote is communication efficient and fault tolerant. In International Conference on Learning Representations. OpenReview.net."},{"key":"e_1_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"e_1_3_2_7_1","unstructured":"Carlson D. Cevher V. & Carin L. (2015). Stochastic spectral descent for restricted Boltzmann machines. In Artificial intelligence and statistics (pp. 111\u2013119). PMLR."},{"key":"e_1_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1080\/23307706.2017.1419837"},{"key":"e_1_3_2_9_1","doi-asserted-by":"crossref","unstructured":"Fonseca C. M. & Fleming P. J. (1995). Multiobjective genetic algorithms made easy: Selection sharing and mating restriction. In International Conference on Genetic Algorithms in Engineering Systems: Innovations and Applications (pp. 45\u201352). IET.","DOI":"10.1049\/cp:19951023"},{"key":"e_1_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC62350.2024.10588228"},{"key":"e_1_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(01)00700-7"},{"key":"e_1_3_2_12_1","unstructured":"Karimireddy S. P. Rebjock Q. Stich S. & Jaggi M. (2019). Error feedback fixes SignSGD and other gradient compression schemes. In International Conference on Machine Learning (pp. 3252\u20133261). PMLR."},{"key":"e_1_3_2_13_1","unstructured":"Kingma D. P. & Ba J. (2014). Adam: A method for stochastic optimization. Preprint arXiv:1412.6980."},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3280938"},{"key":"e_1_3_2_15_1","unstructured":"Li X. Zhuang Z. & Orabona F. (2021). A second look at exponential and cosine step sizes: Simplicity adaptivity and performance. In International Conference on Machine Learning (pp. 6553\u20136564). PMLR."},{"key":"e_1_3_2_16_1","unstructured":"Liu S. Chen P. Y. Chen X. & Hong M. (2018). signSGD via zeroth-order oracle. In International Conference on Learning Representations. OpenReview.net."},{"key":"e_1_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.02.012"},{"key":"e_1_3_2_18_1","first-page":"87","article-title":"Une propri\u00e9t\u00e9 topologique des sous-ensembles analytiques r\u00e9els","volume":"117","author":"Lojasiewicz S.","year":"1963","unstructured":"Lojasiewicz, S. (1963). Une propri\u00e9t\u00e9 topologique des sous-ensembles analytiques r\u00e9els. Les \u00e9quations aux d\u00e9riv\u00e9es partielles, 117, 87\u201389.","journal-title":"Les \u00e9quations aux d\u00e9riv\u00e9es partielles"},{"key":"e_1_3_2_19_1","unstructured":"Ma C. Wu L. & Weinan E. (2022). A qualitative study of the dynamic behavior for adaptive gradient algorithms. In Mathematical and scientific machine learning (pp. 671\u2013692). PMLR."},{"key":"e_1_3_2_20_1","unstructured":"Malitsky Y. & Mishchenko K. (2019). Adaptive gradient descent without descent. Preprint arXiv:1910.09529."},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.04.012"},{"key":"e_1_3_2_22_1","volume-title":"Introductory lectures on convex optimization: A basic course","author":"Nesterov Y.","year":"2003","unstructured":"Nesterov, Y. (2003). Introductory lectures on convex optimization: A basic course (Vol. 87). Springer Science & Business Media."},{"issue":"4","key":"e_1_3_2_23_1","first-page":"643","article-title":"Gradient methods for minimizing functionals","volume":"3","author":"Polyak B. T.","year":"1963","unstructured":"Polyak, B. T. (1963). Gradient methods for minimizing functionals. Zhurnal Vychislitel'noi Matematiki i Matematicheskoi Fiziki, 3(4), 643\u2013653.","journal-title":"Zhurnal Vychislitel'noi Matematiki i Matematicheskoi Fiziki"},{"key":"e_1_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298623"},{"key":"e_1_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"e_1_3_2_26_1","unstructured":"Ruder S. (2016). An overview of gradient descent optimization algorithms. Preprint arXiv:1609.04747."},{"key":"e_1_3_2_27_1","unstructured":"Safaryan M. & Richt\u00e1rik P. (2021). Stochastic sign descent methods: New algorithms and better theory. In International Conference on Machine Learning (pp. 9224\u20139234). PMLR."},{"key":"e_1_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1080\/23307706.2018.1552208"},{"key":"e_1_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"issue":"2","key":"e_1_3_2_30_1","first-page":"26","article-title":"Lecture 6.5-RMSPROP: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"Tieleman T.","year":"2012","unstructured":"Tieleman, T., & Hinton, G. (2012). Lecture 6.5-RMSPROP: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning, 4(2), 26\u201331.","journal-title":"COURSERA: Neural Networks for Machine Learning"},{"key":"e_1_3_2_31_1","volume-title":"Multiobjective evolutionary algorithms: Classifications, analyses, and new innovations","author":"Van Veldhuizen D. A.","year":"1999","unstructured":"Van Veldhuizen, D. A. (1999). Multiobjective evolutionary algorithms: Classifications, analyses, and new innovations. Air Force Institute of Technology."},{"key":"e_1_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1080\/23307706.2018.1549516"},{"key":"e_1_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.02.039"},{"key":"e_1_3_2_34_1","unstructured":"Ward R. Wu X. & Bottou L. (2018). Adagrad stepsizes: Sharp convergence over nonconvex landscapes from any initialization. Preprint arXiv:1806.01811."},{"key":"e_1_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-012-1274-4"},{"key":"e_1_3_2_36_1","unstructured":"Wen W. Xu C. Yan F. Wu C. Wang Y. Chen Y. & Li H. (2017). Terngrad: Ternary gradients to reduce communication in distributed deep learning. In Advances in neural information processing systems 30. Curran Associates Inc."},{"key":"e_1_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.147"},{"key":"e_1_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2008.02.017"},{"key":"e_1_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119168"}],"container-title":["Journal of Control and Decision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/23307706.2025.2469888","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T20:52:36Z","timestamp":1745441556000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/23307706.2025.2469888"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,27]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["10.1080\/23307706.2025.2469888"],"URL":"https:\/\/doi.org\/10.1080\/23307706.2025.2469888","relation":{},"ISSN":["2330-7706","2330-7714"],"issn-type":[{"type":"print","value":"2330-7706"},{"type":"electronic","value":"2330-7714"}],"subject":[],"published":{"date-parts":[[2025,2,27]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tjcd20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tjcd20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2024-08-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}