{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T19:52:24Z","timestamp":1780084344352,"version":"3.54.0"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T00:00:00Z","timestamp":1710374400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T00:00:00Z","timestamp":1710374400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"JST SPRING","award":["JPMJSP2108"],"award-info":[{"award-number":["JPMJSP2108"]}]},{"name":"JSPS Grant-in-Aid for Early-Career Scientists","award":["22K13955"],"award-info":[{"award-number":["22K13955"]}]},{"name":"JSPS Grant-in-Aid for Scientific Research","award":["20H01822"],"award-info":[{"award-number":["20H01822"]}]},{"name":"JSPS Grant-in-Aid for Challenging Research","award":["20K21786"],"award-info":[{"award-number":["20K21786"]}]},{"DOI":"10.13039\/501100004721","name":"The University of Tokyo","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004721","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Numer Algor"],"published-print":{"date-parts":[[2024,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The ordinary differential equation (ODE) models of optimization methods allow for concise proofs of convergence rates through discussions based on Lyapunov functions. The weak discrete gradient (wDG) framework discretizes ODEs while preserving the properties of convergence, serving as a foundation for deriving optimization methods. Although various optimization methods have been derived through wDG, their properties and practical applicability remain underexplored. Hence, this study elucidates these aspects through numerical experiments. Particularly, although wDG yields several implicit methods, we highlight the potential utility of these methods in scenarios where the objective function incorporates a regularization term.<\/jats:p>","DOI":"10.1007\/s11075-024-01790-3","type":"journal-article","created":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T00:03:55Z","timestamp":1710374635000},"page":"1331-1362","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Properties and practicability of convergence-guaranteed optimization methods derived from weak discrete gradients"],"prefix":"10.1007","volume":"96","author":[{"given":"Kansei","family":"Ushiyama","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shun","family":"Sato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takayasu","family":"Matsuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,14]]},"reference":[{"key":"1790_CR1","unstructured":"Su, W., Boyd, S., Cand\u00e8s, E.J.: A differential equation for modeling Nesterov\u2019s accelerated gradient method: theory and insights. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"issue":"113","key":"1790_CR2","first-page":"1","volume":"22","author":"AC Wilson","year":"2021","unstructured":"Wilson, A.C., Recht, B., Jordan, M.I.: A Lyapunov analysis of accelerated methods in optimization. J. Mach. Learn. Res. 22(113), 1\u201334 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"1790_CR3","unstructured":"Suh, J.J., Roh, G., Ryu, E.K.: Continuous-time analysis of accelerated gradient methods via conservation laws in dilated coordinate systems. In: Proceedings of the 39th International Conference on Machine Learning (2022)"},{"key":"1790_CR4","unstructured":"Krichene, W., Bayen, A., Bartlett, P.L.: Accelerated mirror descent in continuous and discrete time. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"issue":"1, Ser. A","key":"1790_CR5","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s10107-020-01591-1","volume":"193","author":"H Attouch","year":"2022","unstructured":"Attouch, H., Chbani, Z., Fadili, J., Riahi, H.: First-order optimization algorithms via inertial systems with Hessian driven damping. Math. Program. 193(1, Ser. A), 113\u2013155 (2022)","journal-title":"Math. Program."},{"key":"1790_CR6","unstructured":"Kim, J., Yang, I.: Unifying Nesterov\u2019s accelerated gradient methods for convex and strongly convex objective functions. In: Proceedings of the 40th International Conference on Machine Learning (2023)"},{"key":"1790_CR7","unstructured":"Ushiyama, K., Sato, S., Matsuo, T.: A unified discretization framework for differential equation approach with Lyapunov arguments for convex optimization. In: Advances in Neural Information Processing Systems (2023)"},{"issue":"3","key":"1790_CR8","first-page":"543","volume":"269","author":"YE Nesterov","year":"1983","unstructured":"Nesterov, Y.E.: A method for solving the convex programming problem with convergence rate $$O(1\/k^{2})$$. Dokl. Akad. Nauk SSSR. 269(3), 543\u2013547 (1983)","journal-title":"Dokl. Akad. Nauk SSSR."},{"key":"1790_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91578-4","volume-title":"Lectures on convex optimization","author":"Y Nesterov","year":"2018","unstructured":"Nesterov, Y.: Lectures on convex optimization. Springer, Cham (2018)"},{"issue":"5","key":"1790_CR10","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/BF02440162","volume":"6","author":"O Gonzalez","year":"1996","unstructured":"Gonzalez, O.: Time integration and discrete Hamiltonian systems. J. Nonlinear Sci. 6(5), 449\u2013467 (1996)","journal-title":"J. Nonlinear Sci."},{"issue":"1","key":"1790_CR11","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/0021-9991(88)90132-5","volume":"76","author":"T Itoh","year":"1988","unstructured":"Itoh, T., Abe, K.: Hamiltonian-conserving discrete canonical equations based on variational difference quotients. J. Comput. Phys. 76(1), 85\u2013102 (1988)","journal-title":"J. Comput. Phys."},{"issue":"4","key":"1790_CR12","doi-asserted-by":"publisher","first-page":"045206","DOI":"10.1088\/1751-8113\/41\/4\/045206","volume":"41","author":"GRW Quispel","year":"2008","unstructured":"Quispel, G.R.W., McLaren, D.I.: A new class of energy-preserving numerical integration methods. J. Phys. A. 41(4), 045206\u20137 (2008)","journal-title":"J. Phys. A."},{"issue":"3","key":"1790_CR13","doi-asserted-by":"publisher","first-page":"1558","DOI":"10.1137\/22M1498486","volume":"33","author":"C Moucer","year":"2023","unstructured":"Moucer, C., Taylor, A., Bach, F.: A systematic approach to Lyapunov analyses of continuous-time models in convex optimization. SIAM J. Optim. 33(3), 1558\u20131586 (2023)","journal-title":"SIAM J. Optim."},{"key":"1790_CR14","volume-title":"Geometric numerical integration","author":"E Hairer","year":"2006","unstructured":"Hairer, E., Lubich, C., Wanner, G.: Geometric numerical integration, 2nd edn. Springer, Berlin (2006)","edition":"2"},{"issue":"1","key":"1790_CR15","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/LCSYS.2017.2722406","volume":"2","author":"B Van Scoy","year":"2018","unstructured":"Van Scoy, B., 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":"1790_CR16","unstructured":"Hairer, E., N\u00f8rsett, S.P., Wanner, G.: Solving ordinary differential equations. I, 2nd edn. Springer, Berlin (1993). Nonstiff problems"}],"container-title":["Numerical Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11075-024-01790-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11075-024-01790-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11075-024-01790-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T08:24:35Z","timestamp":1717662275000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11075-024-01790-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,14]]},"references-count":16,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["1790"],"URL":"https:\/\/doi.org\/10.1007\/s11075-024-01790-3","relation":{},"ISSN":["1017-1398","1572-9265"],"issn-type":[{"value":"1017-1398","type":"print"},{"value":"1572-9265","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,14]]},"assertion":[{"value":"31 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}