{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T09:51:00Z","timestamp":1775037060257,"version":"3.50.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T00:00:00Z","timestamp":1761350400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T00:00:00Z","timestamp":1761350400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-2204519"],"award-info":[{"award-number":["DMS-2204519"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Optim Theory Appl"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s10957-025-02864-5","type":"journal-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T15:21:30Z","timestamp":1761405690000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Convergence of First-Order Algorithms with Momentum from the Perspective of an Inexact Gradient Descent Method"],"prefix":"10.1007","volume":"208","author":[{"given":"Pham Duy","family":"Khanh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boris S.","family":"Mordukhovich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dat Ba","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,25]]},"reference":[{"key":"2864_CR1","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1137\/040605266","volume":"16","author":"P-A Absil","year":"2005","unstructured":"Absil, P.-A., Mahony, R., Andrews, B.: Convergence of the iterates of descent methods for analytic cost functions. SIAM J. Optim. 16, 531\u2013547 (2005)","journal-title":"SIAM J. Optim."},{"key":"2864_CR2","unstructured":"Andriuschenko, M., Flammarion, N.: Towards understanding sharpness-aware minimization. ICML, pages 639\u2013668, (2022)"},{"key":"2864_CR3","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1287\/moor.1100.0449","volume":"35","author":"H Attouch","year":"2010","unstructured":"Attouch, H., Bolt\u00e9, J., Redont, P., Soubeyran, A.: Proximal alternating minimization and projection methods for nonconvex problems. an approach based on the Kurdyka-\u0141ojasiewicz property. Math. Oper. Res. 35, 438\u2013457 (2010)","journal-title":"Math. Oper. Res."},{"key":"2864_CR4","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/s10107-011-0484-9","volume":"137","author":"H Attouch","year":"2013","unstructured":"Attouch, H., Bolt\u00e9, J., Svaiter, B.F.: Convergence of descent methods for definable and tame problems: Proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods. Math. Program. 137, 91\u2013129 (2013)","journal-title":"Math. Program."},{"key":"2864_CR5","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1137\/080716542","volume":"2","author":"A Beck","year":"2009","unstructured":"Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2, 183\u2013202 (2009)","journal-title":"SIAM J. Imaging Sci."},{"key":"2864_CR6","doi-asserted-by":"crossref","unstructured":"Bento, G., Mordukhovich, B.\u00a0S., Mota, T., Nesterov, Y.: Convergence of descent optimization algorithms under Polyak-\u0141ojasiewicz-Kurdyka conditions. https:\/\/optimization-online.org\/?p=29340, (2025)","DOI":"10.1007\/s10957-025-02816-z"},{"key":"2864_CR7","first-page":"536","volume":"25","author":"A Cauchy","year":"1847","unstructured":"Cauchy, A.: Method g\u00e9n\u00e9ral pour la r\u00e9solution des systemes d\u2019\u00e9quations simulan\u00e9es. Comptes Rendus 25, 536 (1847)","journal-title":"Comptes Rendus"},{"key":"2864_CR8","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/s10208-021-09516-w","volume":"22","author":"D Davis","year":"2022","unstructured":"Davis, D., Drusviatskiy, D.: Proximal methods avoid active strict saddles of weakly convex functions. Found. Comput. Math. 22, 561\u2013606 (2022)","journal-title":"Found. Comput. Math."},{"key":"2864_CR9","unstructured":"Foret, P., Kleiner, A., Mobahi, H., Neyshabur, B.: Sharpness-aware minimization for efficiently improving generalization. ICLR, (2021)"},{"key":"2864_CR10","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1137\/0805015","volume":"5","author":"P Gilmore","year":"1995","unstructured":"Gilmore, P., Kelley, C.T.: An implicit filtering algorithm for optimization of functions with many local minima. SIAM J. Optim. 5, 269\u2013285 (1995)","journal-title":"SIAM J. Optim."},{"key":"2864_CR11","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1137\/0802032","volume":"2","author":"O Guller","year":"1992","unstructured":"Guller, O.: New proximal point algorithms for convex minimization. SIAM J. Optim. 2, 649\u2013664 (1992)","journal-title":"SIAM J. Optim."},{"key":"2864_CR12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-56468-0","volume-title":"Fundamentals of Convex Analysis","author":"J-B Hiriart-Urruty","year":"2001","unstructured":"Hiriart-Urruty, J.-B., Lemar\u00e9chal, C.: Fundamentals of Convex Analysis. Grundlehren Text Editions. Springer, Berlin (2001)"},{"key":"2864_CR13","doi-asserted-by":"publisher","first-page":"1894","DOI":"10.1137\/080722059","volume":"19","author":"AD Ioffe","year":"2009","unstructured":"Ioffe, A.D.: An invitation to tame optimization. SIAM J. Optim. 19, 1894\u20131917 (2009)","journal-title":"SIAM J. Optim."},{"key":"2864_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-04247-3","volume-title":"Newton-Type Methods for Optimization and Variational Problems","author":"AF Izmailov","year":"2014","unstructured":"Izmailov, A.F., Solodov, M.V.: Newton-Type Methods for Optimization and Variational Problems. Springer, New York (2014)"},{"issue":"355","key":"2864_CR15","first-page":"383","volume":"202","author":"C Josz","year":"2023","unstructured":"Josz, C.: Global convergence of the gradient method for functions definable in o-minimal structures. Math. Program. 202(355), 383 (2023)","journal-title":"Math. Program."},{"key":"2864_CR16","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1007\/978-3-319-46128-1_50","volume":"1","author":"H Karimi","year":"2016","unstructured":"Karimi, H., Nutini, J., Schmidt, M.: Linear convergence of gradient and proximal-gradient methods under the polyak-\u0142ojasiewicz condition. Machine Learning and Knowledge Discovery in Databases, Part 1, 795\u2013811 (2016)","journal-title":"Machine Learning and Knowledge Discovery in Databases, Part"},{"key":"2864_CR17","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1137\/23M1627237","volume":"35","author":"PD Khanh","year":"2025","unstructured":"Khanh, P.D., Khoa, V.V.H., Mordukhovich, B.S., Phat, V.T.: Second-order subdifferential optimality conditions in nonsmooth optimization. SIAM J. Optim. 35, 678\u2013711 (2025)","journal-title":"SIAM J. Optim."},{"key":"2864_CR18","doi-asserted-by":"crossref","unstructured":"Khanh, P.\u00a0D., Luong, H.-C., Mordukhovich, B.\u00a0S., Tran, D.\u00a0B.: Fundamental convergence analysis of sharpness-aware minimization. Proceedings of NeurIPS 2024, (2024)","DOI":"10.52202\/079017-0419"},{"key":"2864_CR19","doi-asserted-by":"publisher","first-page":"1211","DOI":"10.1137\/22M1519250","volume":"33","author":"PD Khanh","year":"2023","unstructured":"Khanh, P.D., Mordukhovich, B.S., Phat, V.T.: Variational convexity of functions and variational sufficiency in optimization. SIAM J. Optim. 33, 1211\u20131158 (2023)","journal-title":"SIAM J. Optim."},{"key":"2864_CR20","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s10898-024-01460-7","volume":"91","author":"PD Khanh","year":"2025","unstructured":"Khanh, P.D., Mordukhovich, B.S., Phat, V.T., Tran, D.B.: Inexact proximal methods for weakly convex functions. J. Global Optim. 91, 611\u2013646 (2025)","journal-title":"J. Global Optim."},{"key":"2864_CR21","doi-asserted-by":"publisher","first-page":"2138","DOI":"10.1007\/s10957-023-02319-9","volume":"203","author":"PD Khanh","year":"2024","unstructured":"Khanh, P.D., Mordukhovich, B.S., Tran, D.B.: Inexact reduced gradient methods in smooth nonconvex optimization. J. Optim. Theory Appl. 203, 2138\u20132178 (2024)","journal-title":"J. Optim. Theory Appl."},{"key":"2864_CR22","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2024.2322700","author":"PD Khanh","year":"2024","unstructured":"Khanh, P.D., Mordukhovich, B.S., Tran, D.B.: Anewinexact gradient descentmethodwith applications to nonsmooth convex optimization. Optim. Methods Softw. (2024). https:\/\/doi.org\/10.1080\/10556788.2024.2322700","journal-title":"Optim. Methods Softw."},{"key":"2864_CR23","doi-asserted-by":"publisher","unstructured":"Khanh, P.\u00a0D., Mordukhovich, B.\u00a0S., Tran, D.\u00a0B.: Globally convergent derivative-free methods in nonconvex optimization with and without noise. Math. Program. https:\/\/doi.org\/10.1007\/s10107-025-02255-8, pages 1\u201361, (2025)","DOI":"10.1007\/s10107-025-02255-8"},{"key":"2864_CR24","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/s10107-021-01643-0","volume":"190","author":"D Kim","year":"2021","unstructured":"Kim, D.: Accelerated proximal point method for maximally monotone operators. Math. Program. 190, 57\u201387 (2021)","journal-title":"Math. Program."},{"key":"2864_CR25","first-page":"747","volume":"12","author":"GM Korpelevich","year":"1976","unstructured":"Korpelevich, G.M.: An extragradient method for finding saddle points and for other problems. Ekon. Mat. Metod. 12, 747\u2013756 (1976)","journal-title":"Ekon. Mat. Metod."},{"key":"2864_CR26","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1137\/S1052623496303470","volume":"9","author":"JC Lagarias","year":"1998","unstructured":"Lagarias, J.C., Reeds, J.A., Wright, M.H., Wright, P.E.: Convergence properties of the Nelder-Mead simplex method in low dimensions. SIAM J. Optim. 9, 112\u2013147 (1998)","journal-title":"SIAM J. Optim."},{"key":"2864_CR27","doi-asserted-by":"crossref","unstructured":"L\u00e1szl\u00f3, S.C.: Convergence rates for an inertial algorithm of gradient type associated to a smooth non-convex minimization. Math. Program. 190, 285\u2013329 (2021)","DOI":"10.1007\/s10107-020-01534-w"},{"key":"2864_CR28","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1007\/s10208-017-9366-8","volume":"18","author":"G Li","year":"2018","unstructured":"Li, G., Pong, T.K.: Calculus of the exponent of Kurdyka-\u0141ojasiewicz inequality and its applications to linear convergence of first-order methods. Found. Comput. Math. 18, 1199\u20131232 (2018)","journal-title":"Found. Comput. Math."},{"key":"2864_CR29","unstructured":"Lin, T., Kong, L., Stich, S.\u00a0U., Jaggi, M.: Extrapolation for large-batch training in deep learning. ICML, (2020)"},{"key":"2864_CR30","volume-title":"Variational Analysis and Generalized Differentiation, I: Basic Theory, II: Applications","author":"BS Mordukhovich","year":"2006","unstructured":"Mordukhovich, B.S.: Variational Analysis and Generalized Differentiation, I: Basic Theory, II: Applications. Springer, Berlin (2006)"},{"key":"2864_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-92775-6","volume-title":"Variational Analysis and Applications","author":"BS Mordukhovich","year":"2018","unstructured":"Mordukhovich, B.S.: Variational Analysis and Applications. Springer, Cham, Switzerland (2018)"},{"key":"2864_CR32","volume-title":"A method of solving a convex programming problem with convergence rate $${\\cal{O} }(1\/k^2)$$","author":"Yu Nesterov","year":"1983","unstructured":"Nesterov, Yu.: A method of solving a convex programming problem with convergence rate $${\\cal{O} }(1\/k^2)$$. Soviet Math, Dokl (1983)"},{"key":"2864_CR33","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/s10107-012-0629-5","volume":"140","author":"Yu Nesterov","year":"2013","unstructured":"Nesterov, Yu.: Gradient methods for minimizing composite functions. Math. Program. 140, 125\u2013161 (2013)","journal-title":"Math. Program."},{"key":"2864_CR34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91578-4","volume-title":"Lectures on Convex Optimization","author":"Yu Nesterov","year":"2018","unstructured":"Nesterov, Yu.: Lectures on Convex Optimization. Springer, Cham, Switzerland (2018)"},{"key":"2864_CR35","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/s10208-015-9296-2","volume":"17","author":"Yu Nesterov","year":"2017","unstructured":"Nesterov, Yu., Spokoiny, V.: Random gradient-free minimization of convex functions. Found. Comput. Math. 17, 527\u2013566 (2017)","journal-title":"Found. Comput. Math."},{"key":"2864_CR36","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s10957-017-1200-6","volume":"176","author":"TP Nguyen","year":"2018","unstructured":"Nguyen, T.P., Pauwels, E., Richard, E., Sutter, B.W.: Extragradient method in optimization: convergence and complexity. J. Optim. Theory Appl. 176, 137\u2013162 (2018)","journal-title":"J. Optim. Theory Appl."},{"key":"2864_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0041-5553(64)90137-5","volume":"4","author":"BT Polyak","year":"1964","unstructured":"Polyak, B.T.: Some methods of speeding up the convergence of iteration methods. USSR Comput. Math. Math. Phys. 4, 1\u201317 (1964)","journal-title":"USSR Comput. Math. Math. Phys."},{"key":"2864_CR38","volume-title":"Introduction to Optimization","author":"BT Polyak","year":"1987","unstructured":"Polyak, B.T.: Introduction to Optimization. Optimization Software, New York (1987)"},{"key":"2864_CR39","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1007\/s10898-012-9951-y","volume":"56","author":"LM Rios","year":"2013","unstructured":"Rios, L.M., Sahinidis, N.V.: Derivative-free optimization: a review of algorithms and comparison of software implementations. J. Global Optim. 56, 1247\u20131293 (2013)","journal-title":"J. Global Optim."},{"key":"2864_CR40","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1287\/moor.1.2.97","volume":"1","author":"RT Rockafellar","year":"1976","unstructured":"Rockafellar, R.T.: Augmented Lagrangians and applications of the proximal point algorithm in convex programming. Math. Oper. Res. 1, 97\u2013116 (1976)","journal-title":"Math. Oper. Res."},{"key":"2864_CR41","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1137\/0314056","volume":"14","author":"RT Rockafellar","year":"1976","unstructured":"Rockafellar, R.T.: Monotone operators and the proximal point algorithm. SIAM J. Control. Optim. 14, 877\u2013898 (1976)","journal-title":"SIAM J. Control. Optim."},{"key":"2864_CR42","first-page":"2347","volume":"22","author":"RT Rockafellar","year":"2021","unstructured":"Rockafellar, R.T.: Advances in convergence and scope of the proximal point algorithm. J. Nonlinear Convex Anal. 22, 2347\u20132375 (2021)","journal-title":"J. Nonlinear Convex Anal."},{"key":"2864_CR43","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1007\/s10107-022-01832-5","volume":"199","author":"RT Rockafellar","year":"2023","unstructured":"Rockafellar, R.T.: Convergence of augmented Lagrangian methods in extensions beyond nonlinear programming. Math. Program. 199, 375\u2013420 (2023)","journal-title":"Math. Program."},{"key":"2864_CR44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02431-3","volume-title":"Variational Analysis","author":"RT Rockafellar","year":"1998","unstructured":"Rockafellar, R.T., Wets, R.J.-B.: Variational Analysis. Springer, Berlin (1998)"},{"key":"2864_CR45","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1007\/s10107-021-01681-8","volume":"195","author":"B Shi","year":"2022","unstructured":"Shi, B., Du, S.S., Jordan, M.I., Su, W.J.: Understanding the acceleration phenomenon via high-resolution differential equations. Math. Program. 195, 79\u2013148 (2022)","journal-title":"Math. Program."},{"key":"2864_CR46","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1080\/10556788.2022.2121832","volume":"38","author":"HM Shi","year":"2023","unstructured":"Shi, H.M., Xuan, M.Q., Oztoprak, F., Nocedal, J.: On the numerical performance of finite-difference-based methods for derivative-free optimization. Optim. Methods Softw. 38, 289\u2013311 (2023)","journal-title":"Optim. Methods Softw."},{"key":"2864_CR47","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/s10589-017-9912-y","volume":"67","author":"A Themelis","year":"2017","unstructured":"Themelis, A., Stella, L., Patrinos, P.: Forward-backward quasi-Newton methods for nonsmooth optimization problems. Comput. Optim. Appl. 67, 443\u2013487 (2017)","journal-title":"Comput. Optim. Appl."},{"key":"2864_CR48","doi-asserted-by":"crossref","unstructured":"Wang, X.: On chebyshev functions and klee functions. Journal of Mathematical Analysis and Applications, pages 293\u2013310, (2010)","DOI":"10.1016\/j.jmaa.2010.03.041"},{"key":"2864_CR49","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, Z.: Calculus rules of the generalized concave Kurdyka\u2013\u0141ojasiewicz property. J. Optim. Theory Appl., (2023)","DOI":"10.1007\/s10957-023-02219-y"},{"key":"2864_CR50","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1137\/16M1055323","volume":"27","author":"B Wen","year":"2017","unstructured":"Wen, B., Chen, X., Pong, T.K.: Linear convergence of proximal gradient algorithm with extrapolation for a class of nonconvex nonsmooth minimization problems. SIAM J. Optim. 27, 124\u2013145 (2017)","journal-title":"SIAM J. Optim."},{"key":"2864_CR51","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/BF01128757","volume":"4","author":"S Zavriev","year":"1993","unstructured":"Zavriev, S., Kostyuk, F.: Heavy ball method in nonconvex optimization problems. Comput. Math. Model. 4, 336\u2013341 (1993)","journal-title":"Comput. Math. Model."}],"container-title":["Journal of Optimization Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-025-02864-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10957-025-02864-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-025-02864-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T07:22:21Z","timestamp":1775028141000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10957-025-02864-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,25]]},"references-count":51,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["2864"],"URL":"https:\/\/doi.org\/10.1007\/s10957-025-02864-5","relation":{},"ISSN":["0022-3239","1573-2878"],"issn-type":[{"value":"0022-3239","type":"print"},{"value":"1573-2878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,25]]},"assertion":[{"value":"17 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"40"}}