{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T10:54:09Z","timestamp":1775040849671,"version":"3.50.1"},"reference-count":103,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"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":["J Optim Theory Appl"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s10957-025-02804-3","type":"journal-article","created":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T07:00:02Z","timestamp":1759474802000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Accelerated Adaptive Cubic Regularized Quasi-Newton Methods"],"prefix":"10.1007","volume":"208","author":[{"given":"Dmitry","family":"Kamzolov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Klea","family":"Ziu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Artem","family":"Agafonov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Tak\u00e1\u010d","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,3]]},"reference":[{"key":"2804_CR1","doi-asserted-by":"crossref","unstructured":"Agafonov, A., Dvurechensky, P., Scutari, G., Gasnikov, A., Kamzolov, D., Lukashevich, A., Daneshmand, A.: An accelerated second-order method for distributed stochastic optimization. In 2021 60th IEEE Conference on Decision and Control (CDC), pages 2407\u20132413, 2021","DOI":"10.1109\/CDC45484.2021.9683400"},{"key":"2804_CR2","unstructured":"Agafonov, A., Erraji, B., Tak\u00e1\u010d, M.: FLECS-CGD: A federated learning second-order framework via compression and sketching with compressed gradient differences. arXiv preprintarXiv:2210.09626, (2022)"},{"issue":"1","key":"2804_CR3","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1080\/10556788.2023.2261604","volume":"39","author":"A Agafonov","year":"2024","unstructured":"Agafonov, A., Kamzolov, D., Dvurechensky, P., Gasnikov, A., Tak\u00e1\u010d, M.: Inexact tensor methods and their application to stochastic convex optimization. Optimization Methods and Software 39(1), 42\u201383 (2024)","journal-title":"Optimization Methods and Software"},{"key":"2804_CR4","unstructured":"Agafonov, A., Kamzolov, D., Tappenden, R., Gasnikov, A., Tak\u00e1\u010d, M.: FLECS: A federated learning second-order framework via compression and sketching. arXiv preprint arXiv:2206.02009 , (2022)"},{"issue":"1","key":"2804_CR5","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1137\/0805002","volume":"5","author":"F Alizadeh","year":"1995","unstructured":"Alizadeh, F.: Interior point methods in semidefinite programming with applications to combinatorial optimization. SIAM J. Optim. 5(1), 13\u201351 (1995)","journal-title":"SIAM J. Optim."},{"key":"2804_CR6","doi-asserted-by":"crossref","unstructured":"Antonakopoulos, K., Kavis, A., Cevher, V.: Extra-newton: A first approach to noise-adaptive accelerated second-order methods. In S\u00a0Koyejo, S\u00a0Mohamed, A\u00a0Agarwal, D\u00a0Belgrave, K\u00a0Cho, and A\u00a0Oh, editors, Advances in Neural Information Processing Systems, volume\u00a035, pages 29859\u201329872. Curran Associates, Inc., (2022)","DOI":"10.52202\/068431-2165"},{"key":"2804_CR7","doi-asserted-by":"publisher","first-page":"2881","DOI":"10.1137\/18M1226282","volume":"29","author":"S Bellavia","year":"2019","unstructured":"Bellavia, S., Gurioli, G., Morini, B., Toint, P.L.: Adaptive regularization algorithms with inexact evaluations for nonconvex optimization. SIAM J. Optim. 29, 2881\u20132915 (2019)","journal-title":"SIAM J. Optim."},{"issue":"10","key":"2804_CR8","doi-asserted-by":"publisher","first-page":"592","DOI":"10.1073\/pnas.2.10.592","volume":"2","author":"AA Bennett","year":"1916","unstructured":"Bennett, A.A.: Newton\u2019s method in general analysis. Proc. Natl. Acad. Sci. 2(10), 592\u2013598 (1916)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"2804_CR9","doi-asserted-by":"crossref","unstructured":"Berahas, A.S., Jahani, M., Richt\u00e1rik, P., Tak\u00e1\u010d, M.: Quasi-newton methods for machine learning: forget the past, just sample. Optimization Methods and Software, pages 1\u201337, (2021)","DOI":"10.1080\/10556788.2021.1977806"},{"key":"2804_CR10","unstructured":"Berahas, A.S., Nocedal, J., Tak\u00e1c, M.: A multi-batch l-bfgs method for machine learning. Advances in Neural Information Processing Systems, 29, (2016)"},{"issue":"3","key":"2804_CR11","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ab460a","volume":"36","author":"C Bertocchi","year":"2020","unstructured":"Bertocchi, C., Chouzenoux, E., Corbineau, M.-C., Pesquet, J.-C., Prato, M.: Deep unfolding of a proximal interior point method for image restoration. Inverse Prob. 36(3), 034005 (2020)","journal-title":"Inverse Prob."},{"key":"2804_CR12","first-page":"1737","volume":"10","author":"A Bordes","year":"2009","unstructured":"Bordes, A., Bottou, L., Gallinari, P.: SGD-QN: careful quasi-Newton stochastic gradient descent. J. Mach. Learn. Res. 10, 1737\u20131754 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"2804_CR13","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1090\/S0025-5718-1967-0224273-2","volume":"21","author":"CG Broyden","year":"1967","unstructured":"Broyden, C.G.: Quasi-Newton methods and their application to function minimisation. Math. Comput. 21, 368\u2013381 (1967)","journal-title":"Math. Comput."},{"key":"2804_CR14","doi-asserted-by":"crossref","unstructured":"Byrd, R.H., Khalfan, H.F., Schnabel, R.B.: Analysis of a symmetric rank-one trust region method SIAM J. Optim. 6, 1025\u20131039 (1996)","DOI":"10.1137\/S1052623493252985"},{"issue":"2","key":"2804_CR15","doi-asserted-by":"publisher","first-page":"1008","DOI":"10.1137\/140954362","volume":"26","author":"RH Byrd","year":"2016","unstructured":"Byrd, R.H., Nocedal, J., Singer, Y.: A stochastic quasi-Newton method for large-scale optimization. SIAM J. Optim. 26(2), 1008\u20131031 (2016)","journal-title":"SIAM J. Optim."},{"key":"2804_CR16","doi-asserted-by":"crossref","unstructured":"Carmon, Y., Hausler, D., Jambulapati, A., Jin, Y., Sidford, A.: Optimal and adaptive monteiro-svaiter acceleration. In S\u00a0Koyejo, S\u00a0Mohamed, A\u00a0Agarwal, D\u00a0Belgrave, K\u00a0Cho, and A\u00a0Oh, editors, Advances in Neural Information Processing Systems, volume\u00a035, pages 20338\u201320350. Curran Associates, Inc., (2022)","DOI":"10.52202\/068431-1479"},{"issue":"2","key":"2804_CR17","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s10107-009-0286-5","volume":"127","author":"C Cartis","year":"2011","unstructured":"Cartis, C., Gould, N.I.M., Toint, P.L.: Adaptive cubic regularisation methods for unconstrained optimization. part i: motivation, convergence and numerical results. Math. Program. 127(2), 245\u2013295 (2011)","journal-title":"Math. Program."},{"issue":"2","key":"2804_CR18","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/s10107-009-0337-y","volume":"130","author":"C Cartis","year":"2011","unstructured":"Cartis, C., Gould, N.I.M., Toint, P.L.: Adaptive cubic regularisation methods for unconstrained optimization. part ii: worst-case function-and derivative-evaluation complexity. Math. Program. 130(2), 295\u2013319 (2011)","journal-title":"Math. Program."},{"issue":"3","key":"2804_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"C-C Chang","year":"2011","unstructured":"Chang, C.-C., Lin, C.-J.: Libsvm: A library for support vector machines. ACM transactions on intelligent systems and technology (TIST) 2(3), 1\u201327 (2011)","journal-title":"ACM transactions on intelligent systems and technology (TIST)"},{"key":"2804_CR20","doi-asserted-by":"crossref","unstructured":"Conn, A.R., Gould, N.I.M., Toint, P.L.: Trust Region Methods. Society for Industrial and Applied Mathematics (2000)","DOI":"10.1137\/1.9780898719857"},{"key":"2804_CR21","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/BF01594934","volume":"50","author":"AR Conn","year":"1991","unstructured":"Conn, A.R., Gould, N.I.M., Toint, P.L.: Convergence of Quasi-Newton matrices generated by the symmetric rank one update. Math. Program. 50, 177\u2013195 (1991)","journal-title":"Math. Program."},{"key":"2804_CR22","unstructured":"Daneshmand, A., Scutari, G., Dvurechensky, P. Gasnikov, A.: Newton method over networks is fast up to the statistical precision. In International Conference on Machine Learning, pages 2398\u20132409. PMLR, (2021)"},{"key":"2804_CR23","doi-asserted-by":"crossref","unstructured":"Dennis, J.E., Jr and Jorge J Mor\u00e9.: Quasi-newton methods, motivation and theory. SIAM Rev. 19(1), 46\u201389 (1977)","DOI":"10.1137\/1019005"},{"key":"2804_CR24","unstructured":"Doikov, N., Chayti, EI.M., Jaggi, M.: Second-order optimization with lazy Hessians. In Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett, editors, Proceedings of the 40th International Conference on Machine Learning, volume 202, pages 8138\u20138161. PMLR, 9 2023"},{"key":"2804_CR25","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1137\/22M1519444","volume":"34","author":"N Doikov","year":"2024","unstructured":"Doikov, N., Mishchenko, K., Nesterov, Y.: Super-universal regularized newton method. SIAM J. Optim. 34, 27\u201356 (2024)","journal-title":"SIAM J. Optim."},{"key":"2804_CR26","unstructured":"Doikov, N., Nesterov, Y.: Inexact tensor methods with dynamic accuracies. In Hal\u00a0Daum\u00e9 III and Aarti Singh, editors, Proceedings of the 37th International Conference on Machine Learning, volume 119, pages 2577\u20132586. PMLR, 5 2020"},{"key":"2804_CR27","doi-asserted-by":"crossref","unstructured":"Doikov, N., Nesterov, N.: Affine-invariant contracting-point methods for convex optimization. Mathematical Programming, pages 1\u201323, 2022","DOI":"10.1007\/s10107-021-01761-9"},{"key":"2804_CR28","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s10107-020-01606-x","volume":"193","author":"N Doikov","year":"2022","unstructured":"Doikov, N., Nesterov, Y.: Local convergence of tensor methods. Math. Program. 193, 315\u2013336 (2022)","journal-title":"Math. Program."},{"key":"2804_CR29","doi-asserted-by":"crossref","unstructured":"Doikov, N., Nesterov Y.: Gradient regularization of Newton method with Bregman distances. Mathematical Programming, 2023","DOI":"10.1007\/s10107-023-01943-7"},{"key":"2804_CR30","unstructured":"Doikov, N., Richt\u00e1rik, P.: Randomized block cubic Newton method. In Jennifer Dy and Andreas Krause, editors, The 35th International Conference on Machine Learning (ICML), volume\u00a080 of Proceedings of Machine Learning Research, pages 1290\u20131298, Stockholmsm\u00e4ssan, Stockholm Sweden, 10\u201315 Jul 2018. PMLR"},{"key":"2804_CR31","doi-asserted-by":"crossref","unstructured":"Dvurechensky, P., Kamzolov, D., Lukashevich, A., Lee, S., Ordentlich, E., Uribe, C\u2019e A., Gasnikov, A.: Hyperfast second-order local solvers for efficient statistically preconditioned distributed optimization. EURO Journal on Computational Optimization, 10:100045, 2022","DOI":"10.1016\/j.ejco.2022.100045"},{"key":"2804_CR32","volume-title":"Global performance guarantees of second-order methods for unconstrained convex minimization","author":"P Dvurechensky","year":"2018","unstructured":"Dvurechensky, P., Nesterov, Y.: Global performance guarantees of second-order methods for unconstrained convex minimization. Technical report, CORE (2018)"},{"key":"2804_CR33","doi-asserted-by":"crossref","unstructured":"Fletcher, R.: A new approach to variable metric algorithms. The Computer Journal, 13:317\u2013322, 1 1970","DOI":"10.1093\/comjnl\/13.3.317"},{"key":"2804_CR34","unstructured":"Fletcher, R.: Practical methods of optimization. John Wiley & Sons, 2013"},{"key":"2804_CR35","unstructured":"Gasnikov, A., Dvurechensky, P., Gorbunov, E., Vorontsova, E., Selikhanovych, D., Uribe, C\u2019A., Jiang, B., Wang, H., Zhang, S., Bubeck, S., Jiang, Q., Lee, T, Y., LI, Y., Sidford Near optimal methods for minimizing convex functions with Lipschitz p-th derivatives. In Alina Beygelzimer and Daniel Hsu, editors, Proceedings of the Thirty-Second Conference on Learning Theory, volume\u00a099, pages 1392\u20131393. PMLR, 5 2019"},{"key":"2804_CR36","unstructured":"Ghadimi, S., Liu, H., Zhang, T.: Second-order methods with cubic regularization under inexact information. arXiv preprint arXiv:1710.05782 (2017)"},{"key":"2804_CR37","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/s10589-017-9964-z","volume":"69","author":"H Ghanbari","year":"2018","unstructured":"Ghanbari, H., Scheinberg, K.: Proximal Quasi-Newton methods for regularized convex optimization with linear and accelerated sublinear convergence rates. Comput. Optim. Appl. 69, 597\u2013627 (2018)","journal-title":"Comput. Optim. Appl."},{"key":"2804_CR38","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1090\/S0025-5718-1970-0258249-6","volume":"24","author":"D Goldfarb","year":"1970","unstructured":"Goldfarb, D.: A family of variable-metric methods derived by variational means. Math. Comput. 24, 23\u201326 (1970)","journal-title":"Math. Comput."},{"key":"2804_CR39","unstructured":"Gower, R., Hanzely, F., Richt\u00e1rik, P., Stich, S.U.: Accelerated stochastic matrix inversion: General theory and speeding up BFGS rules for faster second-order optimization. In S\u00a0Bengio, H\u00a0Wallach, H\u00a0Larochelle, K\u00a0Grauman, N\u00a0Cesa-Bianchi, and R\u00a0Garnett, editors, Advances in Neural Information Processing Systems, volume\u00a031. Curran Associates, Inc., (2018)"},{"key":"2804_CR40","doi-asserted-by":"crossref","unstructured":"Gower, R., Richt\u00e1rik, P.: Randomized Quasi-Newton updates are linearly convergent matrix inversion algorithms. SIAM Journal on Matrix Analysis and Applications, 38:1380\u20131409, 2017","DOI":"10.1137\/16M1062053"},{"key":"2804_CR41","unstructured":"Gower, R., Kovalev, D., Lieder, F., Richt\u00e1rik, P.: RSN: Randomized Subspace Newton. In H.\u00a0Wallach, H.\u00a0Larochelle, A.\u00a0Beygelzimer, F.\u00a0d\u2019Alch\u00e9 Buc, E.\u00a0Fox, and R.\u00a0Garnett, editors, Advances in Neural Information Processing Systems 32, pages 616\u2013625. Curran Associates, Inc., 2019"},{"key":"2804_CR42","unstructured":"Gower, R., Goldfarb, D., Richt\u00e1rik, P.: Stochastic block BFGS: squeezing more curvature out of data. In 33rd International Conference on Machine Learning, pages 1869\u20131878, 2016"},{"key":"2804_CR43","doi-asserted-by":"crossref","unstructured":"Grapiglia N, G., Nesterov, Y.: On inexact solution of auxiliary problems in tensor methods for convex optimization. Optimization Methods and Software 36, 145\u2013170 (2021)","DOI":"10.1080\/10556788.2020.1731749"},{"key":"2804_CR44","unstructured":"Griewank, A.: The modification of Newton\u2019s method for unconstrained optimization by bounding cubic terms. Technical report, Technical report NA\/12, 1981"},{"key":"2804_CR45","unstructured":"Hanzely, F., Doikov, N., Richt\u00e1rik, P., Nesterov, Y.: Stochastic subspace cubic Newton method. In 37th International Conference on Machine Learning (ICML), 2020"},{"key":"2804_CR46","unstructured":"Hanzely, S., Kamzolov, D., Pasechnyuk, D., Gasnikov, A., Richt\u00e1rik, P., Tak\u00e1\u010d A.: damped Newton method achieves global $$\\cal{O}\\left(\\frac{1}{k^{2}}\\right) $$ and local quadratic convergence rate. In S.\u00a0Koyejo, S.\u00a0Mohamed, A.\u00a0Agarwal, D.\u00a0Belgrave, K.\u00a0Cho, and A.\u00a0Oh, editors, Advances in Neural Information Processing Systems, volume\u00a035, pages 25320\u201325334. Curran Associates, Inc., 2022"},{"key":"2804_CR47","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/s00186-021-00755-9","volume":"94","author":"R Hildebrand","year":"2021","unstructured":"Hildebrand, R.: Optimal step length for the newton method: case of self-concordant functions. Math. Methods Oper. Res. 94, 253\u2013279 (2021)","journal-title":"Math. Methods Oper. Res."},{"key":"2804_CR48","unstructured":"Rustem Islamov, Xun Qian, Slavom\u00edr Hanzely, Mher Safaryan, and Peter Richt\u00e1rik. Distributed newton-type methods with communication compression and bernoulli aggregation. Transactions on Machine Learning Research, 2023"},{"key":"2804_CR49","unstructured":"Rustem Islamov, Xun Qian, and Peter Richt\u00e1rik. Distributed second order methods with fast rates and compressed communication. In International Conference on Machine Learning (ICML), 2021"},{"key":"2804_CR50","doi-asserted-by":"crossref","unstructured":"Dmitry Kamzolov. Near-optimal hyperfast second-order method for convex optimization. In Yury Kochetov, Igor Bykadorov, and Tatiana Gruzdeva, editors, Mathematical Optimization Theory and Operations Research, pages 167\u2013178. Springer International Publishing, 2020","DOI":"10.1007\/978-3-030-58657-7_15"},{"key":"2804_CR51","doi-asserted-by":"crossref","unstructured":"Dmitry Kamzolov, Alexander Gasnikov, Pavel Dvurechensky, Artem Agafonov, and Martin Tak\u00e1\u010d. Exploiting Higher Order Derivatives in Convex Optimization Methods, pages 1\u201313. Springer International Publishing, 2023","DOI":"10.1007\/978-3-030-54621-2_858-1"},{"key":"2804_CR52","unstructured":"Leonid\u00a0Vitalyevich Kantorovich. Functional analysis and applied mathematics. Uspekhi Matematicheskikh Nauk, 3(6):89\u2013185, 1948. (In Russian). Translated as N.B.S Report 1509, Washington D.C. (1952)"},{"key":"2804_CR53","unstructured":"Leonid Vitalyevich Kantorovich: On Newton\u2019s method for functional equations. Dokl. Akad. Nauk SSSR 59(7), 1237\u20131240 (1948). (In Russian)"},{"key":"2804_CR54","unstructured":"Leonid Vitalyevich Kantorovich: On Newton\u2019s method. Trudy Matematicheskogo Instituta imeni VA Steklova 28, 104\u2013144 (1949). (In Russian)"},{"key":"2804_CR55","unstructured":"Leonid Vitalyevich Kantorovich: Principle of majorants and Newton\u2019s method. Dokl. Akad. Nauk SSSR 76(1), 17\u201320 (1951). (In Russian)"},{"key":"2804_CR56","unstructured":"Leonid Vitalyevich Kantorovich: Some further applications of principle of majorants. Dokl. Akad. Nauk SSSR 80(6), 849\u2013852 (1951). (In Russian)"},{"key":"2804_CR57","unstructured":"Leonid Vitalyevich Kantorovich: On approximate solution of functional equations. Uspekhi Matematicheskikh Nauk 11(6), 99\u2013116 (1956). (In Russian)"},{"key":"2804_CR58","unstructured":"Kantorovich, L,V.: Some further applications of Newton\u2019s method. Vestnik LGU, Seriya Matemetika Mekhanika, 0(7):68\u2013103, 1957. (In Russian)"},{"key":"2804_CR59","doi-asserted-by":"crossref","unstructured":"Khalfan, H, F., Byrd, R, H., Schnabel, R, B.: A theoretical and experimental study of the symmetric rank-one update. SIAM Journal on Optimization, 3:1\u201324, 1993","DOI":"10.1137\/0803001"},{"key":"2804_CR60","unstructured":"Koh, K., Kim, S., Boyd, S.: An interior-point method for large-scale l1-regularized logistic regression. Journal of Machine learning research, 8(Jul):1519\u20131555, 2007"},{"key":"2804_CR61","doi-asserted-by":"crossref","unstructured":"Kovalev, D., Mishchenko, K.: The first optimal acceleration of high-order methods in smooth convex optimization. In S\u00a0Koyejo, S\u00a0Mohamed, A\u00a0Agarwal, D\u00a0Belgrave, K\u00a0Cho, and A\u00a0Oh, editors, Advances in Neural Information Processing Systems, volume\u00a035, pages 35339\u201335351. Curran Associates, Inc., 2022","DOI":"10.52202\/068431-2561"},{"key":"2804_CR62","unstructured":"Kovalev, D., Gower, R.M., Richt\u00e1rik, P.: and Alexander Rogozin. Fast linear convergence of randomized BFGS. arXiv preprint arXiv:2002.11337, (2020)"},{"key":"2804_CR63","unstructured":"Kovalev, D., Mishchenko, K., Richt\u00e1rik, P.: Stochastic Newton and cubic Newton methods with simple local linear-quadratic rates. In NeurIPS Beyond First Order Methods Workshop, (2019)"},{"key":"2804_CR64","unstructured":"LeCun, Y.: The mnist database of handwritten digits. http:\/\/yann.lecun.com\/exdb\/mnist\/, (1998)"},{"key":"2804_CR65","unstructured":"Lin, D., Ye, H., Zhang, Z.: Greedy and random Quasi-Newton methods with faster explicit superlinear convergence. In Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P.S., Vaughan, J.W., editors, Advances in Neural Information Processing Systems, volume\u00a034, pages 6646\u20136657. Curran Associates, Inc., (2021)"},{"key":"2804_CR66","doi-asserted-by":"publisher","first-page":"2856","DOI":"10.1093\/imanum\/drac057","volume":"43","author":"A Lucchi","year":"2023","unstructured":"Lucchi, A., Kohler, J.: A sub-sampled tensor method for nonconvex optimization. IMA J. Numer. Anal. 43, 2856\u20132891 (2023). (10)","journal-title":"IMA J. Numer. Anal."},{"key":"2804_CR67","first-page":"735","volume":"27","author":"J Martens","year":"2010","unstructured":"Martens, J.: Deep learning via hessian-free optimization. In ICML 27, 735\u2013742 (2010)","journal-title":"In ICML"},{"key":"2804_CR68","unstructured":"Meng, S.Y., Vaswani, S., Laradji, I.H., Schmidt, M.: and Simon Lacoste-Julien. Fast and furious convergence: Stochastic second order methods under interpolation. In Silvia Chiappa and Roberto Calandra, editors, International Conference on Artificial Intelligence and Statistics, volume 108, pages 1375\u20131386. PMLR, 9 (2020)"},{"key":"2804_CR69","doi-asserted-by":"publisher","first-page":"1440","DOI":"10.1137\/22M1488752","volume":"33","author":"K Mishchenko","year":"2023","unstructured":"Mishchenko, K.: Regularized Newton method with global $$\\cal{O} \\left(\\frac{1}{k^{2}}\\right)$$ convergence. SIAM J. Optim. 33, 1440\u20131462 (2023)","journal-title":"SIAM J. Optim."},{"key":"2804_CR70","first-page":"3151","volume":"16","author":"A Mokhtari","year":"2015","unstructured":"Mokhtari, A., Ribeiro, A.: Global convergence of online limited memory BFGS. J. Mach. Learn. Res. 16, 3151\u20133181 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"2804_CR71","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1137\/110833786","volume":"23","author":"RDC Monteiro","year":"2013","unstructured":"Monteiro, R.D.C., Svaiter, B.F.: An accelerated hybrid proximal extragradient method for convex optimization and its implications to second-order methods. SIAM J. Optim. 23, 1092\u20131125 (2013)","journal-title":"SIAM J. Optim."},{"key":"2804_CR72","doi-asserted-by":"crossref","unstructured":"Mor\u00e9, J.J.: The levenberg\u2013marquardt algorithm: implementation and theory. In Conference on Numerical Analysis, University of Dundee, Scotland, 7 (1977)","DOI":"10.1007\/BFb0067700"},{"issue":"3","key":"2804_CR73","first-page":"543","volume":"269","author":"Y Nesterov","year":"1983","unstructured":"Nesterov, Y.: A method for solving the convex programming problem with convergence rate $$\\cal{O} \\left(\\frac{1}{k^{2}}\\right) $$. Dokl. Akad. Nauk SSSR 269(3), 543\u2013547 (1983). ((In Russian))","journal-title":"Dokl. Akad. Nauk SSSR"},{"key":"2804_CR74","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/s10107-006-0089-x","volume":"112","author":"Y Nesterov","year":"2008","unstructured":"Nesterov, Y.: Accelerating the cubic regularization of Newton\u2019s method on convex problems. Math. Program. 112, 159\u2013181 (2008)","journal-title":"Math. Program."},{"key":"2804_CR75","doi-asserted-by":"crossref","unstructured":"Nesterov, Y.: Lectures on Convex Optimization. Springer Cham, 2 edition, (2018)","DOI":"10.1007\/978-3-319-91578-4"},{"key":"2804_CR76","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s10107-019-01449-1","volume":"186","author":"Y Nesterov","year":"2021","unstructured":"Nesterov, Y.: Implementable tensor methods in unconstrained convex optimization. Math. Program. 186, 157\u2013183 (2021)","journal-title":"Math. Program."},{"key":"2804_CR77","doi-asserted-by":"publisher","first-page":"2807","DOI":"10.1137\/20M134705X","volume":"31","author":"Y Nesterov","year":"2021","unstructured":"Nesterov, Y.: Inexact high-order proximal-point methods with auxiliary search procedure. SIAM J. Optim. 31, 2807\u20132828 (2021)","journal-title":"SIAM J. Optim."},{"key":"2804_CR78","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10957-021-01930-y","volume":"191","author":"Y Nesterov","year":"2021","unstructured":"Nesterov, Y.: Superfast second-order methods for unconstrained convex optimization. J. Optim. Theory Appl. 191, 1\u201330 (2021)","journal-title":"J. Optim. Theory Appl."},{"issue":"3","key":"2804_CR79","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1080\/10556788.2020.1854252","volume":"37","author":"Y Nesterov","year":"2022","unstructured":"Nesterov, Y.: Inexact basic tensor methods for some classes of convex optimization problems. Optimization Methods and Software 37(3), 878\u2013906 (2022)","journal-title":"Optimization Methods and Software"},{"key":"2804_CR80","doi-asserted-by":"crossref","unstructured":"Nesterov, Y.: Set-limited functions and polynomial-time interior-point methods. J. Optim. Theory and Appl. (2023)","DOI":"10.1007\/s10957-023-02163-x"},{"key":"2804_CR81","doi-asserted-by":"crossref","unstructured":"Nesterov, Y., Nemirovskii, A.: Interior-Point Polynomial Algorithms in Convex Programming. Society for Industrial and Applied Mathematics, (1994)","DOI":"10.1137\/1.9781611970791"},{"key":"2804_CR82","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s10107-006-0706-8","volume":"108","author":"Y Nesterov","year":"2006","unstructured":"Nesterov, Y., Polyak, B.T.: Cubic regularization of Newton method and its global performance. Math. Program. 108, 177\u2013205 (2006)","journal-title":"Math. Program."},{"key":"2804_CR83","doi-asserted-by":"crossref","unstructured":"Newton, I.: Philosophiae naturalis principia mathematica. Edmond Halley, (1687)","DOI":"10.5479\/sil.52126.39088015628399"},{"key":"2804_CR84","doi-asserted-by":"publisher","DOI":"10.1007\/b98874","volume-title":"Numerical Optimization","author":"J Nocedal","year":"1999","unstructured":"Nocedal, J., Wright, S.J.: Numerical Optimization, 1st edn. Springer, New York, NY (1999)","edition":"1"},{"issue":"1","key":"2804_CR85","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1137\/15M1021106","volume":"27","author":"M Pilanci","year":"2017","unstructured":"Pilanci, M., Wainwright, M.: Newton sketch: A linear-time optimization algorithm with linear-quadratic convergence. SIAM J. Optim. 27(1), 205\u2013245 (2017)","journal-title":"SIAM J. Optim."},{"key":"2804_CR86","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1016\/j.ejor.2005.06.076","volume":"181","author":"Boris Teodorovich Polyak","year":"2007","unstructured":"Boris Teodorovich Polyak: Newton\u2019s method and its use in optimization. Eur. J. Oper. Res. 181, 1086\u20131096 (2007)","journal-title":"Eur. J. Oper. Res."},{"key":"2804_CR87","unstructured":"Polyak, R.: Complexity of the regularized Newton method. arXiv preprintarXiv:1706.08483, (2017)"},{"key":"2804_CR88","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/s10107-007-0143-3","volume":"120","author":"RA Polyak","year":"2009","unstructured":"Polyak, R.A.: Regularized Newton method for unconstrained convex optimization. Math. Program. 120, 125\u2013145 (2009)","journal-title":"Math. Program."},{"key":"2804_CR89","unstructured":"Qian, X., Islamov, R., Safaryan, M., Richt\u00e1rik, P.: Basis matters: better communication-efficient second order methods for federated learning. In International Conference on Artificial Intelligence and Statistics (AISTATS), (2022)"},{"key":"2804_CR90","unstructured":"Qu, Z., Richt\u00e1rik, P., Tak\u00e1\u010d, M., Fercoq, O: SDNA: Stochastic dual Newton ascent for empirical risk minimization. In The 33rd International Conference on Machine Learning (ICML), pages 1823\u20131832, (2016)"},{"issue":"3","key":"2804_CR91","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1023\/A:1021711402723","volume":"99","author":"CV Rao","year":"1998","unstructured":"Rao, C.V., Wright, S.J., Rawlings, J.B.: Application of interior-point methods to model predictive control. J. Optim. Theory Appl. 99(3), 723\u2013757 (1998)","journal-title":"J. Optim. Theory Appl."},{"key":"2804_CR92","unstructured":"Raphson, J.: Analysis Aequationum Universalis Seu Ad Aequationes Algebraicas Resolvendas Methodus Generalis & Expedita, Ex Nova Infinitarum Serierum Methodo, Deducta Ac Demonstrata. Th. Braddyll, (1697)"},{"key":"2804_CR93","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1137\/20M1320651","volume":"31","author":"A Rodomanov","year":"2021","unstructured":"Rodomanov, A., Nesterov, Y.: Greedy Quasi-Newton methods with explicit superlinear convergence. SIAM J. Optim. 31, 785\u2013811 (2021)","journal-title":"SIAM J. Optim."},{"key":"2804_CR94","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/s10957-020-01805-8","volume":"188","author":"A Rodomanov","year":"2021","unstructured":"Rodomanov, A., Nesterov, Y.: New results on superlinear convergence of classical Quasi-Newton methods. J. Optim. Theory Appl. 188, 744\u2013769 (2021)","journal-title":"J. Optim. Theory Appl."},{"key":"2804_CR95","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/s10107-021-01622-5","volume":"194","author":"A Rodomanov","year":"2021","unstructured":"Rodomanov, A., Nesterov, Y.: Rates of superlinear convergence for classical Quasi-Newton methods. Math. Program. 194, 159\u2013190 (2021)","journal-title":"Math. Program."},{"key":"2804_CR96","unstructured":"Safaryan, M., Islamov, R., Qian, X., Richt\u00e1rik, P.: FedNL: Making Newton-type methods applicable to federated learning. In Internatioanl Conference on Machine Learning, (2022)"},{"key":"2804_CR97","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s10107-016-0997-3","volume":"160","author":"K Scheinberg","year":"2016","unstructured":"Scheinberg, K., Tang, X.: Practical inexact proximal Quasi-Newton method with global complexity analysis. Math. Program. 160, 495\u2013529 (2016)","journal-title":"Math. Program."},{"key":"2804_CR98","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1090\/S0025-5718-1970-0274029-X","volume":"24","author":"DF Shanno","year":"1970","unstructured":"Shanno, D.F.: Conditioning of Quasi-Newton methods for function minimization. Math. Comput. 24, 647\u2013656 (1970)","journal-title":"Math. Comput."},{"key":"2804_CR99","unstructured":"Simpson, T.: Essays on several curious and useful subjects, in speculative and mix\u2019d mathematicks. Illustrated by a variety of examples. H. Woodfall (1740)"},{"key":"2804_CR100","first-page":"3","volume":"9","author":"MA Woodbury","year":"1949","unstructured":"Woodbury, M.A.: The stability of out-input matrices. Chicago IL 9, 3\u20138 (1949)","journal-title":"Chicago IL"},{"key":"2804_CR101","unstructured":"Woodbury, M.A.: Inverting modified matrices. Department of Statistics, Princeton University, (1950)"},{"key":"2804_CR102","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/s10107-019-01405-z","volume":"184","author":"X Peng","year":"2020","unstructured":"Peng, X., Roosta, F., Mahoney, M.W.: Newton-type methods for non-convex optimization under inexact Hessian information. Math. Program. 184, 35\u201370 (2020)","journal-title":"Math. Program."},{"key":"2804_CR103","unstructured":"Zhang, Y., Lin, X.: Disco: Distributed optimization for self-concordant empirical loss. In Francis Bach and David Blei, editors, Proceedings of the 32nd International Conference on Machine Learning, volume\u00a037 of Proceedings of Machine Learning Research, pages 362\u2013370, Lille, France, 07\u201309 Jul 2015. PMLR"}],"container-title":["Journal of Optimization Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-025-02804-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10957-025-02804-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-025-02804-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T08:58:41Z","timestamp":1775033921000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10957-025-02804-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"references-count":103,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["2804"],"URL":"https:\/\/doi.org\/10.1007\/s10957-025-02804-3","relation":{},"ISSN":["0022-3239","1573-2878"],"issn-type":[{"value":"0022-3239","type":"print"},{"value":"1573-2878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]},"assertion":[{"value":"30 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"27"}}