{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T05:03:54Z","timestamp":1784869434156,"version":"3.55.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"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":[[2026,7]]},"DOI":"10.1007\/s10957-026-03033-y","type":"journal-article","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T11:24:28Z","timestamp":1782127468000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adjusted Shuffling SARAH: Advancing Complexity Analysis via Dynamic Gradient Weighting"],"prefix":"10.1007","volume":"210","author":[{"given":"Duc Toan","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trang H.","family":"Tran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6083-606X","authenticated-orcid":false,"given":"Lam M.","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"3033_CR1","unstructured":"Ahn, K., Yun, C., Sra, S.: SGD with Shuffling: optimal rates without component convexity and large epoch requirements. In: Advances in Neural Information Processing Systems, vol. 33, pp. 17526\u201317535. (2020)"},{"key":"3033_CR2","unstructured":"Allen-Zhu, Z., Yuan, Y.: Improved SVRG for Non-Strongly-Convex or Sum-of-Non-Convex Objectives. In: Proceedings of The Thirty-Third International Conference on Machine Learning, vol. 48, pp. 1080\u20131089. (2016) . (PMLR)"},{"key":"3033_CR3","doi-asserted-by":"crossref","unstructured":"Bach, F.R., Lanckriet, G.R.G., Jordan, M.I.: Multiple kernel learning, conic duality, and the SMO algorithm. In: Proceedings of the Twenty-First International Conference on Machine Learning, ICML \u201904, p.\u00a06 (2004)","DOI":"10.1145\/1015330.1015424"},{"key":"3033_CR4","doi-asserted-by":"crossref","unstructured":"Bengio, Y.: Practical recommendations for gradient-based training of deep architectures. In: Neural Networks: Tricks of the Trade: Second Edition, pp. 437\u2013478. Springer Berlin Heidelberg, Berlin, Heidelberg (2012)","DOI":"10.1007\/978-3-642-35289-8_26"},{"issue":"3","key":"3033_CR5","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1007\/s11590-023-02081-x","volume":"18","author":"A Beznosikov","year":"2024","unstructured":"Beznosikov, A., Tak\u00e1\u010d, M.: Random-reshuffled SARAH does not need full gradient computations. Optim. Lett. 18(3), 727\u2013749 (2024)","journal-title":"Optim. Lett."},{"key":"3033_CR6","unstructured":"Bottou, L.: Curiously fast convergence of some stochastic gradient descent algorithms. In: Proceedings of the Symposium on Learning and Data Science, vol. 8, pp. 2624\u20132633. Citeseer, Paris (2009)"},{"issue":"2","key":"3033_CR7","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1137\/16M1080173","volume":"60","author":"L Bottou","year":"2018","unstructured":"Bottou, L., Curtis, F.E., Nocedal, J.: Optimization Methods for Large-Scale Machine Learning. SIAM Rev. 60(2), 223\u2013311 (2018)","journal-title":"SIAM Rev."},{"key":"3033_CR8","unstructured":"Cai, X., Diakonikolas, J.: Last Iterate Convergence of Incremental Methods as a Model of Forgetting. In: International Conference on Learning Representations, vol. 2025, pp. 102,613\u2013102,647 (2025)"},{"key":"3033_CR9","doi-asserted-by":"crossref","unstructured":"Cai, X., Lin, C.Y., Diakonikolas, J.: Tighter Convergence Bounds for Shuffled SGD via Primal-Dual Perspective. In: Advances in Neural Information Processing Systems, vol. 37, pp. 72475\u201372524. (2024)","DOI":"10.52202\/079017-2310"},{"key":"3033_CR10","unstructured":"Cha, J., Lee, J., Yun, C.: Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond. In: Proceedings of the Fortieth International Conference on Machine Learning, vol. 202, pp. 3855\u20133912. (2023) . (PMLR)"},{"key":"3033_CR11","doi-asserted-by":"crossref","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol 2(3), (2011)","DOI":"10.1145\/1961189.1961199"},{"key":"3033_CR12","doi-asserted-by":"crossref","unstructured":"Cox, D.R.: The Regression Analysis of Binary Sequences. J. R. Stat. Soc. Ser. B Methodol. 20(2), 215\u2013232 (1958)","DOI":"10.1111\/j.2517-6161.1958.tb00292.x"},{"key":"3033_CR13","unstructured":"Defazio, A., Bach, F., Lacoste-Julien, S.: SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives. In: Advances in Neural Information Processing Systems, vol. 27, (2014)"},{"issue":"2","key":"3033_CR14","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.1137\/15M1049695","volume":"27","author":"M G\u00fcrb\u00fczbalaban","year":"2017","unstructured":"G\u00fcrb\u00fczbalaban, M., Ozdaglar, A., Parrilo, P.A.: On the Convergence Rate of Incremental Aggregated Gradient Algorithms. SIAM J. Optim. 27(2), 1035\u20131048 (2017)","journal-title":"SIAM J. Optim."},{"issue":"4","key":"3033_CR15","doi-asserted-by":"publisher","first-page":"2542","DOI":"10.1137\/17M1147846","volume":"29","author":"M G\u00fcrb\u00fczbalaban","year":"2019","unstructured":"G\u00fcrb\u00fczbalaban, M., Ozdaglar, A., Parrilo, P.A.: Convergence Rate of Incremental Gradient and Incremental Newton Methods. SIAM J. Optim. 29(4), 2542\u20132565 (2019)","journal-title":"SIAM J. Optim."},{"key":"3033_CR16","unstructured":"Haochen, J., Sra, S.: Random Shuffling Beats SGD after Finite Epochs. In: Proceedings of the Thirty-Sixth International Conference on Machine Learning, vol. 97, pp. 2624\u20132633. (2019) . (PMLR)"},{"key":"3033_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction","author":"T Hastie","year":"2009","unstructured":"Hastie, T.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, New York (2009)"},{"issue":"3","key":"3033_CR18","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/s10915-025-02798-0","volume":"102","author":"X Hu","year":"2025","unstructured":"Hu, X., Xiao, N., Liu, X., Toh, K.C.: Learning-Rate-Free Momentum SGD with Reshuffling Converges in Nonsmooth Nonconvex Optimization. J. Sci. Comput. 102(3), 85 (2025)","journal-title":"J. Sci. Comput."},{"key":"3033_CR19","unstructured":"Huang, X., Yuan, K., Mao, X., Yin, W.: An Improved Analysis and Rates for Variance Reduction under Without-replacement Sampling Orders. In: Advances in Neural Information Processing Systems, vol. 34, pp. 3232\u20133243. (2021)"},{"key":"3033_CR20","unstructured":"Johnson, R., Zhang, T.: Accelerating Stochastic Gradient Descent using Predictive Variance Reduction. In: Advances in Neural Information Processing Systems, vol. 26, (2013)"},{"key":"3033_CR21","unstructured":"Liu, Z., Zhou, Z.: On the Last-Iterate Convergence of Shuffling Gradient Methods. In: Proceedings of the Forty-First International Conference on Machine Learning, vol. 235, pp. 32471\u201332508. (2024) . (PMLR)"},{"key":"3033_CR22","unstructured":"Malinovsky, G., Sailanbayev, A., Richt\u00e1rik, P.: Random Reshuffling with Variance Reduction: New Analysis and Better Rates. In: Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, vol. 216, pp. 1347\u20131357. (2023) . (PMLR)"},{"key":"3033_CR23","unstructured":"Medyakov, D., Molodtsov, G., Chezhegov, S., Rebrikov, A., Beznosikov, A.: Variance reduction methods do not need to compute full gradients: Improved efficiency through shuffling, (2025). arXiv:2502.14648 arXiv preprint"},{"key":"3033_CR24","unstructured":"Mishchenko, K., Khaled, A., Richtarik, P.: Random Reshuffling: Simple Analysis with Vast Improvements. In: Advances in Neural Information Processing Systems, vol. 33, pp. 17309\u201317320. (2020)"},{"issue":"2","key":"3033_CR25","doi-asserted-by":"publisher","first-page":"1420","DOI":"10.1137\/16M1101702","volume":"28","author":"A Mokhtari","year":"2018","unstructured":"Mokhtari, A., G\u00fcrb\u00fczbalaban, M., Ribeiro, A.: Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate. SIAM J. Optim. 28(2), 1420\u20131447 (2018)","journal-title":"SIAM J. Optim."},{"key":"3033_CR26","unstructured":"Nguyen, L.M., Liu, J., Scheinberg, K., Tak\u00e1\u010d, M.: SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient. In: Proceedings of the Thirty-Fourth International Conference on Machine Learning, vol. 70, pp. 2613\u20132621. PMLR (2017)"},{"issue":"1","key":"3033_CR27","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1080\/10556788.2020.1818081","volume":"36","author":"LM Nguyen","year":"2021","unstructured":"Nguyen, L.M., Scheinberg, K., Tak\u00e1\u010d, M.: Inexact SARAH algorithm for stochastic optimization. Optim. Methods Softw. 36(1), 237\u2013258 (2021)","journal-title":"Optim. Methods Softw."},{"issue":"207","key":"3033_CR28","first-page":"1","volume":"22","author":"LM Nguyen","year":"2021","unstructured":"Nguyen, L.M., Tran-Dinh, Q., Phan, D.T., Nguyen, P.H., van Dijk, M.: A Unified Convergence Analysis for Shuffling-Type Gradient Methods. J. Mach. Learn. Res. 22(207), 1\u201344 (2021)","journal-title":"J. Mach. Learn. Res."},{"issue":"6","key":"3033_CR29","doi-asserted-by":"publisher","first-page":"1583","DOI":"10.1007\/s11590-019-01520-y","volume":"14","author":"Y Park","year":"2020","unstructured":"Park, Y., Ryu, E.K.: Linear Convergence of Cyclic SAGA. Optim. Lett. 14(6), 1583\u20131598 (2020)","journal-title":"Optim. Lett."},{"issue":"110","key":"3033_CR30","first-page":"1","volume":"21","author":"NH Pham","year":"2020","unstructured":"Pham, N.H., Nguyen, L.M., Phan, D.T., Tran-Dinh, Q.: ProxSARAH: An Efficient Algorithmic Framework for Stochastic Composite Nonconvex Optimization. J. Mach. Learn. Res. 21(110), 1\u201348 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"3033_CR31","unstructured":"Rajput, S., Gupta, A., Papailiopoulos, D.: Closing the convergence gap of SGD without replacement. In: Proceedings of the Thirty-Seventh International Conference on Machine Learning, vol. 119, pp. 7964\u20137973. (2020) . (PMLR)"},{"issue":"2","key":"3033_CR32","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/s12532-013-0053-8","volume":"5","author":"B Recht","year":"2013","unstructured":"Recht, B., R\u00e9, C.: Parallel Stochastic Gradient Algorithms for Large-Scale Matrix Completion. Math. Program. Comput. 5(2), 201\u2013226 (2013)","journal-title":"Math. Program. Comput."},{"key":"3033_CR33","doi-asserted-by":"crossref","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Statist. pp , 400\u2013407 (1951)","DOI":"10.1214\/aoms\/1177729586"},{"key":"3033_CR34","unstructured":"Roux, N., Schmidt, M., Bach, F.: A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets. In: Advances in Neural Information Processing Systems, vol. 25, (2012)"},{"key":"3033_CR35","unstructured":"Safran, I., Shamir, O.: How Good is SGD with Random Shuffling? In: Proceedings of Thirty-Third Conference on Learning Theory, vol. 125, pp. 3250\u20133284. (2020) . (PMLR)"},{"key":"3033_CR36","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/8996.001.0001","volume-title":"Optimization for Machine Learning","author":"S Sra","year":"2011","unstructured":"Sra, S., Nowozin, S., Wright, S.J.: Optimization for Machine Learning. MIT Press, Cambridge (2011)"},{"issue":"2","key":"3033_CR37","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/s40305-020-00309-6","volume":"8","author":"RY Sun","year":"2020","unstructured":"Sun, R.Y.: Optimization for Deep Learning: An Overview. J. Oper. Res. Soc. China. 8(2), 249\u2013294 (2020)","journal-title":"J. Oper. Res. Soc. China."},{"key":"3033_CR38","unstructured":"Tran, T.H., Nguyen, L.M., Tran-Dinh, Q.: SMG: A shuffling gradient-based method with momentum. In: Proceedings of the Thirty-Eighth International Conference on Machine Learning, vol. 139, pp. 10,379\u201310,389. PMLR (2021)"},{"key":"3033_CR39","unstructured":"Tran, T.H., Scheinberg, K., Nguyen, L.M.: Nesterov Accelerated Shuffling Gradient Method for Convex Optimization. In: Proceedings of the Thirty-Nineth International Conference on Machine Learning, vol. 162, pp. 21703\u201321732. (2022) . (PMLR)"},{"issue":"4","key":"3033_CR40","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1007\/s10013-024-00699-7","volume":"53","author":"TH Tran","year":"2025","unstructured":"Tran, T.H., Tran-Dinh, Q., Nguyen, L.M.: Shuffling Momentum Gradient Algorithm for Convex Optimization. Vietnam J. Math. 53(4), 773\u2013801 (2025)","journal-title":"Vietnam J. Math."},{"issue":"2","key":"3033_CR41","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.1137\/16M1094415","volume":"28","author":"ND Vanli","year":"2018","unstructured":"Vanli, N.D., G\u00fcrb\u00fczbalaban, M., Ozdaglar, A.: Global Convergence Rate of Proximal Incremental Aggregated Gradient Methods. SIAM J. Optim. 28(2), 1282\u20131300 (2018)","journal-title":"SIAM J. Optim."},{"key":"3033_CR42","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms, (2017). arXiv:1708.07747 arXiv preprint"},{"key":"3033_CR43","doi-asserted-by":"publisher","first-page":"1390","DOI":"10.1109\/TSP.2020.2968280","volume":"68","author":"B Ying","year":"2020","unstructured":"Ying, B., Yuan, K., Sayed, A.H.: Variance-Reduced Stochastic Learning Under Random Reshuffling. IEEE Trans. Signal Process. 68, 1390\u20131408 (2020)","journal-title":"IEEE Trans. Signal Process."}],"container-title":["Journal of Optimization Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-026-03033-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10957-026-03033-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-026-03033-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T04:51:01Z","timestamp":1784868661000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10957-026-03033-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["3033"],"URL":"https:\/\/doi.org\/10.1007\/s10957-026-03033-y","relation":{},"ISSN":["0022-3239","1573-2878"],"issn-type":[{"value":"0022-3239","type":"print"},{"value":"1573-2878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,22]]},"assertion":[{"value":"11 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"12"}}