{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T06:50:34Z","timestamp":1774507834967,"version":"3.50.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T00:00:00Z","timestamp":1717113600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T00:00:00Z","timestamp":1717113600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100016046","name":"Provincial Secretariat for Higher Education and Scientific Research, Autonomous Province of Vojvodina","doi-asserted-by":"crossref","award":["142-451-2593\/2021-01\/2"],"award-info":[{"award-number":["142-451-2593\/2021-01\/2"]}],"id":[{"id":"10.13039\/501100016046","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100016046","name":"Provincial Secretariat for Higher Education and Scientific Research, Autonomous Province of Vojvodina","doi-asserted-by":"crossref","award":["142-451-2593\/2021-01\/2"],"award-info":[{"award-number":["142-451-2593\/2021-01\/2"]}],"id":[{"id":"10.13039\/501100016046","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Gruppo Nazionale per l\u2019Analisi Matematica, la Probabilit\u00e1 e le loro Applicazioni","award":["CUP E53C22001930001"],"award-info":[{"award-number":["CUP E53C22001930001"]}]},{"name":"Gruppo Nazionale per l\u2019Analisi Matematica, la Probabilit\u00e1 e le loro Applicazioni","award":["CUP E53C22001930001"],"award-info":[{"award-number":["CUP E53C22001930001"]}]},{"DOI":"10.13039\/501100004434","name":"Universit\u00e0 degli Studi di Firenze","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004434","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comput Optim Appl"],"published-print":{"date-parts":[[2024,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In this work, we introduce a novel stochastic second-order method, within the framework of a non-monotone trust-region approach, for solving the unconstrained, nonlinear, and non-convex optimization problems arising in the training of deep neural networks. The proposed algorithm makes use of subsampling strategies that yield noisy approximations of the finite sum objective function and its gradient. We introduce an adaptive sample size strategy based on inexpensive additional sampling to control the resulting approximation error. Depending on the estimated progress of the algorithm, this can yield sample size scenarios ranging from mini-batch to full sample functions. We provide convergence analysis for all possible scenarios and show that the proposed method achieves almost sure convergence under standard assumptions for the trust-region framework. We report numerical experiments showing that the proposed algorithm outperforms its state-of-the-art counterpart in deep neural network training for image classification and regression tasks while requiring a significantly smaller number of gradient evaluations.<\/jats:p>","DOI":"10.1007\/s10589-024-00580-w","type":"journal-article","created":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T14:03:11Z","timestamp":1717164191000},"page":"247-278","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A non-monotone trust-region method with noisy oracles and additional sampling"],"prefix":"10.1007","volume":"89","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3348-7233","authenticated-orcid":false,"given":"Nata\u0161a","family":"Kreji\u0107","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5195-9295","authenticated-orcid":false,"given":"Nata\u0161a","family":"Krklec Jerinki\u0107","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4826-1114","authenticated-orcid":false,"given":"\u00c1ngeles","family":"Mart\u00ednez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2937-9654","authenticated-orcid":false,"given":"Mahsa","family":"Yousefi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,5,31]]},"reference":[{"key":"580_CR1","doi-asserted-by":"publisher","unstructured":"Nocedal, J., Wright, S.: Numerical Optimization. Springer, New York, NY (2006). https:\/\/doi.org\/10.1007\/978-0-387-40065-5","DOI":"10.1007\/978-0-387-40065-5"},{"key":"580_CR2","doi-asserted-by":"publisher","unstructured":"Conn, A.R., Gould, N.I.M., Toint, P.L.: Trust-Region Methods. SIAM, Philadelphia, PA (2000). https:\/\/doi.org\/10.1137\/1.9780898719857","DOI":"10.1137\/1.9780898719857"},{"issue":"1","key":"580_CR3","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1016\/j.apm.2011.07.021","volume":"36","author":"M Ahookhosh","year":"2012","unstructured":"Ahookhosh, M., Amini, K., Peyghami, M.R.: A non-monotone trust-region line search method for large-scale unconstrained optimization. Appl. Math. Model. 36(1), 478\u2013487 (2012). https:\/\/doi.org\/10.1016\/j.apm.2011.07.021","journal-title":"Appl. Math. Model."},{"issue":"341","key":"580_CR4","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1090\/mcom\/3802","volume":"92","author":"D Di Serafino","year":"2023","unstructured":"Di Serafino, D., Kreji\u0107, N., Krklec Jerinki\u0107, N., Viola, M.: LSOS: line-search second-order stochastic optimization methods for nonconvex finite sums. Math. Comput. 92(341), 1273\u20131299 (2023). https:\/\/doi.org\/10.1090\/mcom\/3802","journal-title":"Math. Comput."},{"key":"580_CR5","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22, 400\u2013407 (1951). https:\/\/doi.org\/10.1214\/aoms\/1177729586","journal-title":"Ann. Math. Stat."},{"key":"580_CR6","unstructured":"Bottou, L., LeCun, Y.: Large scale online learning. In: Advances in Neural Information Processing Systems, vol. 16, pp. 217\u2013224 (2004). Available at: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2003"},{"key":"580_CR7","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, pp. 1646\u20131654 (2014). Available at: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2014"},{"key":"580_CR8","unstructured":"Johnson, R., Zhang, T.: Accelerating stochastic gradient descent using predictive variance reduction. In: Advances in Neural Information Processing Systems, vol. 26, pp. 315\u2013323 (2013). Available at: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2013"},{"issue":"1\u20132","key":"580_CR9","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s10107-016-1030-6","volume":"162","author":"M Schmidt","year":"2017","unstructured":"Schmidt, M., Le Roux, N., Bach, F.: Minimizing finite sums with the stochastic average gradient. Math. Program. 162(1\u20132), 83\u2013112 (2017). https:\/\/doi.org\/10.1007\/s10107-016-1030-6","journal-title":"Math. Program."},{"key":"580_CR10","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: International Conference on Machine Learning, pp. 2613\u20132621 (2017). PMLR. Available at: https:\/\/proceedings.mlr.press\/v70\/"},{"key":"580_CR11","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(7) (2011). Available at: https:\/\/www.jmlr.org\/papers\/v12\/"},{"key":"580_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings (2015). Available at: http:\/\/arxiv.org\/abs\/1412.6980"},{"issue":"2","key":"580_CR13","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). https:\/\/doi.org\/10.1137\/16M1080173","journal-title":"SIAM Rev."},{"key":"580_CR14","doi-asserted-by":"publisher","unstructured":"Kylasa, S., Roosta, F., Mahoney, M.W., Grama, A.: GPU accelerated sub-sampled Newton\u2019s method for convex classification problems. In: Proceedings of the 2019 SIAM International Conference on Data Mining, pp. 702\u2013710 (2019). https:\/\/doi.org\/10.1137\/1.9781611975673.79 . SIAM","DOI":"10.1137\/1.9781611975673.79"},{"key":"580_CR15","unstructured":"Martens, J.: Deep learning via Hessian-free optimization. In: Proceedings of the 27th International Conference on Machine Learning, pp. 735\u2013742 (2010). Available at: https:\/\/www.icml2010.org\/abstracts.html"},{"key":"580_CR16","doi-asserted-by":"publisher","unstructured":"Martens, J., Sutskever, I.: Training deep and recurrent networks with Hessian-free optimization. In: Neural Networks: Tricks of the Trade, pp. 479\u2013535. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-35289-8_27","DOI":"10.1007\/978-3-642-35289-8_27"},{"issue":"2","key":"580_CR17","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1093\/imanum\/dry009","volume":"39","author":"R Bollapragada","year":"2019","unstructured":"Bollapragada, R., Byrd, R.H., Nocedal, J.: Exact and inexact subsampled Newton methods for optimization. IMA J. Numer. Anal. 39(2), 545\u2013578 (2019). https:\/\/doi.org\/10.1093\/imanum\/dry009","journal-title":"IMA J. Numer. Anal."},{"key":"580_CR18","doi-asserted-by":"publisher","unstructured":"Xu, P., Roosta, F., Mahoney, M.W.: Second-order optimization for non-convex machine learning: An empirical study. In: Proceedings of the 2020 SIAM International Conference on Data Mining, pp. 199\u2013207 (2020). https:\/\/doi.org\/10.1137\/1.9781611976236.23 . SIAM","DOI":"10.1137\/1.9781611976236.23"},{"key":"580_CR19","unstructured":"Martens, J., Grosse, R.: Optimizing neural networks with Kronecker-factored approximate curvature. In: International Conference on Machine Learning, pp. 2408\u20132417 (2015). PMLR. Available at: https:\/\/proceedings.mlr.press\/v37\/"},{"key":"580_CR20","unstructured":"Goldfarb, D., Ren, Y., Bahamou, A.: Practical quasi-newton methods for training deep neural networks. In: Advances in Neural Information Processing Systems, vol. 33, pp. 2386\u20132396 (2020). Available at: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020"},{"issue":"1","key":"580_CR21","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(1), 3151\u20133181 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"580_CR22","unstructured":"Gower, R., Goldfarb, D., Richt\u00e1rik, P.: Stochastic block BFGS: Squeezing more curvature out of data. In: International Conference on Machine Learning, pp. 1869\u20131878 (2016). PMLR. Available at: https:\/\/proceedings.mlr.press\/v48\/"},{"issue":"2","key":"580_CR23","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1137\/15M1053141","volume":"27","author":"X Wang","year":"2017","unstructured":"Wang, X., Ma, S., Goldfarb, D., Liu, W.: Stochastic quasi-Newton methods for nonconvex stochastic optimization. SIAM J. Optim. 27(2), 927\u2013956 (2017). https:\/\/doi.org\/10.1137\/15M1053141","journal-title":"SIAM J. Optim."},{"issue":"1","key":"580_CR24","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1080\/10556788.2019.1658107","volume":"35","author":"AS Berahas","year":"2020","unstructured":"Berahas, A.S., Tak\u00e1\u010d, M.: A robust multi-batch L-BFGS method for machine learning. Optim. Methods Softw. 35(1), 191\u2013219 (2020). https:\/\/doi.org\/10.1080\/10556788.2019.1658107","journal-title":"Optim. Methods Softw."},{"key":"580_CR25","unstructured":"Bollapragada, R., Nocedal, J., Mudigere, D., Shi, H.-J., Tang, P.T.P.: A progressive batching L-BFGS method for machine learning. In: International Conference on Machine Learning, pp. 620\u2013629 (2018). PMLR. Available at: https:\/\/proceedings.mlr.press\/v80\/"},{"key":"580_CR26","doi-asserted-by":"publisher","unstructured":"Jahani, M., Nazari, M., Rusakov, S., Berahas, A.S., Tak\u00e1\u010d, M.: Scaling up quasi-newton algorithms: communication efficient distributed SR1. In: Machine Learning, Optimization, and Data Science. LOD 2020. Lecture Notes in Computer Science, vol. 12565, pp. 41\u201354. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-64583-0_5","DOI":"10.1007\/978-3-030-64583-0_5"},{"issue":"5","key":"580_CR27","doi-asserted-by":"publisher","first-page":"1668","DOI":"10.1080\/10556788.2021.1977806","volume":"37","author":"AS Berahas","year":"2022","unstructured":"Berahas, A.S., Jahani, M., Richt\u00e1rik, P., Tak\u00e1\u010d, M.: Quasi-newton methods for machine learning: forget the past, just sample. Optim. Methods Softw. 37(5), 1668\u20131704 (2022). https:\/\/doi.org\/10.1080\/10556788.2021.1977806","journal-title":"Optim. Methods Softw."},{"key":"580_CR28","doi-asserted-by":"publisher","unstructured":"Rafati, J., Marcia, R.F.: Improving L-BFGS initialization for trust-region methods in deep learning. In: 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 501\u2013508 (2018). https:\/\/doi.org\/10.1109\/ICMLA.2018.00081 . IEEE","DOI":"10.1109\/ICMLA.2018.00081"},{"key":"580_CR29","doi-asserted-by":"publisher","unstructured":"Yousefi, M., Mart\u00ednez\u00a0Calomardo, \u00c1.: A stochastic modified limited memory BFGS for training deep neural networks. In: Intelligent Computing: Proceedings of the 2022 Computing Conference, Volume 2, pp. 9\u201328 (2022). Springer. https:\/\/doi.org\/10.1007\/978-3-031-10464-0_2","DOI":"10.1007\/978-3-031-10464-0_2"},{"issue":"3","key":"580_CR30","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1080\/10556788.2019.1624747","volume":"35","author":"JB Erway","year":"2020","unstructured":"Erway, J.B., Griffin, J., Marcia, R.F., Omheni, R.: Trust-region algorithms for training responses: machine learning methods using indefinite Hessian approximations. Optim. Methods Softw. 35(3), 460\u2013487 (2020). https:\/\/doi.org\/10.1080\/10556788.2019.1624747","journal-title":"Optim. Methods Softw."},{"issue":"4","key":"580_CR31","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1137\/0723046","volume":"23","author":"L Grippo","year":"1986","unstructured":"Grippo, L., Lampariello, F., Lucidi, S.: A non-monotone line search technique for Newton\u2019s method. SIAM J. Numer. Anal. 23(4), 707\u2013716 (1986). https:\/\/doi.org\/10.1137\/0723046","journal-title":"SIAM J. Numer. Anal."},{"issue":"2","key":"580_CR32","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1007\/BF00939608","volume":"76","author":"N Deng","year":"1993","unstructured":"Deng, N., Xiao, Y., Zhou, F.: Nonmonotonic trust-region algorithm. J. Optim. Theory Appl. 76(2), 259\u2013285 (1993). https:\/\/doi.org\/10.1007\/BF00939608","journal-title":"J. Optim. Theory Appl."},{"issue":"8","key":"580_CR33","doi-asserted-by":"publisher","first-page":"2432","DOI":"10.1016\/j.cam.2010.10.044","volume":"235","author":"Z Cui","year":"2011","unstructured":"Cui, Z., Wu, B., Qu, S.: Combining non-monotone conic trust-region and line search techniques for unconstrained optimization. J. Comput. Appl. Math. 235(8), 2432\u20132441 (2011). https:\/\/doi.org\/10.1016\/j.cam.2010.10.044","journal-title":"J. Comput. Appl. Math."},{"issue":"4","key":"580_CR34","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1007\/s11075-014-9869-1","volume":"68","author":"N Kreji\u0107","year":"2015","unstructured":"Kreji\u0107, N., Krklec Jerinki\u0107, N.: Non-monotone line search methods with variable sample size. Numer. Algor. 68(4), 711\u2013739 (2015). https:\/\/doi.org\/10.1007\/s11075-014-9869-1","journal-title":"Numer. Algor."},{"key":"580_CR35","doi-asserted-by":"publisher","unstructured":"Yousefi, M., Mart\u00ednez\u00a0Calomardo, \u00c1.: A stochastic nonmonotone trust-region training algorithm for image classification. In: 2022 16th International Conference on Signal-Image Technology and Internet-Based Systems (SITIS), pp. 522\u2013529 (2022). IEEE. https:\/\/doi.org\/10.1109\/SITIS57111.2022.00084","DOI":"10.1109\/SITIS57111.2022.00084"},{"key":"580_CR36","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-023-01941-9","author":"S Sun","year":"2023","unstructured":"Sun, S., Nocedal, J.: A trust-region method for noisy unconstrained optimization. Math. Program. (2023). https:\/\/doi.org\/10.1007\/s10107-023-01941-9","journal-title":"Math. Program."},{"key":"580_CR37","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-023-01999-5","author":"L Cao","year":"2023","unstructured":"Cao, L., Berahas, A.S., Scheinberg, K.: First- and second-order high probability complexity bounds for trust-region methods with noisy oracles. Math. Program. (2023). https:\/\/doi.org\/10.1007\/s10107-023-01999-5","journal-title":"Math. Program."},{"issue":"1","key":"580_CR38","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1137\/17M1144799","volume":"29","author":"AN Iusem","year":"2019","unstructured":"Iusem, A.N., Jofr\u00e9, A., Oliveira, R.I., Thompson, P.: Variance-based extra gradient methods with line search for stochastic variational inequalities. SIAM J. Optim. 29(1), 175\u2013206 (2019). https:\/\/doi.org\/10.1137\/17M1144799","journal-title":"SIAM J. Optim."},{"issue":"6","key":"580_CR39","doi-asserted-by":"publisher","first-page":"1164","DOI":"10.1080\/10556788.2015.1025403","volume":"30","author":"N Kreji\u0107","year":"2015","unstructured":"Kreji\u0107, N., Lu\u017eanin, Z., Ovcin, Z., Stojkovska, I.: Descent direction method with line search for unconstrained optimization in noisy environment. Optim. Methods Softw. 30(6), 1164\u20131184 (2015). https:\/\/doi.org\/10.1080\/10556788.2015.1025403","journal-title":"Optim. Methods Softw."},{"issue":"2","key":"580_CR40","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1287\/ijoo.2019.0016","volume":"1","author":"J Blanchet","year":"2019","unstructured":"Blanchet, J., Cartis, C., Menickelly, M., Scheinberg, K.: Convergence rate analysis of a stochastic trust-region method via supermartingales. INFORMS J. Optim. 1(2), 92\u2013119 (2019). https:\/\/doi.org\/10.1287\/ijoo.2019.0016","journal-title":"INFORMS J. Optim."},{"issue":"2","key":"580_CR41","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1007\/s10107-017-1141-8","volume":"169","author":"R Chen","year":"2018","unstructured":"Chen, R., Menickelly, M., Scheinberg, K.: Stochastic optimization using a trust-region method and random models. Math. Program. 169(2), 447\u2013487 (2018). https:\/\/doi.org\/10.1007\/s10107-017-1141-8","journal-title":"Math. Program."},{"issue":"1","key":"580_CR42","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/s10589-022-00430-7","volume":"84","author":"S Bellavia","year":"2023","unstructured":"Bellavia, S., Kreji\u0107, N., Morini, B., Rebegoldi, S.: A stochastic first-order trust-region method with inexact restoration for finite-sum minimization. Comput. Optim. Appl. 84(1), 53\u201384 (2023). https:\/\/doi.org\/10.1007\/s10589-022-00430-7","journal-title":"Comput. Optim. Appl."},{"key":"580_CR43","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, pp. 249\u2013256 (2010). Available at: https:\/\/proceedings.mlr.press\/v9\/"},{"issue":"2","key":"580_CR44","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s10589-016-9868-3","volume":"66","author":"J Brust","year":"2017","unstructured":"Brust, J., Erway, J.B., Marcia, R.F.: On solving L-SR1 trust-region subproblems. Comput. Optim. Appl. 66(2), 245\u2013266 (2017). https:\/\/doi.org\/10.1007\/s10589-016-9868-3","journal-title":"Comput. Optim. Appl."},{"key":"580_CR45","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge, MA (2016)"},{"key":"580_CR46","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"issue":"10","key":"580_CR47","doi-asserted-by":"publisher","first-page":"490","DOI":"10.3390\/a16100490","volume":"16","author":"M Yousefi","year":"2023","unstructured":"Yousefi, M., Mart\u00ednez, \u00c1.: Deep neural networks training by stochastic quasi-newton trust-region methods. Algorithms 16(10), 490 (2023). https:\/\/doi.org\/10.3390\/a16100490","journal-title":"Algorithms"},{"issue":"11","key":"580_CR48","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998). https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc. IEEE"},{"key":"580_CR49","unstructured":"LeCun, Y.: The MNIST Database of Handwritten Digits (1998). Available at: https:\/\/www.kaggle.com\/datasets\/hojjatk\/mnist-dataset"},{"key":"580_CR50","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images (2009). Available at: https:\/\/api.semanticscholar.org\/CorpusID:18268744"}],"container-title":["Computational Optimization and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10589-024-00580-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10589-024-00580-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10589-024-00580-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T08:12:52Z","timestamp":1722845572000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10589-024-00580-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,31]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["580"],"URL":"https:\/\/doi.org\/10.1007\/s10589-024-00580-w","relation":{},"ISSN":["0926-6003","1573-2894"],"issn-type":[{"value":"0926-6003","type":"print"},{"value":"1573-2894","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,31]]},"assertion":[{"value":"7 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 May 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":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}