{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T12:55:48Z","timestamp":1774529748350,"version":"3.50.1"},"reference-count":80,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T00:00:00Z","timestamp":1723161600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T00:00:00Z","timestamp":1723161600000},"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 Glob Optim"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s10898-024-01426-9","type":"journal-article","created":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T02:02:31Z","timestamp":1724119351000},"page":"347-376","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["The limitation of neural nets for approximation and optimization"],"prefix":"10.1007","volume":"94","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1436-5348","authenticated-orcid":false,"given":"T.","family":"Giovannelli","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3633-5518","authenticated-orcid":false,"given":"O.","family":"Sohab","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1097-6384","authenticated-orcid":false,"given":"L. N.","family":"Vicente","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,9]]},"reference":[{"key":"1426_CR1","doi-asserted-by":"crossref","unstructured":"Al-Kababji, A., Bensaali, F., Prasad Dakua, S: Scheduling techniques for liver segmentation: ReduceLRonPlateau Vs OneCycleLR. Preprint at arXiv:2202.06373 (2022)","DOI":"10.1007\/978-3-031-08277-1_17"},{"key":"1426_CR2","doi-asserted-by":"crossref","unstructured":"Audet, C., Hare, W.: Derivative-Free and Blackbox Optimization. Springer Series in Operations Research and Financial Engineering. Springer, Cham, 2017. With a foreword by John E. Dennis Jr","DOI":"10.1007\/978-3-319-68913-5"},{"key":"1426_CR3","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1137\/040603371","volume":"17","author":"C Audet","year":"2006","unstructured":"Audet, C., Dennis, J.E., Jr.: Mesh adaptive direct search algorithms for constrained optimization. SIAM J. Optim. 17, 188\u2013217 (2006)","journal-title":"SIAM J. Optim."},{"key":"1426_CR4","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/s10107-009-0305-6","volume":"128","author":"CP Avelino","year":"2011","unstructured":"Avelino, C.P., Moguerza, J.M., Olivares, A., Prieto, F.J.: Combining and scaling descent and negative curvature directions. Math. Program. 128, 285\u2013319 (2011)","journal-title":"Math. Program."},{"key":"1426_CR5","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/s10107-012-0578-z","volume":"134","author":"AS Bandeira","year":"2012","unstructured":"Bandeira, A.S., Scheinberg, K., Vicente, L.N.: Computation of sparse low degree interpolating polynomials and their application to derivative-free optimization. Math. Program. 134, 223\u2013257 (2012)","journal-title":"Math. Program."},{"key":"1426_CR6","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1137\/18M1177718","volume":"29","author":"AS Berahas","year":"2019","unstructured":"Berahas, A.S., Byrd, R.H., Nocedal, J.: Derivative-free optimization of noisy functions via quasi-newton methods. SIAM J. Optim. 29, 965\u2013993 (2019)","journal-title":"SIAM J. Optim."},{"key":"1426_CR7","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1137\/19M1291832","volume":"31","author":"AS Berahas","year":"2021","unstructured":"Berahas, A.S., Cao, L., Scheinberg, K.: Global convergence rate analysis of a generic line search algorithm with noise. SIAM J. Optim. 31, 1489\u20131518 (2021)","journal-title":"SIAM J. Optim."},{"key":"1426_CR8","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1007\/s10208-021-09513-z","volume":"22","author":"AS Berahas","year":"2022","unstructured":"Berahas, A.S., Cao, L., Choromanski, K., Scheinberg, K.: A theoretical and empirical comparison of gradient approximations in derivative-free optimization. Found. Comput. Math. 22, 507\u2013560 (2022)","journal-title":"Found. Comput. Math."},{"key":"1426_CR9","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1080\/10556788.2022.2142582","volume":"38","author":"AS Berahas","year":"2023","unstructured":"Berahas, A.S., Sohab, O., Vicente, L.N.: Full-low evaluation methods for derivative-free optimization. Optim. Methods Softw. 38, 386\u2013411 (2023)","journal-title":"Optim. Methods Softw."},{"key":"1426_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.probengmech.2020.103024","volume":"60","author":"A Bhaduri","year":"2020","unstructured":"Bhaduri, A., Brandyberry, D., Shields, M.D., Geubelle, P., Graham-Brady, L.: On the usefulness of gradient information in surrogate modeling: application to uncertainty propagation in composite material models. Probabilistic Eng. Mech. 60, 103024 (2020)","journal-title":"Probabilistic Eng. Mech."},{"key":"1426_CR11","unstructured":"Bingham, G., Miikkulainen, R.: Discovering parametric activation functions. Print at arXiv:2006.03179 (2020)"},{"key":"1426_CR12","first-page":"1","volume":"17","author":"AJ Booker","year":"1998","unstructured":"Booker, A.J., Dennis, J.E., Jr., Frank, P.D., Serafini, D.B., Torczon, V., Trosset, M.W.: A rigorous framework for optimization of expensive functions by surrogates. Struct. Multidiscipl. Optim. 17, 1\u201313 (1998)","journal-title":"Struct. Multidiscipl. Optim."},{"key":"1426_CR13","doi-asserted-by":"crossref","unstructured":"Boresta, M., Giovannelli, T., Roma, M.: Managing low-acuity patients in an emergency department through simulation-based multiobjective optimization using a neural network metamodel. Health Care Manag. Sci. 6: 1\u201321 (2024)","DOI":"10.1007\/s10729-024-09678-3"},{"key":"1426_CR14","series-title":"Cambridge Monographs on Applied and Computational Mathematics","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511543241","volume-title":"Radial Basis Functions: Theory and Implementations","author":"MD Buhmann","year":"2003","unstructured":"Buhmann, M.D.: Radial Basis Functions: Theory and Implementations. Cambridge Monographs on Applied and Computational Mathematics, Cambridge University Press, Cambridge (2003)"},{"key":"1426_CR15","unstructured":"Chen, Y., Hoffman, M.W., Gomez Colmenarejo, S., Denil, M., Lillicrap, T.P., Botvinick, M., de Freitas N.: Learning to learn without gradient descent by gradient descent. Preprint at arXiv:1611.03824 (2016)"},{"key":"1426_CR16","unstructured":"Clevert, D., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). Preprint at arXiv:1511.07289 (2015)"},{"key":"1426_CR17","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/978-1-4899-0289-4_3","volume-title":"Nonlinear Optimization and Applications","author":"AR Conn","year":"1996","unstructured":"Conn, A.R., Toint, Ph.L.: An algorithm using quadratic interpolation for unconstrained derivative free optimization. In: Di Pillo, G., Gianessi, F. (eds.) Nonlinear Optimization and Applications, pp. 27\u201347. Plenum Publishing, New York (1996)"},{"key":"1426_CR18","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1093\/imanum\/drn046","volume":"28","author":"AR Conn","year":"2008","unstructured":"Conn, A.R., Scheinberg, K., Vicente, L.N.: Geometry of sample sets in derivative free optimization: polynomial regression and underdetermined interpolation. IMA J. Numer. Anal. 28, 721\u2013748 (2008)","journal-title":"IMA J. Numer. Anal."},{"key":"1426_CR19","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/s10107-006-0073-5","volume":"111","author":"AR Conn","year":"2008","unstructured":"Conn, A.R., Scheinberg, K., Vicente, L.N.: Geometry of interpolation sets in derivative-free optimization. Math. Program. 111, 141\u2013172 (2008)","journal-title":"Math. Program."},{"key":"1426_CR20","series-title":"MPS\/SIAM Book Series on Optimization","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718768","volume-title":"Introduction to Derivative-Free Optimization","author":"AR Conn","year":"2009","unstructured":"Conn, A.R., Scheinberg, K., Vicente, L.N.: Introduction to Derivative-Free Optimization. MPS\/SIAM Book Series on Optimization, SIAM, Philadelphia (2009)"},{"key":"1426_CR21","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1137\/060673424","volume":"20","author":"AR Conn","year":"2009","unstructured":"Conn, A.R., Scheinberg, K., Vicente, L.N.: Global convergence of general derivative-free trust-region algorithms to first- and second-order critical points. SIAM J. Optim. 20, 387\u2013415 (2009)","journal-title":"SIAM J. Optim."},{"key":"1426_CR22","doi-asserted-by":"crossref","unstructured":"Cust\u00f3dio, A.L., Scheinberg, K., Vicente, L. N.: Chapter 37: methodologies and software for derivative-free optimization. In: Advances and Trends in Optimization with Engineering Applications, pp. 495\u2013506. SIAM (2017)","DOI":"10.1137\/1.9781611974683.ch37"},{"key":"1426_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s101070100263","volume":"91","author":"ED Dolan","year":"2002","unstructured":"Dolan, E.D., Mor\u00e9, J.J.: Benchmarking optimization software with performance profiles. Math. Program. 91, 1 (2002)","journal-title":"Math. Program."},{"key":"1426_CR24","volume-title":"Advances in Neural Information Processing Systems","author":"C Dugas","year":"2000","unstructured":"Dugas, C., Bengio, Y., B\u00e9lisle, F., Nadeau, C., Garcia, R.: Incorporating second-order functional knowledge for better option pricing. In: Leen, T., Dietterich, T., Tresp, V. (eds.) Advances in Neural Information Processing Systems, vol. 13. MIT Press (2000)"},{"key":"1426_CR25","doi-asserted-by":"crossref","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Preprint at arXiv:1702.03118 (2017)","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"1426_CR26","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1080\/10556780802409296","volume":"24","author":"G Fasano","year":"2009","unstructured":"Fasano, G., Morales, J.L., Nocedal, J.: On the geometry phase in model-based algorithms for derivative-free optimization. Optim. Methods Softw. 24, 145\u2013154 (2009)","journal-title":"Optim. Methods Softw."},{"key":"1426_CR27","doi-asserted-by":"publisher","first-page":"959","DOI":"10.1137\/130940037","volume":"24","author":"G Fasano","year":"2014","unstructured":"Fasano, G., Liuzzi, G., Lucidi, S., Rinaldi, F.: A linesearch-based derivative-free approach for nonsmooth constrained optimization. SIAM J. Optim. 24, 959\u2013992 (2014)","journal-title":"SIAM J. Optim."},{"key":"1426_CR28","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/s10589-022-00363-1","volume":"82","author":"T Giovannelli","year":"2022","unstructured":"Giovannelli, T., Liuzzi, G., Lucidi, S., Rinaldi, F.: Derivative-free methods for mixed-integer nonsmooth constrained optimization. Comput. Optim. Appl. 82, 293\u2013327 (2022)","journal-title":"Comput. Optim. Appl."},{"key":"1426_CR29","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Gordon, G., Dunson, D., Dud\u00edk, M. (eds), Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, volume 15 of Proceedings of Machine Learning Research, pp. 315\u2013323 PMLR, Fort Lauderdale (2011)"},{"key":"1426_CR30","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256. JMLR Workshop and Conference Proceedings (2010)"},{"key":"1426_CR31","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, London (2016)"},{"key":"1426_CR32","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1007\/s10589-014-9687-3","volume":"60","author":"N Gould","year":"2015","unstructured":"Gould, N., Orban, D., Toint, P.: CUTEst: a constrained and unconstrained testing environment with safe threads for mathematical optimization. Comput. Optim. Appl. 60, 545\u2013557 (2015)","journal-title":"Comput. Optim. Appl."},{"key":"1426_CR33","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1137\/140961602","volume":"25","author":"S Gratton","year":"2015","unstructured":"Gratton, S., Royer, C.W., Vicente, L.N., Zhang, Z.: Direct search based on probabilistic descent. SIAM J. Optim. 25, 1515\u20131541 (2015)","journal-title":"SIAM J. Optim."},{"key":"1426_CR34","first-page":"1","volume":"179","author":"S Gratton","year":"2018","unstructured":"Gratton, S., Royer, C., Vicente, L.N.: A decoupled first\/second-order steps technique for nonconvex nonlinear unconstrained optimization with improved complexity bounds. Math. Program. 179, 1\u201328 (2018)","journal-title":"Math. Program."},{"key":"1426_CR35","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1023\/A:1011255519438","volume":"19","author":"H-M Gutmann","year":"2001","unstructured":"Gutmann, H.-M.: A radial basis function method for global optimization. J. Global Optim. 19, 201\u2013227 (2001)","journal-title":"J. Global Optim."},{"key":"1426_CR36","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun. J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. Preprint at arXiv:1502.01852 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"1426_CR37","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun. J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"1426_CR38","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Bach, F., Blei, D. (eds), Proceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings of Machine Learning Research, pp. 448\u2013456. PMLR, Lille (2015)"},{"key":"1426_CR39","unstructured":"Jagtap, A.D., Karniadakis, G.E.: How important are activation functions in regression and classification? A survey, performance comparison, and future directions. Preprint at arXiv:2209.02681 (2022)"},{"key":"1426_CR40","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.icte.2021.12.012","volume":"9","author":"I Jahan","year":"2023","unstructured":"Jahan, I., Ahmed, M.F., Ali, M.O., Jang, Y.M.: Self-gated rectified linear unit for performance improvement of deep neural networks. ICT Express 9, 320\u2013325 (2023)","journal-title":"ICT Express"},{"key":"1426_CR41","doi-asserted-by":"crossref","unstructured":"Jarrett, K., Kavukcuoglu, K., Ranzato, M., LeCun, Y.: What is the best multi-stage architecture for object recognition? In: 2009 IEEE 12th International Conference on Computer Vision, pp. 2146\u20132153 (2009)","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"1426_CR42","doi-asserted-by":"crossref","unstructured":"Kalman, B.L., Kwasny, S.C.: Why tanh: Choosing a sigmoidal function. In: [Proceedings 1992] IJCNN International Joint Conference on Neural Networks, vol. 4, pp. 578\u2013581 (1992)","DOI":"10.1109\/IJCNN.1992.227257"},{"key":"1426_CR43","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. Preprint at arXiv:1412.6980 (2014)"},{"key":"1426_CR44","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1137\/S003614450242889","volume":"45","author":"TG Kolda","year":"2003","unstructured":"Kolda, T.G., Lewis, R.M., Torczon, V.: Optimization by direct search: new perspectives on some classical and modern methods. SIAM Rev. 45, 385\u2013482 (2003)","journal-title":"SIAM Rev."},{"key":"1426_CR45","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1017\/S0962492919000060","volume":"28","author":"J Larson","year":"2019","unstructured":"Larson, J., Menickelly, M., Wild, S.M.: Derivative-free optimization methods. Acta Numer. 28, 287\u2013404 (2019)","journal-title":"Acta Numer."},{"key":"1426_CR46","doi-asserted-by":"publisher","first-page":"3012","DOI":"10.1137\/19M125772X","volume":"29","author":"G Liuzzi","year":"2019","unstructured":"Liuzzi, G., Lucidi, S., Rinaldi, F., Vicente, L.N.: Trust-region methods for the derivative-free optimization of nonsmooth black-box functions. SIAM J. Optim. 29, 3012\u20133035 (2019)","journal-title":"SIAM J. Optim."},{"key":"1426_CR47","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.4208\/cicp.OA-2020-0165","volume":"28","author":"L Lu","year":"2020","unstructured":"Lu, L.: Dying ReLU and initialization: theory and numerical examples. Commun. Comput. Phys. 28, 1671\u20131706 (2020)","journal-title":"Commun. Comput. Phys."},{"key":"1426_CR48","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1137\/S1052623497330392","volume":"13","author":"S Lucidi","year":"2002","unstructured":"Lucidi, S., Sciandrone, M.: On the global convergence of derivative-free methods for unconstrained optimization. SIAM J. Optim. 13, 97\u2013116 (2002)","journal-title":"SIAM J. Optim."},{"key":"1426_CR49","unstructured":"Maas, A.L. Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of ICML, vol. 30, p. 3 (2013)"},{"key":"1426_CR50","doi-asserted-by":"crossref","unstructured":"Manessi, F., Rozza, A.: Learning combinations of activation functions. Preprint at arXiv:1801.09403 (2018)","DOI":"10.1109\/ICPR.2018.8545362"},{"key":"1426_CR51","doi-asserted-by":"publisher","first-page":"2095","DOI":"10.1016\/j.apm.2006.08.008","volume":"31","author":"DB McDonald","year":"2007","unstructured":"McDonald, D.B., Grantham, W.J., Tabor, W.L., Murphy, M.J.: Global and local optimization using radial basis function response surface models. Appl. Math. Model. 31, 2095\u20132110 (2007)","journal-title":"Appl. Math. Model."},{"key":"1426_CR52","first-page":"10","volume":"142","author":"MC Messner","year":"2019","unstructured":"Messner, M.C.: Convolutional neural network surrogate models for the mechanical properties of periodic structures. J. Mech. Des. 142, 10 (2019)","journal-title":"J. Mech. Des."},{"key":"1426_CR53","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1137\/080724083","volume":"20","author":"JJ Mor\u00e9","year":"2009","unstructured":"Mor\u00e9, J.J., Wild, S.M.: Benchmarking derivative-free optimization algorithms. SIAM J. Optim. 20, 172\u2013191 (2009)","journal-title":"SIAM J. Optim."},{"key":"1426_CR54","doi-asserted-by":"publisher","first-page":"1292","DOI":"10.1137\/100786125","volume":"33","author":"JJ Mor\u00e9","year":"2011","unstructured":"Mor\u00e9, J.J., Wild, S.M.: Estimating computational noise. SIAM J. Sci. Comput. 33, 1292\u20131314 (2011)","journal-title":"SIAM J. Sci. Comput."},{"key":"1426_CR55","doi-asserted-by":"crossref","unstructured":"Mor\u00e9, J.J., Wild, S.M.: Estimating derivatives of noisy simulations. ACM Transactions on Mathematical Software (2012)","DOI":"10.1145\/2168773.2168777"},{"key":"1426_CR56","volume-title":"Numerical Optimization","author":"J Nocedal","year":"2006","unstructured":"Nocedal, J., Wright, S.J.: Numerical Optimization, 2nd edn. Springer-Verlag, Berlin (2006)","edition":"2"},{"key":"1426_CR57","doi-asserted-by":"publisher","first-page":"3483","DOI":"10.1016\/j.egypro.2014.11.377","volume":"63","author":"I Pan","year":"2014","unstructured":"Pan, I., Babaei, M., Korre, A., Durucan, S.: Artificial neural network based surrogate modelling for multi-objective optimisation of geological CO$$_{2}$$ storage operations. Energy Procedia 63, 3483\u20133491 (2014)","journal-title":"Energy Procedia"},{"key":"1426_CR58","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/j.cma.2017.09.010","volume":"328","author":"V Papadopoulos","year":"2018","unstructured":"Papadopoulos, V., Soimiris, G., Giovanis, D.G., Papadrakakis, M.: A neural network-based surrogate model for carbon nanotubes with geometric nonlinearities. Comput. Methods Appl. Mech. Eng. 328, 411\u2013430 (2018)","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"1426_CR59","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., Chintala, S.: Pytorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32, 8024\u20138035 (2019)"},{"key":"1426_CR60","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1080\/10556780108805839","volume":"16","author":"MJD Powell","year":"2001","unstructured":"Powell, M.J.D.: On the Lagrange functions of quadratic models that are defined by interpolation. Optim. Methods Softw. 16, 289\u2013309 (2001)","journal-title":"Optim. Methods Softw."},{"key":"1426_CR61","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1007\/s101070100290","volume":"92","author":"MJD Powell","year":"2002","unstructured":"Powell, M.J.D.: UOBYQA: unconstrained optimization by quadratic approximation. Math. Program. 92, 555\u2013582 (2002)","journal-title":"Math. Program."},{"key":"1426_CR62","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s10107-003-0490-7","volume":"100","author":"MJD Powell","year":"2004","unstructured":"Powell, M.J.D.: Least Frobenius norm updating of quadratic models that satisfy interpolation conditions. Math. Program. 100, 183\u2013215 (2004)","journal-title":"Math. Program."},{"key":"1426_CR63","unstructured":"Powell, M.J.D.: The NEWUOA software for unconstrained optimization without derivatives. Technical Report DAMTP 2004\/NA08, Department of Applied Mathematics and Theoretical Physics, University of Cambridge (2004b)"},{"key":"1426_CR64","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1093\/jxb\/10.2.290","volume":"10","author":"FJ Richards","year":"1959","unstructured":"Richards, F.J.: A flexible growth function for empirical use. J. Exp. Bot. 10, 290\u2013301 (1959)","journal-title":"J. Exp. Bot."},{"key":"1426_CR65","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1037\/h0042519","volume":"65","author":"F Rosenblatt","year":"1958","unstructured":"Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65, 386\u2013408 (1958)","journal-title":"Psychol. Rev."},{"key":"1426_CR66","unstructured":"Ruan, Y., Xiong, Y., Reddi, S., Kumar, S., Hsieh C.: Learning to learn by zeroth-order oracle. Preprint at arXiv:1910.09464 (2019)"},{"key":"1426_CR67","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533\u2013536 (1986)","journal-title":"Nature"},{"key":"1426_CR68","unstructured":"Scardapane, S., Scarpiniti, M., Comminiello, D., Uncini, A.: Learning activation functions from data using cubic spline interpolation. Preprint at arXiv:1605.05509 (2016)"},{"key":"1426_CR69","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1080\/10556788.2022.2121832","volume":"38","author":"HJM Shi","year":"2023","unstructured":"Shi, H.J.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":"1426_CR70","doi-asserted-by":"publisher","first-page":"03","DOI":"10.1007\/s12289-023-01744-5","volume":"16","author":"K Slimani","year":"2023","unstructured":"Slimani, K., Zaaf, M., Balan, T.: Accurate surrogate models for the flat rolling process. Int. J. Mater. Form. 16, 03 (2023)","journal-title":"Int. J. Mater. Form."},{"key":"1426_CR71","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2021.102403","volume":"114","author":"JV Soares do Amaral","year":"2022","unstructured":"Soares do Amaral, J.V., Barra Montevechi, J.A., de Carvalho Miranda, R., de Sousa, W.T.: Metamodel-based simulation optimization: a systematic literature review. Simul. Model. Pract. Theory 114, 102403 (2022)","journal-title":"Simul. Model. Pract. Theory"},{"key":"1426_CR72","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1137\/S1052623493250780","volume":"7","author":"V Torczon","year":"1997","unstructured":"Torczon, V.: On the convergence of pattern search algorithms. SIAM J. Optim. 7, 1\u201325 (1997)","journal-title":"SIAM J. Optim."},{"key":"1426_CR73","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s10107-010-0429-8","volume":"133","author":"LN Vicente","year":"2012","unstructured":"Vicente, L.N., Cust\u00f3dio, A.L.: Analysis of direct searches for discontinuous functions. Math. Program. 133, 299\u2013325 (2012)","journal-title":"Math. Program."},{"key":"1426_CR74","doi-asserted-by":"publisher","first-page":"3197","DOI":"10.1137\/070691814","volume":"30","author":"SM Wild","year":"2008","unstructured":"Wild, S.M., Regis, R.G., Shoemaker, C.A.: ORBIT: optimization by radial basis function interpolation in trust-regions. SIAM J. Sci. Comput. 30, 3197\u20133219 (2008)","journal-title":"SIAM J. Sci. Comput."},{"key":"1426_CR75","unstructured":"Winfield, D.: Function and Functional Optimization by Interpolation in Data Tables. PhD thesis, Harvard University (1969)"},{"key":"1426_CR76","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1093\/imamat\/12.3.339","volume":"12","author":"D Winfield","year":"1973","unstructured":"Winfield, D.: Function minimization by interpolation in a data set. J. Inst. Math. Appl. 12, 339\u2013347 (1973)","journal-title":"J. Inst. Math. Appl."},{"key":"1426_CR77","unstructured":"Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. Preprint at arXiv:1505.00853 (2015)"},{"key":"1426_CR78","doi-asserted-by":"publisher","first-page":"18757","DOI":"10.1038\/s41598-021-96723-8","volume":"11","author":"B Yuen","year":"2021","unstructured":"Yuen, B., Hoang, M.T., Dong, X., Lu, T.: Universal activation function for machine learning. Sci. Rep. 11, 18757 (2021)","journal-title":"Sci. Rep."},{"key":"1426_CR79","doi-asserted-by":"crossref","unstructured":"Zaborski, M., Ma\u0144dziuk, J.: LQ-R-SHADE: R-SHADE with quadratic surrogate model. In: Artificial Intelligence and Soft Computing: 21st International Conference, ICAISC 2022, Zakopane, Proceedings, Part I, pp. 265\u2013276. Springer-Verlag, Berlin (2023)","DOI":"10.1007\/978-3-031-23492-7_23"},{"key":"1426_CR80","doi-asserted-by":"crossref","unstructured":"Zheng, H., Yang, Z., Liu, W., Liang, J., Li, Y.: Improving deep neural networks using softplus units. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20134 (2015)","DOI":"10.1109\/IJCNN.2015.7280459"}],"container-title":["Journal of Global Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10898-024-01426-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10898-024-01426-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10898-024-01426-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T12:02:22Z","timestamp":1774526542000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10898-024-01426-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,9]]},"references-count":80,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["1426"],"URL":"https:\/\/doi.org\/10.1007\/s10898-024-01426-9","relation":{},"ISSN":["0925-5001","1573-2916"],"issn-type":[{"value":"0925-5001","type":"print"},{"value":"1573-2916","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,9]]},"assertion":[{"value":"20 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 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"}}]}}