{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T07:55:49Z","timestamp":1770710149428,"version":"3.49.0"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T00:00:00Z","timestamp":1661472000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T00:00:00Z","timestamp":1661472000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/V049038\/1"],"award-info":[{"award-number":["EP\/V049038\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/N510129\/1"],"award-info":[{"award-number":["EP\/N510129\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Math Meth Oper Res"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Support vector classification (SVC) is a classical and well-performed learning method for classification problems. A regularization parameter, which significantly affects the classification performance, has to be chosen and this is usually done by the cross-validation procedure. In this paper, we reformulate the hyperparameter selection problem for support vector classification as a bilevel optimization problem in which the upper-level problem minimizes the average number of misclassified data points over all the cross-validation folds, and the lower-level problems are the <jats:inline-formula><jats:alternatives><jats:tex-math>$$l_1$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:msub>\n                    <mml:mi>l<\/mml:mi>\n                    <mml:mn>1<\/mml:mn>\n                  <\/mml:msub>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula>-loss SVC problems, with each one for each fold in T-fold cross-validation. The resulting bilevel optimization model is then converted to a mathematical program with equilibrium constraints (MPEC). To solve this MPEC, we propose a global relaxation cross-validation algorithm (GR\u2013CV) based on the well-know Sholtes-type global relaxation method (GRM). It is proven to converge to a C-stationary point. Moreover, we prove that the MPEC-tailored version of the Mangasarian\u2013Fromovitz constraint qualification (MFCQ), which is a key property to guarantee the convergence of the GRM, automatically holds at each feasible point of this MPEC. Extensive numerical results verify the efficiency of the proposed approach. In particular, compared with other methods, our algorithm enjoys superior generalization performance over almost all the data sets used in this paper.<\/jats:p>","DOI":"10.1007\/s00186-022-00798-6","type":"journal-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T18:03:54Z","timestamp":1661537034000},"page":"315-350","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Bilevel hyperparameter optimization for support vector classification: theoretical analysis and a solution method"],"prefix":"10.1007","volume":"96","author":[{"given":"Qingna","family":"Li","sequence":"first","affiliation":[]},{"given":"Zhen","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1265-4178","authenticated-orcid":false,"given":"Alain","family":"Zemkoho","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,8,26]]},"reference":[{"key":"798_CR1","unstructured":"Anitescu M (2000) On solving mathematical programs with complementarity constraints as nonlinear programs. Preprint ANL\/MCS-P$$864$$-$$1200$$, Argonne National Laboratory, Argonne, IL 3"},{"key":"798_CR2","doi-asserted-by":"crossref","unstructured":"Bennett KP, Hu J, Ji XY, Kunapuli G, Pang J-S (2006) Model selection via bilevel optimization. In: The 2006 IEEE International Joint Conference on Neural Network Proceedings, pp 1922\u20131929 . IEEE","DOI":"10.1109\/IJCNN.2006.246935"},{"key":"798_CR3","doi-asserted-by":"crossref","unstructured":"Bennett KP, Kunapuli G, Hu J, Pang J-S (2008) Bilevel optimization and machine learning. In: IEEE World Congress on Computational Intelligence, pp 25\u201347","DOI":"10.1007\/978-3-540-68860-0_2"},{"issue":"1","key":"798_CR4","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1023\/A:1012450327387","volume":"46","author":"O Chapelle","year":"2002","unstructured":"Chapelle O, Vapnik V, Bousquet O, Mukherjee S (2002) Choosing multiple parameters for support vector machines. Mach Learn 46(1):131\u2013159","journal-title":"Mach Learn"},{"issue":"2","key":"798_CR5","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1007\/s10462-018-9614-6","volume":"52","author":"VK Chauhan","year":"2019","unstructured":"Chauhan VK, Dahiya K, Sharma A (2019) Problem formulations and solvers in linear SVM: a review. Artif Intell Rev 52(2):803\u2013855","journal-title":"Artif Intell Rev"},{"issue":"1","key":"798_CR6","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1007\/s10479-007-0176-2","volume":"153","author":"B Colson","year":"2007","unstructured":"Colson B, Marcotte P, Savard G (2007) An overview of bilevel optimization. Ann Oper Res 153(1):235\u2013256","journal-title":"Ann Oper Res"},{"issue":"3","key":"798_CR7","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273\u2013297","journal-title":"Mach Learn"},{"key":"798_CR8","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/j.neucom.2014.11.025","volume":"153","author":"N Couellan","year":"2015","unstructured":"Couellan N, Wang WJ (2015) Bi-level stochastic gradient for large scale support vector machine. Neurocomputing 153:300\u2013308","journal-title":"Neurocomputing"},{"key":"798_CR9","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511801389","volume-title":"An Introduction to Support Vector Machines and Other Kernel-based Learning Methods","author":"N Cristianini","year":"2000","unstructured":"Cristianini N, Shawe-Taylor J (2000) An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge University Press, Cambridge"},{"key":"798_CR10","doi-asserted-by":"crossref","unstructured":"Crockett C, Fessler JA (2021) Bilevel methods for image reconstruction. arXiv preprint arXiv:2109.09610","DOI":"10.1561\/9781638280033"},{"key":"798_CR11","volume-title":"Foundations of Bilevel Programming","author":"S Dempe","year":"2002","unstructured":"Dempe S (2002) Foundations of Bilevel Programming. Springer, New York"},{"issue":"3","key":"798_CR12","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1080\/0233193031000149894","volume":"52","author":"S Dempe","year":"2003","unstructured":"Dempe S (2003) Annotated bibliography on bilevel programming and mathematical programs with equilibrium constraints. Optimization 52(3):333\u2013359","journal-title":"Optimization"},{"issue":"3","key":"798_CR13","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1016\/j.na.2011.05.097","volume":"75","author":"S Dempe","year":"2012","unstructured":"Dempe S, Zemkoho AB (2012) On the Karush-Kuhn-Tucker reformulation of the bilevel optimization problem. Nonlinear Analysis: Theory, Methods Appl 75(3):1202\u20131218","journal-title":"Nonlinear Analysis: Theory, Methods Appl"},{"key":"798_CR14","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-52119-6","volume-title":"Bilevel Optimization Advances and Next Challenges","author":"S Dempe","year":"2020","unstructured":"Dempe S, Zemkoho AB (2020) Bilevel Optimization Advances and Next Challenges. Springer, New York"},{"key":"798_CR15","doi-asserted-by":"crossref","unstructured":"Dong Y-L, Xia Z-Q, Wang M-Z (2007) An MPEC model for selecting optimal parameter in support vector machines. In: The First International Symposium on Optimization and Systems Biology, pp 351\u2013357","DOI":"10.1109\/ICMLA.2007.38"},{"key":"798_CR16","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/S0925-2312(02)00601-X","volume":"51","author":"KB Duan","year":"2003","unstructured":"Duan KB, Keerthi SS, Poo AN (2003) Evaluation of simple performance measures for tuning SVM hyperparameters. Neurocomputing 51:41\u201359","journal-title":"Neurocomputing"},{"key":"798_CR17","volume-title":"Finite-dimensional Variational Inequalities and Complementarity Problems","author":"F Facchinei","year":"2007","unstructured":"Facchinei F, Pang J-S (2007) Finite-dimensional Variational Inequalities and Complementarity Problems. Springer, NewYork"},{"key":"798_CR18","doi-asserted-by":"crossref","unstructured":"Fischer A, Zemkoho AB, Zhou S (2021) Semismooth Newton-type method for bilevel optimization: global convergence and extensive numerical experiments. Optimization Methods & Software, 1\u201335","DOI":"10.1080\/10556788.2021.1977810"},{"key":"798_CR19","doi-asserted-by":"crossref","unstructured":"Flegel ML (2005) Constraint qualifications and stationarity concepts for mathematical programs with equilibrium constraints. PhD thesis, Universit\u00e4t W\u00fcrzburg","DOI":"10.1080\/02331930500342591"},{"issue":"1","key":"798_CR20","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1137\/S1052623402407382","volume":"17","author":"R Fletcher","year":"2006","unstructured":"Fletcher R, Leyffer S, Ralph D, Scholtes S (2006) Local convergence of SQP methods for mathematical programs with equilibrium constraints. SIAM J Optim 17(1):259\u2013286","journal-title":"SIAM J Optim"},{"issue":"3","key":"798_CR21","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1137\/S1052623499363232","volume":"12","author":"M Fukushima","year":"2002","unstructured":"Fukushima M, Tseng P (2002) An implementable active-set algorithm for computing a B-stationary point of a mathematical program with linear complementarity constraints. SIAM J Optim 12(3):724\u2013739","journal-title":"SIAM J Optim"},{"key":"798_CR22","doi-asserted-by":"crossref","unstructured":"Galli L, Lin C-J (2021) A study on truncated newton methods for linear classification. IEEE Transactions on Neural Networks and Learning Systems","DOI":"10.1109\/TNNLS.2020.3045836"},{"key":"798_CR23","volume-title":"User\u2019s Guide for Snopt version 6","author":"PE Gill","year":"2002","unstructured":"Gill PE, Murray W, Saunders MA (2002) User\u2019s Guide for Snopt version 6. A Fortran Package for Large-Scale Nonlinear Programming. University of California, California"},{"issue":"1","key":"798_CR24","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/s10957-014-0699-z","volume":"166","author":"L Guo","year":"2015","unstructured":"Guo L, Lin G-H, Ye JJ (2015) Solving mathematical programs with equilibrium constraints. J Optim Theory Appl 166(1):234\u2013256","journal-title":"J Optim Theory Appl"},{"issue":"2","key":"798_CR25","doi-asserted-by":"crossref","first-page":"1459","DOI":"10.1137\/20M1321413","volume":"31","author":"F Harder","year":"2021","unstructured":"Harder F, Mehlitz P, Wachsmuth G (2021) Reformulation of the M-stationarity conditions as a system of discontinuous equations and its solution by a semismooth Newton method. SIAM J Optim 31(2):1459\u20131488","journal-title":"SIAM J Optim"},{"issue":"1","key":"798_CR26","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1007\/s10107-011-0488-5","volume":"137","author":"T Hoheisel","year":"2013","unstructured":"Hoheisel T, Kanzow C, Schwartz A (2013) Theoretical and numerical comparison of relaxation methods for mathematical programs with complementarity constraints. Math Program 137(1):257\u2013288","journal-title":"Math Program"},{"key":"798_CR27","doi-asserted-by":"crossref","unstructured":"Hsieh C-J, Chang K-W, Lin C-J, Keerthi SS, Sundararajan S (2008) A dual coordinate descent method for large-scale linear SVM. In Proceedings of the 25th International Conference on Machine Learning, pp 408\u2013415","DOI":"10.1145\/1390156.1390208"},{"issue":"5","key":"798_CR28","doi-asserted-by":"crossref","first-page":"984","DOI":"10.1109\/TPAMI.2013.178","volume":"36","author":"X Huang","year":"2013","unstructured":"Huang X, Shi L, Suykens JA (2013) Support vector machine classifier with pinball loss. IEEE Trans Pattern Anal Mach Intell 36(5):984\u2013997","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"798_CR29","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/s10107-017-1208-6","volume":"169","author":"F Jara-Moroni","year":"2018","unstructured":"Jara-Moroni F, Pang J-S, W\u00e4chter A (2018) A study of the difference-of-convex approach for solving linear programs with complementarity constraints. Math Program 169(1):221\u2013254","journal-title":"Math Program"},{"issue":"1","key":"798_CR30","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s11750-011-0228-2","volume":"20","author":"JJ J\u00fadice","year":"2012","unstructured":"J\u00fadice JJ (2012) Algorithms for linear programming with linear complementarity constraints. TOP 20(1):4\u201325","journal-title":"TOP"},{"key":"798_CR31","unstructured":"Keerthi S, Sindhwani V, Chapelle O (2006) An efficient method for gradient-based adaptation of hyperparameters in SVM models. Advances in neural information processing systems 19"},{"key":"798_CR32","volume-title":"A Bilevel Optimization Approach to Machine Learning","author":"G Kunapuli","year":"2008","unstructured":"Kunapuli G (2008) A Bilevel Optimization Approach to Machine Learning. Rensselaer Polytechnic Institute, New York"},{"issue":"4","key":"798_CR33","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1080\/10556780802102586","volume":"23","author":"G Kunapuli","year":"2008","unstructured":"Kunapuli G, Bennett KP, Hu J, Pang J-S (2008) Classification model selection via bilevel programming. Optim Methods Softw 23(4):475\u2013489","journal-title":"Optim Methods Softw"},{"key":"798_CR34","first-page":"129","volume":"45","author":"G Kunapuli","year":"2008","unstructured":"Kunapuli G, Bennett KP, Hu J, Pang J-S (2008) Bilevel model selection for support vector machines. Data mining mathe programming 45:129\u2013158","journal-title":"Data mining mathe programming"},{"issue":"2","key":"798_CR35","doi-asserted-by":"crossref","first-page":"938","DOI":"10.1137\/120882706","volume":"6","author":"K Kunisch","year":"2013","unstructured":"Kunisch K, Pock T (2013) A bilevel optimization approach for parameter learning in variational models. SIAM J Imag Sci 6(2):938\u2013983","journal-title":"SIAM J Imag Sci"},{"issue":"3","key":"798_CR36","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s13675-015-0041-z","volume":"3","author":"Y-C Lee","year":"2015","unstructured":"Lee Y-C, Pang J-S, Mitchell JE (2015) Global resolution of the support vector machine regression parameters selection problem with LPCC. EURO J Comput Optim 3(3):197\u2013261","journal-title":"EURO J Comput Optim"},{"key":"798_CR37","first-page":"885","volume":"269","author":"JL Li","year":"2015","unstructured":"Li JL, Huang RS, Jian JB (2015) A superlinearly convergent QP-free algorithm for mathematical programs with equilibrium constraints. Appl Math Comput 269:885\u2013903","journal-title":"Appl Math Comput"},{"issue":"1","key":"798_CR38","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1007\/s10107-013-0633-4","volume":"144","author":"G-H Lin","year":"2014","unstructured":"Lin G-H, Xu MW, Ye JJ (2014) On solving simple bilevel programs with a nonconvex lower level program. Math Program 144(1):277\u2013305","journal-title":"Math Program"},{"issue":"1","key":"798_CR39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s13721-015-0108-z","volume":"5","author":"G Luo","year":"2016","unstructured":"Luo G (2016) A review of automatic selection methods for machine learning algorithms and hyper-parameter values. Netw Model Anal Health Inform Bioinform 5(1):1\u201316","journal-title":"Netw Model Anal Health Inform Bioinform"},{"key":"798_CR40","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511983658","volume-title":"Mathematical Programs with Equilibrium Constraints","author":"Z-Q Luo","year":"1996","unstructured":"Luo Z-Q, Pang J-S, Ralph D (1996) Mathematical Programs with Equilibrium Constraints. Cambridge University Press, Cambridge"},{"issue":"4","key":"798_CR41","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/BF01096681","volume":"5","author":"OL Mangasarian","year":"1994","unstructured":"Mangasarian OL (1994) Misclassification minimization. J Global Optim 5(4):309\u2013323","journal-title":"J Global Optim"},{"key":"798_CR42","doi-asserted-by":"crossref","unstructured":"Mej\u00eda-de-Dios J-A, Mezura-Montes E (2019) A metaheuristic for bilevel optimization using tykhonov regularization and the quasi-newton method. In: 2019 IEEE Congress on Evolutionary Computation (CEC), pp 3134\u20133141","DOI":"10.1109\/CEC.2019.8790097"},{"key":"798_CR43","doi-asserted-by":"crossref","unstructured":"Momma M, Bennett KP (2002) A pattern search method for model selection of support vector regression. In: Proceedings of the 2002 SIAM International Conference on Data Mining, pp 261\u2013274","DOI":"10.1137\/1.9781611972726.16"},{"key":"798_CR44","unstructured":"Moore G, Bergeron C, Bennett KP. Gradient-type methods for primal SVM model selection"},{"key":"798_CR45","doi-asserted-by":"crossref","unstructured":"Moore G, Bergeron C, Bennett KP (2009) Nonsmooth bilevel programming for hyperparameter selection. In: 2009 IEEE International Conference on Data Mining Workshops, pp 374\u2013381","DOI":"10.1109\/ICDMW.2009.74"},{"issue":"2","key":"798_CR46","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1007\/s10851-016-0663-7","volume":"56","author":"P Ochs","year":"2016","unstructured":"Ochs P, Ranftl R, Brox T, Pock T (2016) Techniques for gradient-based bilevel optimization with non-smooth lower level problems. J Mathe Imag Vision 56(2):175\u2013194","journal-title":"J Mathe Imag Vision"},{"key":"798_CR47","doi-asserted-by":"crossref","unstructured":"Ochs P, Ranftl R, Brox T, Pock T (2015) Bilevel optimization with nonsmooth lower level problems. In: International Conference on Scale Space and Variational Methods in Computer Vision, pp 654\u2013665","DOI":"10.1007\/978-3-319-18461-6_52"},{"key":"798_CR48","unstructured":"Okuno T, Takeda A, Kawana A (2018) Hyperparameter learning for bilevel nonsmooth optimization. arXiv preprint arXiv:1806.01520"},{"issue":"4","key":"798_CR49","doi-asserted-by":"crossref","first-page":"918","DOI":"10.1137\/S1052623499361233","volume":"11","author":"S Scholtes","year":"2001","unstructured":"Scholtes S (2001) Convergence properties of a regularization scheme for mathematical programs with complementarity constraints. SIAM J Optim 11(4):918\u2013936","journal-title":"SIAM J Optim"},{"issue":"1","key":"798_CR50","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10107-010-0420-4","volume":"127","author":"S Shalev-Shwartz","year":"2011","unstructured":"Shalev-Shwartz S, Singer Y, Srebro N, Cotter A (2011) Pegasos: Primal estimated sub-gradient solver for SVM. Math Program 127(1):3\u201330","journal-title":"Math Program"},{"key":"798_CR51","volume-title":"The Nature of Statistical Learning Theory","author":"V Vapnik","year":"2013","unstructured":"Vapnik V (2013) The Nature of Statistical Learning Theory. Springer, New York"},{"key":"798_CR52","doi-asserted-by":"crossref","unstructured":"Wang H, Shao Y, Zhou S, Zhang C, Xiu N (2021) Support vector machine classifier via $${L}_{0\/1}$$ soft-margin loss. IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2021.3092177"},{"issue":"4","key":"798_CR53","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1007\/s11075-014-9922-0","volume":"69","author":"J Wu","year":"2015","unstructured":"Wu J, Zhang LW, Zhang Y (2015) An inexact Newton method for stationary points of mathematical programs constrained by parameterized quasi-variational inequalities. Numer Algorithms 69(4):713\u2013735","journal-title":"Numer Algorithms"},{"issue":"4","key":"798_CR54","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1080\/10556788.2020.1734002","volume":"35","author":"YQ Yan","year":"2020","unstructured":"Yan YQ, Li QN (2020) An efficient augmented Lagrangian method for support vector machine. Optim Methods Softw 35(4):855\u2013883","journal-title":"Optim Methods Softw"},{"issue":"1","key":"798_CR55","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1016\/j.jmaa.2004.10.032","volume":"307","author":"JJ Ye","year":"2005","unstructured":"Ye JJ (2005) Necessary and sufficient optimality conditions for mathematical programs with equilibrium constraints. J Math Anal Appl 307(1):350\u2013369","journal-title":"J Math Anal Appl"},{"issue":"4","key":"798_CR56","doi-asserted-by":"crossref","first-page":"1885","DOI":"10.1137\/080725088","volume":"20","author":"JJ Ye","year":"2010","unstructured":"Ye JJ, Zhu DL (2010) New necessary optimality conditions for bilevel programs by combining the MPEC and value function approaches. SIAM J Optim 20(4):1885\u20131905","journal-title":"SIAM J Optim"},{"issue":"2","key":"798_CR57","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1007\/s12532-018-0149-2","volume":"11","author":"B Yu","year":"2019","unstructured":"Yu B, Mitchell JE, Pang J-S (2019) Solving linear programs with complementarity constraints using branch-and-cut. Math Program Comput 11(2):267\u2013310","journal-title":"Math Program Comput"},{"key":"798_CR58","unstructured":"Yu T, Zhu H (2020) Hyper-parameter optimization: A review of algorithms and applications. arXiv preprint arXiv:2003.05689"},{"issue":"2","key":"798_CR59","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1007\/s10589-020-00250-7","volume":"78","author":"AB Zemkoho","year":"2021","unstructured":"Zemkoho AB, Zhou SL (2021) Theoretical and numerical comparison of the karush-kuhn-tucker and value function reformulations in bilevel optimization. Comput Optim Appl 78(2):625\u2013674","journal-title":"Comput Optim Appl"},{"key":"798_CR60","doi-asserted-by":"crossref","unstructured":"Zhang T (2004) Solving large scale linear prediction problems using stochastic gradient descent algorithms. In: Proceedings of the Twenty-first International Conference on Machine Learning, p 116","DOI":"10.1145\/1015330.1015332"}],"container-title":["Mathematical Methods of Operations Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00186-022-00798-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00186-022-00798-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00186-022-00798-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T02:25:37Z","timestamp":1669688737000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00186-022-00798-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,26]]},"references-count":60,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["798"],"URL":"https:\/\/doi.org\/10.1007\/s00186-022-00798-6","relation":{},"ISSN":["1432-2994","1432-5217"],"issn-type":[{"value":"1432-2994","type":"print"},{"value":"1432-5217","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,26]]},"assertion":[{"value":"13 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}