{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T14:05:02Z","timestamp":1774533902032,"version":"3.50.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,6,3]],"date-time":"2019-06-03T00:00:00Z","timestamp":1559520000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,6,3]],"date-time":"2019-06-03T00:00:00Z","timestamp":1559520000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Lomonosov Moscow State University and the Foundation","award":["13\/1251\/2018"],"award-info":[{"award-number":["13\/1251\/2018"]}]},{"name":"Government of the Russian Federation","award":["05.Y09.21.0018"],"award-info":[{"award-number":["05.Y09.21.0018"]}]},{"name":"FASIE","award":["44116"],"award-info":[{"award-number":["44116"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Ann Oper Res"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1007\/s10479-019-03286-z","type":"journal-article","created":{"date-parts":[[2019,6,3]],"date-time":"2019-06-03T10:22:37Z","timestamp":1559557357000},"page":"51-65","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Comprehensive analysis of gradient-based hyperparameter optimization algorithms"],"prefix":"10.1007","volume":"289","author":[{"given":"O. Y.","family":"Bakhteev","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"V. V.","family":"Strijov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,6,3]]},"reference":[{"key":"3286_CR1","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1214\/09-SS054","volume":"4","author":"S Arlot","year":"2010","unstructured":"Arlot, S., & Celisse, A. (2010). A survey of cross-validation procedures for model selection. Statistics Surveys, 4, 40\u201379. \nhttps:\/\/doi.org\/10.1214\/09-SS054\n\n.","journal-title":"Statistics Surveys"},{"key":"3286_CR2","unstructured":"Bakhteev, O. (2019). Pyfos: a library for hyperparameter optimization. \nhttps:\/\/git.io\/fjZks\n\n. Accessed 1 May 2019."},{"key":"3286_CR3","first-page":"1089","volume":"5","author":"Y Bengio","year":"2004","unstructured":"Bengio, Y., & Grandvalet, Y. (2004). No unbiased estimator of the variance of k-fold cross-validation. Journal of machine learning research, 5, 1089\u20131105.","journal-title":"Journal of machine learning research"},{"issue":"Feb","key":"3286_CR4","first-page":"281","volume":"13","author":"J Bergstra","year":"2012","unstructured":"Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of Machine Learning Research, 13(Feb), 281\u2013305.","journal-title":"Journal of Machine Learning Research"},{"key":"3286_CR5","doi-asserted-by":"crossref","unstructured":"Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., & Bengio, Y. (2010). Theano: A cpu and gpu math expression compiler. In Proceedings of the Python for scientific computing conference (SciPy), vol. 4","DOI":"10.25080\/Majora-92bf1922-003"},{"key":"3286_CR6","unstructured":"Bergstra, J. S., Bardenet, R., Bengio, Y., & K\u00e9gl, B. (2011). Algorithms for hyper-parameter optimization. In: J. Shawe-Taylor, R. S. Zemel, P. L. Bartlett, F. Pereira, & K. Q. Weinberger (Eds.), Advances in neural information processing systems (pp. 2546\u20132554). Granada: Curran Associates, Inc. \nhttp:\/\/papers.nips.cc\/paper\/4443-algorithms-for-hyper-parameteroptimization.pdf\n\n."},{"key":"3286_CR7","volume-title":"Pattern recognition and machine learning (information science and statistics)","author":"CM Bishop","year":"2006","unstructured":"Bishop, C. M. (2006). Pattern recognition and machine learning (information science and statistics). New York: Springer."},{"key":"3286_CR8","first-page":"318","volume":"22","author":"J Domke","year":"2012","unstructured":"Domke, J. (2012). Generic methods for optimization-based modeling. AISTATS, 22, 318\u2013326.","journal-title":"AISTATS"},{"issue":"3","key":"3286_CR9","first-page":"1043","volume":"20","author":"A Farcomeni","year":"2010","unstructured":"Farcomeni, A. (2010). Bayesian constrained variable selection. Statistica Sinica, 20(3), 1043\u20131062.","journal-title":"Statistica Sinica"},{"key":"3286_CR10","unstructured":"Fu, J., Luo, H., Feng, J., Low, K.H., & Chua, T.S. (2016). Drmad: distilling reverse-mode automatic differentiation for optimizing hyperparameters of deep neural networks. In Proceedings of the twenty-fifth international joint conference on artificial intelligence, pp. 1469\u20131475"},{"key":"3286_CR11","first-page":"2348","volume":"24","author":"A Graves","year":"2011","unstructured":"Graves, A. (2011). Practical variational inference for neural networks. Advances in Neural Information Processing Systems, 24, 2348\u20132356.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"3286_CR12","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1114.001.0001","volume-title":"Advances in minimum description length: theory and applications","author":"P Gr\u00fcnwald","year":"2005","unstructured":"Gr\u00fcnwald, P. (2005). A tutorial introduction to the minimum description length principle. In P. D. Gr\u00fcnwald, I. J. Myung, & M. A. Pitt (Eds.), Advances in minimum description length: theory and applications. Cambridge: MIT Press."},{"issue":"1","key":"3286_CR13","first-page":"1303","volume":"14","author":"MD Hoffman","year":"2013","unstructured":"Hoffman, M. D., Blei, D. M., Wang, C., & Paisley, J. (2013). Stochastic variational inference. Journal of machine learning research, 14(1), 1303\u20131347.","journal-title":"Journal of machine learning research"},{"key":"3286_CR14","doi-asserted-by":"crossref","unstructured":"Hutter, F., Hoos, H.H., & Leyton-Brown, K. (2011). Sequential model-based optimization for general algorithm configuration. In International conference on learning and intelligent optimization, pp. 507\u2013523","DOI":"10.1007\/978-3-642-25566-3_40"},{"issue":"1\u20132","key":"3286_CR15","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s10479-015-1890-9","volume":"263","author":"S Hwang","year":"2018","unstructured":"Hwang, S., & Jeong, M. K. (2018). Robust relevance vector machine for classification with variational inference. Annals of Operations Research, 263(1\u20132), 21\u201343.","journal-title":"Annals of Operations Research"},{"key":"3286_CR16","first-page":"26","volume":"1050","author":"T Karaletsos","year":"2015","unstructured":"Karaletsos, T., & R\u00e4tsch, G. (2015). Automatic relevance determination for deep generative models. Statistics, 1050, 26.","journal-title":"Statistics"},{"issue":"1","key":"3286_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1758-2946-6-10","volume":"6","author":"D Krstajic","year":"2014","unstructured":"Krstajic, D., Buturovic, L. J., Leahy, D. E., & Thomas, S. (2014). Cross-validation pitfalls when selecting and assessing regression and classification models. Journal of Cheminformatics, 6(1), 1\u201315.","journal-title":"Journal of Cheminformatics"},{"issue":"3","key":"3286_CR18","doi-asserted-by":"publisher","first-page":"607","DOI":"10.15388\/Informatica.2016.102","volume":"27","author":"M Kuznetsov","year":"2016","unstructured":"Kuznetsov, M., Tokmakova, A., & Strijov, V. (2016). Analytic and stochastic methods of structure parameter estimation. Informatica, 27(3), 607\u2013624.","journal-title":"Informatica"},{"issue":"2","key":"3286_CR19","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1145\/1964897.1964918","volume":"12","author":"JR Kwapisz","year":"2011","unstructured":"Kwapisz, J. R., Weiss, G. M., & Moore, S. A. (2011). Activity recognition using cell phone accelerometers. ACM SigKDD Explorations Newsletter, 12(2), 74\u201382.","journal-title":"ACM SigKDD Explorations Newsletter"},{"key":"3286_CR20","unstructured":"LeCun, Y. (1998). The mnist database of handwritten digits. \nhttp:\/\/yann.lecun.com\/exdb\/mnist\/\n\n. Accessed 1 May 2019."},{"key":"3286_CR21","unstructured":"Luketina, J., Berglund, M., Greff, K., & Raiko, T. (2016). Scalable gradient-based tuning of continuous regularization hyperparameters. In International conference on machine learning, pp. 2952\u20132960"},{"key":"3286_CR22","volume-title":"Information theory, inference and learning algorithms","author":"DJC MacKay","year":"2002","unstructured":"MacKay, D. J. C. (2002). Information theory, inference and learning algorithms. New York: Cambridge University Press."},{"key":"3286_CR23","unstructured":"Maclaurin, D., Duvenaud, D., & Adams, R. (2015). Gradient-based hyperparameter optimization through reversible learning. In Proceedings of the 32nd international conference on machine learning (ICML-15), pp. 2113\u20132122"},{"issue":"1-2","key":"3286_CR24","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s10479-018-2947-3","volume":"282","author":"Peter Nystrup","year":"2018","unstructured":"Nystrup, P., Boyd, S., Lindstr\u00f6m, E., & Madsen, H. (2018). Multi-period portfolio selection with drawdown control. Annals of Operations Research. \nhttps:\/\/doi.org\/10.1007\/s10479-018-2947-3\n\n.","journal-title":"Annals of Operations Research"},{"key":"3286_CR25","unstructured":"Oliphant, T.E. (2006). A guide to NumPy, vol.\u00a01. Trelgol Publishing USA"},{"key":"3286_CR26","unstructured":"Pedregosa, F. (2016). Hyperparameter optimization with approximate gradient. In Proceedings of the 33rd international conference on international conference on machine learning, vol. 48, pp. 737\u2013746"},{"key":"3286_CR27","first-page":"412","volume":"2","author":"R Salakhutdinov","year":"2007","unstructured":"Salakhutdinov, R., & Hinton, G. (2007). Learning a nonlinear embedding by preserving class neighbourhood structure. Journal of Machine Learning Research Proceedings Track, 2, 412\u2013419.","journal-title":"Journal of Machine Learning Research Proceedings Track"},{"key":"3286_CR28","first-page":"1218","volume":"37","author":"T Salimans","year":"2015","unstructured":"Salimans, T., Kingma, D. P., & Welling, M. (2015). Markov chain monte carlo and variational inference: Bridging the gap. ICML, 37, 1218\u20131226.","journal-title":"ICML"},{"key":"3286_CR29","unstructured":"Snoek, J., Rippel, O., Swersky, K., Kiros, R., Satish, N., Sundaram, N., Patwary, M.M.A., Prabhat, M., & Adams, R.P. (2015). Scalable bayesian optimization using deep neural networks. In: ICML, pp. 2171\u20132180"},{"key":"3286_CR30","unstructured":"Strijov, V.V. (2014). Model genetation and selection for regression and classification problems (dsc thesis)"},{"key":"3286_CR31","unstructured":"Sutskever, I., Vinyals, O., & Le, Q.V. (2014). Sequence to sequence learning with neural networks. In Advances in neural information processing systems 27: Annual conference on neural information processing systems 2014, December 8-13 2014, Montreal, Quebec, pp. 3104\u20133112"},{"key":"3286_CR32","doi-asserted-by":"crossref","unstructured":"Vishnu, A., Narasimhan, J., Holder, L., Kerbyson, D.J., & Hoisie, A. (2015). Fast and accurate support vector machines on large scale systems. In 2015 IEEE international conference on cluster computing, CLUSTER 2015, Chicago, IL, September 8\u201311, 2015, pp. 110\u2013119","DOI":"10.1109\/CLUSTER.2015.26"}],"container-title":["Annals of Operations Research"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10479-019-03286-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10479-019-03286-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10479-019-03286-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,6,2]],"date-time":"2020-06-02T01:26:49Z","timestamp":1591061209000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10479-019-03286-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,3]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["3286"],"URL":"https:\/\/doi.org\/10.1007\/s10479-019-03286-z","relation":{},"ISSN":["0254-5330","1572-9338"],"issn-type":[{"value":"0254-5330","type":"print"},{"value":"1572-9338","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,3]]},"assertion":[{"value":"3 June 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}