{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T07:23:10Z","timestamp":1774941790320,"version":"3.50.1"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030053178","type":"print"},{"value":"9783030053185","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-05318-5_7","type":"book-chapter","created":{"date-parts":[[2019,5,17]],"date-time":"2019-05-17T17:44:23Z","timestamp":1558115063000},"page":"135-149","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["Towards Automatically-Tuned Deep Neural Networks"],"prefix":"10.1007","author":[{"given":"Hector","family":"Mendoza","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron","family":"Klein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Feurer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jost Tobias","family":"Springenberg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Urban","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Burkart","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maximilian","family":"Dippel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marius","family":"Lindauer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank","family":"Hutter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,18]]},"reference":[{"key":"7_CR1","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., Wicke, M., Yu, Y., Zheng, X.: Tensorflow: A system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16). pp. 265\u2013283 (2016), https:\/\/www.usenix.org\/system\/files\/conference\/osdi16\/osdi16-abadi.pdf"},{"key":"7_CR2","unstructured":"Bergstra, J., Bardenet, R., Bengio, Y., K\u00e9gl, B.: Algorithms for hyper-parameter optimization. In: Shawe-Taylor, J., Zemel, R., Bartlett, P., Pereira, F., Weinberger, K. (eds.) Proceedings of the 25th International Conference on Advances in Neural Information Processing Systems (NIPS\u201911). pp. 2546\u20132554 (2011)"},{"key":"7_CR3","volume-title":"Metalearning: Applications to Data Mining","author":"P Brazdil","year":"2008","unstructured":"Brazdil, P., Giraud-Carrier, C., Soares, C., Vilalta, R.: Metalearning: Applications to Data Mining. Springer Publishing Company, Incorporated, 1 edn. (2008)","edition":"1"},{"key":"7_CR4","unstructured":"Brochu, E., Cora, V., de Freitas, N.: A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. Computing Research Repository (CoRR) abs\/1012.2599 (2010)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Caruana, R., Niculescu-Mizil, A., Crew, G., Ksikes, A.: Ensemble selection from libraries of models. In: In Proceedings of the 21st International Conference on Machine Learning. pp. 137\u2013144. ACM Press (2004)","DOI":"10.1145\/1015330.1015432"},{"key":"7_CR6","doi-asserted-by":"publisher","unstructured":"Dieleman, S., Schl\u00fcter, J., Raffel, C., Olson, E., S\u00f8nderby, S., Nouri, D., Maturana, D., Thoma, M., Battenberg, E., Kelly, J., Fauw, J.D., Heilman, M., diogo149, McFee, B., Weideman, H., takacsg84, peterderivaz, Jon, instagibbs, Rasul, K., CongLiu, Britefury, Degrave, J.: Lasagne: First release. (Aug 2015), https:\/\/doi.org\/10.5281\/zenodo.27878","DOI":"10.5281\/zenodo.27878"},{"key":"7_CR7","unstructured":"Domhan, T., Springenberg, J.T., Hutter, F.: Speeding up automatic hyperparameter optimization of deep neural networks by extrapolation of learning curves. In: Yang, Q., Wooldridge, M. (eds.) Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI\u201915). pp. 3460\u20133468 (2015)"},{"key":"7_CR8","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12, 2121\u20132159 (Jul 2011)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR9","unstructured":"Eggensperger, K., Feurer, M., Hutter, F., Bergstra, J., Snoek, J., Hoos, H., Leyton-Brown, K.: Towards an empirical foundation for assessing Bayesian optimization of hyperparameters. In: NIPS Workshop on Bayesian Optimization in Theory and Practice (BayesOpt\u201913) (2013)"},{"key":"7_CR10","unstructured":"Falkner, S., Klein, A., Hutter, F.: Combining hyperband and bayesian optimization. In: NIPS 2017 Bayesian Optimization Workshop (Dec 2017)"},{"key":"7_CR11","unstructured":"Feurer, M., Klein, A., Eggensperger, K., Springenberg, J.T., Blum, M., Hutter, F.: Efficient and robust automated machine learning. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Proceedings of the 29th International Conference on Advances in Neural Information Processing Systems (NIPS\u201915) (2015)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Feurer, M., Springenberg, T., Hutter, F.: Initializing Bayesian hyperparameter optimization via meta-learning. In: Bonet, B., Koenig, S. (eds.) Proceedings of the Twenty-nineth National Conference on Artificial Intelligence (AAAI\u201915). pp. 1128\u20131135. AAAI Press (2015)","DOI":"10.1609\/aaai.v29i1.9354"},{"key":"7_CR13","unstructured":"Gastaldi, X.: Shake-shake regularization. CoRR abs\/1705.07485 (2017)"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Guyon, I., Bennett, K., Cawley, G., Escalante, H.J., Escalera, S., Ho, T.K., Maci\u00e0, N., Ray, B., Saeed, M., Statnikov, A., Viegas, E.: Design of the 2015 chalearn automl challenge. In: 2015 International Joint Conference on Neural Networks (IJCNN). pp. 1\u20138 (July 2015)","DOI":"10.1109\/IJCNN.2015.7280767"},{"key":"7_CR15","unstructured":"Halko, N., Martinsson, P., Tropp, J.: Finding structure with randomness: Stochastic algorithms for constructing approximate matrix decompositions (2009)"},{"issue":"1","key":"7_CR16","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.: The WEKA data mining software: An update. SIGKDD Explorations 11(1), 10\u201318 (2009)","journal-title":"SIGKDD Explorations"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Hutter, F., Hoos, H., Leyton-Brown, K.: Sequential model-based optimization for general algorithm configuration. In: Coello, C. (ed.) Proceedings of the Fifth International Conference on Learning and Intelligent Optimization (LION\u201911). Lecture Notes in Computer Science, vol. 6683, pp. 507\u2013523. Springer-Verlag (2011)","DOI":"10.1007\/978-3-642-25566-3_40"},{"issue":"4\u20135","key":"7_CR18","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/S0893-6080(00)00026-5","volume":"13","author":"A Hyv\u00e4rinen","year":"2000","unstructured":"Hyv\u00e4rinen, A., Oja, E.: Independent component analysis: algorithms and applications. Neural networks 13(4\u20135), 411\u2013430 (2000)","journal-title":"Neural networks"},{"key":"7_CR19","unstructured":"Jamieson, K., Talwalkar, A.: Non-stochastic best arm identification and hyperparameter optimization. In: Gretton, A., Robert, C. (eds.) Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, AISTATS. JMLR Workshop and Conference Proceedings, vol. 51, pp. 240\u2013248. JMLR.org (2016)"},{"key":"7_CR20","unstructured":"Jin, H., Song, Q., Hu, X.: Efficient neural architecture search with network morphism. CoRR abs\/1806.10282 (2018)"},{"key":"7_CR21","unstructured":"Kingma, D., Ba, J.: Adam: A method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (2015)"},{"key":"7_CR22","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: Bartlett, P., Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) Proceedings of the 26th International Conference on Advances in Neural Information Processing Systems (NIPS\u201912). pp. 1097\u20131105 (2012)"},{"key":"7_CR23","unstructured":"Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., Talwalkar, A.: Hyperband: A novel bandit-based approach to hyperparameter optimization. Journal of Machine Learning Research 18, 185:1\u2013185:52 (2017)"},{"key":"7_CR24","unstructured":"Loshchilov, I., Hutter, F.: Sgdr: Stochastic gradient descent with warm restarts. In: International Conference on Learning Representations (ICLR) 2017 Conference Track (2017)"},{"key":"7_CR25","unstructured":"Loshchilov, I.: Personal communication (2017)"},{"key":"7_CR26","unstructured":"Mendoza, H., Klein, A., Feurer, M., Springenberg, J., Hutter, F.: Towards automatically-tuned neural networks. In: ICML 2016 AutoML Workshop (2016)"},{"key":"7_CR27","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"7_CR28","first-page":"372","volume":"27","author":"Y Nesterov","year":"1983","unstructured":"Nesterov, Y.: A method of solving a convex programming problem with convergence rate O(1\/sqr(k)). Soviet Mathematics Doklady 27, 372\u2013376 (1983)","journal-title":"Soviet Mathematics Doklady"},{"key":"7_CR29","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A.: Automatic differentiation in pytorch. In: Autodiff Workshop at NIPS (2017)"},{"key":"7_CR30","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: Machine learning in Python. Journal of Machine Learning Research 12, 2825\u20132830 (2011)","journal-title":"Journal of Machine Learning Research"},{"key":"7_CR31","unstructured":"Rahimi, A., Recht, B.: Weighted sums of random kitchen sinks: Replacing minimization with randomization in learning. In: Advances in neural information processing systems. pp. 1313\u20131320 (2009)"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Rasmussen, C., Williams, C.: Gaussian Processes for Machine Learning. The MIT Press (2006)","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"7_CR33","unstructured":"Schaul, T., Zhang, S., LeCun, Y.: No More Pesky Learning Rates. In: Dasgupta, S., McAllester, D. (eds.) Proceedings of the 30th International Conference on Machine Learning (ICML\u201913). Omnipress (2014)"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Sch\u00f6lkopf, B., Smola, A., M\u00fcller, K.: Kernel principal component analysis. In: International Conference on Artificial Neural Networks. pp. 583\u2013588. Springer (1997)","DOI":"10.1007\/BFb0020217"},{"issue":"1","key":"7_CR35","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","volume":"104","author":"Bobak Shahriari","year":"2016","unstructured":"Shahriari, B., Swersky, K., Wang, Z., Adams, R., de Freitas, N.: Taking the human out of the loop: A Review of Bayesian Optimization. Proc. of the IEEE 104(1) (12\/2015 2016)","journal-title":"Proceedings of the IEEE"},{"key":"7_CR36","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T., Hassabis, D.: Mastering the game of go with deep neural networks and tree search. Nature 529, 484\u2013503 (2016)","journal-title":"Nature"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Smith, L.N.: Cyclical learning rates for training neural networks. In: Applications of Computer Vision (WACV), 2017 IEEE Winter Conference on. pp. 464\u2013472. IEEE (2017)","DOI":"10.1109\/WACV.2017.58"},{"issue":"1","key":"7_CR38","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research 15(1), 1929\u20131958 (2014)","journal-title":"The Journal of Machine Learning Research"},{"key":"7_CR39","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. CoRR abs\/1409.3215 (2014), http:\/\/arxiv.org\/abs\/1409.3215"},{"key":"7_CR40","unstructured":"Swersky, K., Duvenaud, D., Snoek, J., Hutter, F., Osborne, M.: Raiders of the lost architecture: Kernels for Bayesian optimization in conditional parameter spaces. In: NIPS Workshop on Bayesian Optimization in Theory and Practice (BayesOpt\u201913) (2013)"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deepface: Closing the gap to human-level performance in face verification. In: Proceedings of the International Conference on Computer Vision and Pattern Recognition (CVPR\u201914). pp. 1701\u20131708. IEEE Computer Society Press (2014)","DOI":"10.1109\/CVPR.2014.220"},{"key":"7_CR42","unstructured":"Theano Development Team: Theano: A Python framework for fast computation of mathematical expressions. Computing Research Repository (CoRR) abs\/1605.02688 (may 2016)"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Thornton, C., Hutter, F., Hoos, H., Leyton-Brown, K.: Auto-WEKA: combined selection and hyperparameter optimization of classification algorithms. In: I.Dhillon, Koren, Y., Ghani, R., Senator, T., Bradley, P., Parekh, R., He, J., Grossman, R., Uthurusamy, R. (eds.) The 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD\u201913). pp. 847\u2013855. ACM Press (2013)","DOI":"10.1145\/2487575.2487629"},{"key":"7_CR44","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1613\/jair.4806","volume":"55","author":"Z Wang","year":"2016","unstructured":"Wang, Z., Hutter, F., Zoghi, M., Matheson, D., de Feitas, N.: Bayesian optimization in a billion dimensions via random embeddings. Journal of Artificial Intelligence Research 55, 361\u2013387 (2016)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"7_CR45","unstructured":"Williams, C., Seeger, M.: Using the nystr\u00f6m method to speed up kernel machines. In: Advances in neural information processing systems. pp. 682\u2013688 (2001)"},{"key":"7_CR46","unstructured":"Yamada, Y., Iwamura, M., Kise, K.: Shakedrop regularization. CoRR abs\/1802.02375 (2018)"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks. CoRR abs\/1605.07146 (2016)","DOI":"10.5244\/C.30.87"},{"key":"7_CR48","unstructured":"Zeiler, M.: ADADELTA: an adaptive learning rate method. CoRR abs\/1212.5701 (2012), http:\/\/arxiv.org\/abs\/1212.5701"},{"key":"7_CR49","unstructured":"Zhang, H., Ciss\u00e9, M., Dauphin, Y., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. CoRR abs\/1710.09412 (2017)"}],"container-title":["The Springer Series on Challenges in Machine Learning","Automated Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05318-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,18]],"date-time":"2022-09-18T06:07:52Z","timestamp":1663481272000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05318-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030053178","9783030053185"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05318-5_7","relation":{},"ISSN":["2520-131X","2520-1328"],"issn-type":[{"value":"2520-131X","type":"print"},{"value":"2520-1328","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"18 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}