{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T23:27:00Z","timestamp":1773617220014,"version":"3.50.1"},"reference-count":15,"publisher":"Pleiades Publishing Ltd","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"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":["Autom Remote Control"],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1134\/s00051179220100071","type":"journal-article","created":{"date-parts":[[2022,12,20]],"date-time":"2022-12-20T05:06:28Z","timestamp":1671512788000},"page":"1544-1554","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Gradient Methods for Optimizing Metaparameters in the Knowledge Distillation Problem"],"prefix":"10.1134","volume":"83","author":[{"given":"M.","family":"Gorpinich","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"O. Yu.","family":"Bakhteev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"V. V.","family":"Strijov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"137","published-online":{"date-parts":[[2022,12,20]]},"reference":[{"issue":"1","key":"2335_CR1","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/s10479-019-03286-z","volume":"289","author":"O.Y. Bakhteev","year":"2020","unstructured":"Bakhteev, O.Y. and Strijov, V.V., Comprehensive analysis of gradient-based\nhyperparameter optimization algorithms, Ann. Oper.\nRes., 2020, vol. 289, no. 1, pp. 51\u201365.","journal-title":"Ann. Oper. Res."},{"key":"2335_CR2","unstructured":"Bergstra, J. and Bengio, Y., Random search for hyper-parameter\noptimization, Mach. Learn. Res., 2012, vol. 13,\nno. 2."},{"key":"2335_CR3","unstructured":"Bergstra, J., Yamins, D., and Cox, D., Making a science of model search:\nHyperparameter optimization in hundreds of dimensions for vision architectures, Int. Conf. Mach. Learn. (2013), pp. 115\u2013123."},{"key":"2335_CR4","unstructured":"Bishop, C.M., Pattern Recognition and Machine\nLearning (Information Science and Statistics), 2006."},{"key":"2335_CR5","unstructured":"Hinton, G.E., Vinyals, O., and Dean, J., Distilling the knowledge in a neural\nnetwork, CoRR, 2015, vol. abs\/1503.02531.\n arXiv:1503.02531."},{"key":"2335_CR6","unstructured":"Krizhevsky, A. et al., Learning Multiple Layers of\nFeatures from Tiny Images, 2009."},{"key":"2335_CR7","unstructured":"Liu, H., Simonyan, K., and Yang, Y., Darts:\nDifferentiable Architecture Search, 2018. \narXiv:1806.09055."},{"key":"2335_CR8","unstructured":"Luketina, J., Berglund, M., Greff, K., and Raiko, T., Scalable gradient-based\ntuning of continuous regularization hyperparameters, CoRR, 2015, vol. abs\/1511.06727. \narXiv:1511.06727."},{"key":"2335_CR9","unstructured":"Maclaurin, D., Duvenaud, D., and Adams, R.P., Gradient-based\nhyperparameter optimization through reversible learning, CoRR, 2015, vol. abs\/1502.03492. \narXiv:1502.03492."},{"key":"2335_CR10","doi-asserted-by":"crossref","unstructured":"Passalis, N., Tzelepi, M., and Tefas, A., Heterogeneous knowledge distillation\nusing information flow modeling, Proc. IEEE Conf. Comput. Vis.\nPattern Recognit., (2020).","DOI":"10.1109\/CVPR42600.2020.00241"},{"key":"2335_CR11","unstructured":"Pedregosa, F., Hyperparameter optimization with approximate gradient,\nCoRR, 2016, vol. abs\/ 1602.02355.  arXiv:1602.02355."},{"key":"2335_CR12","doi-asserted-by":"crossref","unstructured":"Rasley, J., Rajbhandari, S., Ruwase, O., and He, Y., Deepspeed: System\noptimizations enable training deep learning models with over 100 billion parameters, Proc. 26th ACM SIGKDD Int. Conf. Knowl. Discovery & Data\nMin. (2020), pp. 3505\u20133506.","DOI":"10.1145\/3394486.3406703"},{"key":"2335_CR13","doi-asserted-by":"crossref","unstructured":"Vatanen, T., Raiko, T., Valpola, H., and LeCun, Y., Pushing stochastic\ngradient towards second-order methods\u2014backpropagation learning with transformations\nin nonlinearities, in Int. Conf. Neural Inf. Process.,\nBerlin\u2013Heidelberg: Springer, 2013, pp. 442\u2013449.","DOI":"10.1007\/978-3-642-42054-2_55"},{"key":"2335_CR14","unstructured":"Xiao, H., Rasul, K., and Vollgraf, R., Fashion-mnist: a novel image dataset\nfor benchmarking machine learning algorithms, CoRR,\n2017, vol. abs\/1708.07747.  arXiv:1708.07747"},{"key":"2335_CR15","unstructured":"Computational experiment code.\n https:\/\/github.com\/Intelligent-Systems-Phystech\/MetaOptDistillation .\nAccessed June 14, 2022."}],"container-title":["Automation and Remote Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1134\/S00051179220100071.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1134\/S00051179220100071","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1134\/S00051179220100071.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T22:37:36Z","timestamp":1773614256000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1134\/S00051179220100071"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":15,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["2335"],"URL":"https:\/\/doi.org\/10.1134\/s00051179220100071","relation":{},"ISSN":["0005-1179","1608-3032"],"issn-type":[{"value":"0005-1179","type":"print"},{"value":"1608-3032","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]},"assertion":[{"value":"17 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 June 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 December 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}