{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:13:58Z","timestamp":1780492438808,"version":"3.54.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"9-10","license":[{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2017R1E1A1A01075927"],"award-info":[{"award-number":["2017R1E1A1A01075927"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["2020-0-00862"],"award-info":[{"award-number":["2020-0-00862"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1007\/s10994-020-05903-6","type":"journal-article","created":{"date-parts":[[2020,9,4]],"date-time":"2020-09-04T16:03:41Z","timestamp":1599235421000},"page":"1837-1853","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Ada-boundary: accelerating DNN training via adaptive boundary batch selection"],"prefix":"10.1007","volume":"109","author":[{"given":"Hwanjun","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sundong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minseok","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8711-7732","authenticated-orcid":false,"given":"Jae-Gil","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,9,4]]},"reference":[{"key":"5903_CR1","doi-asserted-by":"crossref","unstructured":"Bengio, Y., J.\u00a0Louradour, R.\u00a0Collobert, & J.\u00a0Weston (2009). Curriculum learning. In International Conference on Machine Learning (ICML), pp. 41\u201348.","DOI":"10.1145\/1553374.1553380"},{"key":"5903_CR2","unstructured":"Chang, H.-S., E.\u00a0Learned-Miller, & A.\u00a0McCallum (2017). Active Bias: Training more accurate neural networks by emphasizing high variance samples. In Advances in Neural Information Processing Systems (NeurIPS), pp. 1002\u20131012."},{"issue":"4","key":"5903_CR3","doi-asserted-by":"publisher","first-page":"1423","DOI":"10.1109\/18.923725","volume":"47","author":"B Chen","year":"2001","unstructured":"Chen, B., & Wornell, G. W. (2001). Quantization index modulation: A class of provably good methods for digital watermarking and information embedding. Transactions on Information Theory, 47(4), 1423\u20131443.","journal-title":"Transactions on Information Theory"},{"key":"5903_CR4","unstructured":"Fan, Y., Tian, F., Qin, T., & Liu, T.-Y. (2017). Neural data filter for bootstrapping stochastic gradient descent. In International Conference on Learning Representation (ICLR)."},{"key":"5903_CR5","unstructured":"Gao, T., & Jojic, V. (2017). Sample importance in training deep neural networks. https:\/\/openreview.net\/forum?id=r1IRctqxg."},{"key":"5903_CR6","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. Cambridge: MIT Press."},{"issue":"6","key":"5903_CR7","doi-asserted-by":"publisher","first-page":"2325","DOI":"10.1109\/18.720541","volume":"44","author":"RM Gray","year":"1998","unstructured":"Gray, R. M., & Neuhoff, D. L. (1998). Quantization. Transactions on Information Theory, 44(6), 2325\u20132383.","journal-title":"Transactions on Information Theory"},{"issue":"8","key":"5903_CR8","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735\u20131780.","journal-title":"Neural Computation"},{"key":"5903_CR9","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., & Weinberger, K.\u00a0Q. (2017). Densely connected convolutional networks. In International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"5903_CR10","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning (ICML), pp. 448\u2013456."},{"key":"5903_CR11","unstructured":"Katharopoulos, A., & Fleuret, F. (2018). Not all samples are created equal: Deep learning with importance sampling. In International Conference on Machine Learning (ICML), pp. 2525\u20132534."},{"key":"5903_CR12","unstructured":"Kingma, D.\u00a0P., & Ba, J. (2015). Adam: A method for stochastic optimization. In International Conference on Learning Representation (ICLR)."},{"key":"5903_CR13","unstructured":"Krizhevsky, A., Nair, V., & Hinton, G. (2014). CIFAR-10 and CIFAR-100 datasets. https:\/\/www.cs.toronto.edu\/~kriz\/cifar.html."},{"key":"5903_CR14","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G.\u00a0E. (2012). ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (NeurIPS), pp. 1097\u20131105."},{"key":"5903_CR15","unstructured":"Kumar, M.\u00a0P., Packer, B., & Koller, D. (2010). Self-paced learning for latent variable models. In Advances in Neural Information Processing Systems (NeurIPS), pp. 1189\u20131197."},{"key":"5903_CR16","unstructured":"LeCun, Y. (1998). The MNIST database of handwritten digits. http:\/\/yann.lecun.com\/exdb\/mnist."},{"key":"5903_CR17","unstructured":"Loshchilov, I., & Hutter, F. (2016). Online batch selection for faster training of neural networks. In International Conference on Learning Representation (ICLR)."},{"key":"5903_CR18","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., \u010cernock\u1ef3, J., & Khudanpur, S. (2010). Recurrent neural network based language model. In Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 1045\u20131048.","DOI":"10.21437\/Interspeech.2010-343"},{"key":"5903_CR19","unstructured":"Needell, D., Ward, R., & Srebro, N. (2014). Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm. In Advances in Neural Information Processing Systems (NeurIPS), pp. 1017\u20131025."},{"key":"5903_CR20","doi-asserted-by":"crossref","unstructured":"Sachan, M., & Xing, E. (2016). Easy questions first? A case study on curriculum learning for question answering. In Annual Meeting of the Association for Computational Linguistics (ACL), pp. 453\u2013463.","DOI":"10.18653\/v1\/P16-1043"},{"key":"5903_CR21","unstructured":"Schaul, T., Quan, J., Antonoglou, I., & Silver, D. (2016). Prioritized experience replay. In International Conference on Learning Representation (ICLR)."},{"key":"5903_CR22","unstructured":"Schmidt, M., Babanezhad, R., Ahmed, M., Defazio, A., Clifton, A., & Sarkar, A. (2015). Non-uniform stochastic average gradient method for training conditional random fields. In International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 819\u2013828."},{"key":"5903_CR23","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., & Girshick, R. (2016). Training region-based object detectors with online hard example mining. In International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 761\u2013769.","DOI":"10.1109\/CVPR.2016.89"},{"key":"5903_CR24","unstructured":"Song, H., Kim, M., & Lee, J.-G. (2019). SELFIE: Refurbishing unclean samples for robust deep learning. In International Conference on Machine Learning, pp. 5907\u20135915."},{"key":"5903_CR30","doi-asserted-by":"crossref","unstructured":"Song, H., Kim, M., Kim, S., & Lee, J.-G. (2020). Carpe diem, seize the samples uncertain \u201cat the moment\u201d for adaptive batch selection. In International Conference on Information and Knowledge Management (CIKM).","DOI":"10.1145\/3340531.3411898"},{"key":"5903_CR25","doi-asserted-by":"crossref","unstructured":"Tsvetkov, Y., Faruqui, M., Ling, W., MacWhinney, B., & Dyer, C. (2016). Learning the curriculum with bayesian optimization for task-specific word representation learning. In Annual Meeting of the Association for Computational Linguistics (ACL), pp. 130\u2013139.","DOI":"10.18653\/v1\/P16-1013"},{"key":"5903_CR26","doi-asserted-by":"crossref","unstructured":"Wu, C.-Y., Manmatha, R., Smola, A.\u00a0J., & Kr\u00e4henb\u00fchl, P. (2017). Sampling matters in deep embedding learning. In International Conference on Computer Vision (ICCV), pp. 2840\u20132848.","DOI":"10.1109\/ICCV.2017.309"},{"key":"5903_CR27","unstructured":"Xiao, H., Rasul, K., & Vollgraf, R. (2017). Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747."},{"key":"5903_CR28","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., & Komodakis, N. (2016). Wide residual networks. arXiv:1605.07146.","DOI":"10.5244\/C.30.87"},{"key":"5903_CR29","unstructured":"Zeiler, M.\u00a0D. (2012). Adadelta: An adaptive learning rate method. arXiv:1212.5701."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-020-05903-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-020-05903-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-020-05903-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T02:09:29Z","timestamp":1630721369000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-020-05903-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9]]},"references-count":30,"journal-issue":{"issue":"9-10","published-print":{"date-parts":[[2020,9]]}},"alternative-id":["5903"],"URL":"https:\/\/doi.org\/10.1007\/s10994-020-05903-6","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9]]},"assertion":[{"value":"3 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 June 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 September 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}