{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T15:55:04Z","timestamp":1777478104670,"version":"3.51.4"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T00:00:00Z","timestamp":1636416000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T00:00:00Z","timestamp":1636416000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1007\/s10994-021-06101-8","type":"journal-article","created":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T23:02:27Z","timestamp":1636498947000},"page":"1671-1694","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Nested aggregation of experts using inducing points for approximated Gaussian process regression"],"prefix":"10.1007","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0832-0423","authenticated-orcid":false,"given":"Ayano","family":"Nakai-Kasai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5962-9119","authenticated-orcid":false,"given":"Toshiyuki","family":"Tanaka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,11,9]]},"reference":[{"key":"6101_CR1","unstructured":"Ashton, S.R.F., & Sollich, P. (2012). Learning curves for multi-task Gaussian process regression. In Advances in Neural Information Processing Systems 25, pp 1393\u20131428."},{"key":"6101_CR2","unstructured":"Bachoc, F., Durrande, N., Rulli\u00e8re, D., & Chevalier, C. (2017). Some properties of nested Kriging predictors. arXiv preprint arXiv:1707.05708v1."},{"key":"6101_CR3","unstructured":"Bachoc, F., Durrande, N., Rulli\u00e8re, D., & Chevalier, C. (2021). Properties and comparison of some Kriging sub-model aggregation. arXiv preprint arXiv:1707.05708v2."},{"key":"6101_CR4","unstructured":"Bauer, M., van der Wilk, M., & Rasmussen, C.E. (2016). Understanding probabilistic sparse Gaussian process approximations. In Advances in Neural Information Processing Systems 29, pp. 1533\u20131541."},{"key":"6101_CR5","unstructured":"Bradley, P.S., Bennett, K.P., & Demiriz, A. (2000). Constrained k-means clustering. Tech. rep., MSR-TR-2000-65, Microsoft Research, Redmond, WA."},{"key":"6101_CR6","unstructured":"Bui, T.D., & Turner, R.E. (2014). Tree-structured Gaussian process approximations. In Advances in Neural Information Processing Systems 27, pp. 2213\u20132221."},{"key":"6101_CR7","first-page":"533","volume":"99","author":"D Calandriello","year":"2019","unstructured":"Calandriello, D., Carratino, L., Lazaric, A., Valko, M., & Rosasco, L. (2019). Gaussian process optimization with adaptive sketching: Scalable and no regret. Proceedings of the Thirty-Second Conference on Learning Theory, PMLR, 99, 533\u2013557.","journal-title":"Proceedings of the Thirty-Second Conference on Learning Theory, PMLR"},{"key":"6101_CR8","unstructured":"Cao, Y., & Fleet, D.J. (2014). Generalized product of experts for automatic and principled fusion of Gaussian process predictions. arXiv preprint arXiv:1410.7827."},{"key":"6101_CR9","doi-asserted-by":"publisher","unstructured":"Cressie, NAC. (1993). Statistics for Spatial Data, Revised Edition. Wiley, New York, NY, https:\/\/doi.org\/10.1002\/9781119115151.","DOI":"10.1002\/9781119115151"},{"key":"6101_CR10","unstructured":"Deisenroth, M.P., & Ng, J.W. (2015) Distributed Gaussian processes. In Proceedings of the 32th International Conference on Machine Learning, PMLR, pp. 1481\u20131490."},{"issue":"2","key":"6101_CR11","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1109\/TPAMI.2013.218","volume":"37","author":"MP Deisenroth","year":"2015","unstructured":"Deisenroth, M. P., Fox, D., & Rasmussen, C. E. (2015). Gaussian processes for data-efficient learning in robotics and control. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(2), 408\u2013423. https:\/\/doi.org\/10.1109\/TPAMI.2013.218","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"6101_CR12","doi-asserted-by":"crossref","unstructured":"He, J., Qi, J., & Ramamohanarao, K. (2019). Query-aware Bayesian committee machine for scalable Gaussian process regression. In Proceedings of the 2019 SIAM International Conference on Data Mining, pp. 208\u2013216.","DOI":"10.1137\/1.9781611975673.24"},{"key":"6101_CR13","unstructured":"Hensman, J., Fusi, N., & Lawrence, N.D. (2013). Gaussian processes for big data. In Proceedings of the 29th Conference on Uncertainly in Artificial Intelligence, pp. 282\u2013290."},{"issue":"8","key":"6101_CR14","doi-asserted-by":"publisher","first-page":"1771","DOI":"10.1162\/089976602760128018","volume":"14","author":"GE Hinton","year":"2002","unstructured":"Hinton, G. E. (2002). Training products of experts by minimizing contrastive divergence. Neural Computation, 14(8), 1771\u20131800. https:\/\/doi.org\/10.1162\/089976602760128018","journal-title":"Neural Computation"},{"key":"6101_CR15","first-page":"1783","volume":"6","author":"N Lawrence","year":"2005","unstructured":"Lawrence, N. (2005). Probabilistic non-linear principal component analysis with Gaussian process latent variable models. Journal of Machine Learning Research, 6, 1783\u20131816.","journal-title":"Journal of Machine Learning Research"},{"key":"6101_CR16","doi-asserted-by":"crossref","unstructured":"Liberty, E. (2013). Simple and deterministic matrix sketching. In Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 581\u2013588.","DOI":"10.1145\/2487575.2487623"},{"key":"6101_CR17","unstructured":"Liu, H., Cai, J., Wang, Y., & Ong, Y.S. (2018). Generalized robust Bayesian committee machine for large-scale Gaussian process regression. In Proceedings of the 35th International Conference on Machine Learning, PMLR, pp. 3131\u20133140."},{"issue":"11","key":"6101_CR18","doi-asserted-by":"publisher","first-page":"4405","DOI":"10.1109\/TNNLS.2019.2957109","volume":"31","author":"H Liu","year":"2020","unstructured":"Liu, H., Ong, Y. S., Shen, X., & Cai, J. (2020). When Gaussian process meets big data: A review of scalable GPs. IEEE Transactions on Neural Networks and Learning Systems, 31(11), 4405\u20134423. https:\/\/doi.org\/10.1109\/TNNLS.2019.2957109","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"6101_CR19","first-page":"1939","volume":"6","author":"J Qui\u00f1onero-Candela","year":"2005","unstructured":"Qui\u00f1onero-Candela, J., & Rasmussen, C. E. (2005). A unifying view of sparse approximate Gaussian process regression. Journal of Machine Learning Research, 6, 1939\u20131959.","journal-title":"Journal of Machine Learning Research"},{"key":"6101_CR20","volume-title":"Gaussian Process for Machine Learning","author":"CE Rasmussen","year":"2006","unstructured":"Rasmussen, C. E., & Williams, C. K. I. (2006). Gaussian Process for Machine Learning. Cambridge: MIT Press."},{"key":"6101_CR21","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1007\/s11222-017-9766-2","volume":"28","author":"D Rulli\u00e8re","year":"2018","unstructured":"Rulli\u00e8re, D., Durrande, N., Bachoc, F., & Chevalier, C. (2018). Nested Kriging predictions for datasets with a large number of observations. Statistics and Computing, 28, 849\u2013867.","journal-title":"Statistics and Computing"},{"key":"6101_CR22","unstructured":"Snelson, E., & Ghahramani, Z. (2005). Sparse Gaussian processes using pseudo-inputs. In Advances in Neural Information Processing Systems 18, pp. 1257\u20131264."},{"key":"6101_CR23","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1494-6","volume-title":"Interpolation of spatial data: Some theory for kriging","author":"ML Stein","year":"1999","unstructured":"Stein, M. L. (1999). Interpolation of spatial data: Some theory for kriging. New York: Springer,. https:\/\/doi.org\/10.1007\/978-1-4612-1494-6."},{"issue":"8","key":"6101_CR24","doi-asserted-by":"publisher","first-page":"1928","DOI":"10.1109\/TPAMI.2019.2906207","volume":"42","author":"M Tavassolipour","year":"2020","unstructured":"Tavassolipour, M., Motahari, S. A., & Shalmani, M. T. M. (2020). Learning of Gaussian processes in distributed and communication limited systems. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(8), 1928\u20131941. https:\/\/doi.org\/10.1109\/TPAMI.2019.2906207","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"11","key":"6101_CR25","doi-asserted-by":"publisher","first-page":"2719","DOI":"10.1162\/089976600300014908","volume":"12","author":"V Tresp","year":"2000","unstructured":"Tresp, V. (2000). A Bayesian committee machine. Neural Computation, 12(11), 2719\u20132741. https:\/\/doi.org\/10.1162\/089976600300014908","journal-title":"Neural Computation"},{"key":"6101_CR26","first-page":"2095","volume":"12","author":"A van der Vaart","year":"2011","unstructured":"van der Vaart, A., & van Zanten, H. (2011). Information rates of nonparametric Gaussian process methods. Journal of Machine Learning Research, 12, 2095\u20132119.","journal-title":"Journal of Machine Learning Research"},{"issue":"2","key":"6101_CR27","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1145\/2641190.2641198","volume":"15","author":"J Vanschoren","year":"2013","unstructured":"Vanschoren, J., van Rijn, J. N., Bischl, B., & Torgo, L. (2013). OpenML: Networked science in machine learning. SIGKDD Explorations, 15(2), 49\u201360. https:\/\/doi.org\/10.1145\/2641190.2641198","journal-title":"SIGKDD Explorations"},{"key":"6101_CR28","unstructured":"Wilson, A., & Nickisch, H. (2015). Kernel interpolation for scalable structured Gaussian processes (KISS-GP). In Proceedings of the 32nd International Conference on Machine Learning, PMLR, pp. 1775\u20131784."},{"issue":"12","key":"6101_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/0400000060","volume":"10","author":"DP Woodruff","year":"2014","unstructured":"Woodruff, D. P. (2014). Sketching as a tool for numerical linear algebra. Foundations and Trends in Theoretical Computer Science, 10(12), 1\u2013157. https:\/\/doi.org\/10.1561\/0400000060","journal-title":"Foundations and Trends in Theoretical Computer Science"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06101-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-021-06101-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06101-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,9]],"date-time":"2022-11-09T01:08:11Z","timestamp":1667956091000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-021-06101-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,9]]},"references-count":29,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["6101"],"URL":"https:\/\/doi.org\/10.1007\/s10994-021-06101-8","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,9]]},"assertion":[{"value":"2 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 November 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflicts of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The codes for NAE-IP are available at GitHub repository . Factorized training and predictions of conventional methods are implemented relating to Liu et\u00a0al. () at .","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}