{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T06:26:07Z","timestamp":1763533567349,"version":"3.45.0"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T00:00:00Z","timestamp":1748390400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"The Key Project of China Coal Science and Industry Group","award":["2022-2-TD-ZD015"],"award-info":[{"award-number":["2022-2-TD-ZD015"]}]},{"name":"The Basic Research Project of Shanxi Province","award":["202103021223462"],"award-info":[{"award-number":["202103021223462"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This study presents the Mixed Strategy Gaussian Process (MSGP) algorithm, an innovative extension of Gaussian process regression (GPR) addressing computational bottlenecks and scalability challenges in large-scale, high-dimensional, and noisy datasets. By integrating enhanced random feature mapping and dynamic pseudo-input selection, MSGP achieves significantly improved computational efficiency while maintaining competitive predictive performance. Although some combinations of feature mapping and pseudo-input selection may show reduced accuracy in specific datasets, MSGP generally outperforms standard GPR on benchmark datasets. For example, on the Winequality-red dataset, MSGP-C reduces computation time to 0.61 s versus GPR\u2019s 14.45 s, with comparable accuracy (88.92% versus 90.26%). On the high-dimensional Online News Popularity dataset, MSGP achieves improved accuracy as dimensionality increases. MSGP also demonstrates stable computation times and improved error metrics as volume grows in the Bike Sharing dataset. Robustness tests show MSGP performs reliably in noisy environments (e.g. 94.17% accuracy on noisy Abalone data in 2.91 s versus GPR\u2019s 138.32 s). However, in certain complex datasets, such as Abalone with static pseudo-input selection, MSGP may show lower accuracy. These results highlight MSGP\u2019s potential as a scalable and robust solution for large-scale machine learning, while future work will focus on improving performance on smaller datasets and optimizing tuning.<\/jats:p>","DOI":"10.1093\/comjnl\/bxaf066","type":"journal-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T07:44:34Z","timestamp":1747035874000},"page":"1682-1698","source":"Crossref","is-referenced-by-count":0,"title":["Gaussian process regression based on random projections and dynamic pseudo-input selection"],"prefix":"10.1093","volume":"68","author":[{"given":"Jie","family":"Liu","sequence":"first","affiliation":[{"name":"Shanxi Tiandi Coal Mining Machinery Co. , Ltd., 1 Dianzi Street, Xiaodian District, Taiyuan 030000,","place":["China"]}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"CCTEG Taiyuan Research Institute Co. , Ltd., 1 Kehui Road, Comprehensive Reform Zone, Taiyuan 030000,","place":["China"]}]},{"given":"Weijian","family":"Qiu","sequence":"additional","affiliation":[{"name":"CCTEG Taiyuan Research Institute Co. , Ltd., 1 Kehui Road, Comprehensive Reform Zone, Taiyuan 030000,","place":["China"]}]},{"given":"Gangyong","family":"Zuo","sequence":"additional","affiliation":[{"name":"CCTEG Taiyuan Research Institute Co. , Ltd., 1 Kehui Road, Comprehensive Reform Zone, Taiyuan 030000,","place":["China"]}]}],"member":"286","published-online":{"date-parts":[[2025,5,28]]},"reference":[{"key":"2025111901221066500_ref1","first-page":"1939","article-title":"A unifying view of sparse approximate gaussian process regression","volume":"06","author":"Quinonero-Candela","year":"2005","journal-title":"J Mach Learn Res"},{"key":"2025111901221066500_ref2","article-title":"Scalable inference for gaussian process models with black-box likelihoods","volume":"28","author":"Dezfouli","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025111901221066500_ref3","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-1-4471-0657-9_2","article-title":"Space and space-time modeling using process convolutions","author":"Higdon","year":"2002","journal-title":"In Quantitative Methods for Current Environmental Issues"},{"volume-title":"Flexible and Efficient Gaussian Process Models for Machine Learning","year":"2008","author":"Snelson","key":"2025111901221066500_ref4"},{"key":"2025111901221066500_ref5","first-page":"7834","article-title":"Exact Gaussian processes on a million data points","volume":"32","author":"Wang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025111901221066500_ref6","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1109\/TPAMI.2013.192","article-title":"Scaling multidimensional inference for structured gaussian processes","volume":"37","author":"Gilboa","year":"2013","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2025111901221066500_ref7","doi-asserted-by":"publisher","first-page":"203","DOI":"10.7551\/mitpress\/7496.003.0011","article-title":"Approximation methods for gaussian process regression","author":"Quinonero-Candela","year":"2007","journal-title":"Large-scale Kernel Machines"},{"key":"2025111901221066500_ref8","first-page":"01","article-title":"A unifying framework for gaussian process pseudo-point approximations using power expectation propagation","volume":"18","author":"Bui","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"2025111901221066500_ref9","first-page":"1775","article-title":"Kernel interpolation for scalable structured Gaussian processes (KISS-GP)","volume":"37","author":"Wilson","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning"},{"key":"2025111901221066500_ref10","article-title":"Random features for large-scale kernel machines","volume":"20","author":"Rahimi","year":"2007","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025111901221066500_ref11","first-page":"1","article-title":"GPflow: a gaussian process library using tensor flow","volume":"18","author":"Matthews","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"2025111901221066500_ref12","first-page":"1891","article-title":"Generalized spike-and-slab priors for Bayesian group feature selection using expectation propagation","volume":"14","author":"Hern\u00e1ndez-Lobato","year":"2013","journal-title":"J Mach Learn Res"},{"key":"2025111901221066500_ref13","article-title":"Sparse convolved gaussian processes for multi-output regression","volume":"21","author":"Alvarez","year":"2008","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025111901221066500_ref14","article-title":"Practical Bayesian optimization of machine learning algorithms","volume":"25","author":"Snoek","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025111901221066500_ref15","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1162\/089976602317250933","article-title":"Sparse on-line gaussian processes","volume":"14","author":"Csat\u00f3","year":"2002","journal-title":"Neural Comput"},{"author":"Snoek","key":"2025111901221066500_ref16","article-title":"Bayesian optimization and semiparametric models with applications to assistive technology"},{"key":"2025111901221066500_ref17","article-title":"Convolutional gaussian processes","volume":"30","author":"Van","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025111901221066500_ref18","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1198\/016214508000000689","article-title":"Bayesian treed gaussian process models with an application to computer modeling","volume":"103","author":"Gramacy","year":"2008","journal-title":"J Am Stat Assoc"},{"key":"2025111901221066500_ref19","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1080\/01621459.2018.1473776","article-title":"Frequentist consistency of variational bayes","volume":"114","author":"Wang","year":"2018","journal-title":"J Am Stat Assoc"},{"key":"2025111901221066500_ref20","first-page":"1865","article-title":"Sparse spectrum gaussian process regression","volume":"11","author":"L\u00e1zaro-Gredilla","year":"2010","journal-title":"J Mach Learn Res"},{"key":"2025111901221066500_ref21","article-title":"Variational inference for gaussian process models with linear complexity","volume":"30","author":"Cheng","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025111901221066500_ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2019.106732","article-title":"Gaussian process regression with linear inequality constraints","volume":"195","author":"Da Veiga","year":"2020","journal-title":"Reliab Eng Syst Saf"},{"key":"2025111901221066500_ref23","article-title":"Fast sparse gaussian process methods: The informative vector machine","volume":"15","author":"Lawrence","year":"2002","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025111901221066500_ref24","first-page":"1166","article-title":"Structure discovery in nonparametric regression through compositional kernel search","volume":"28","author":"Duvenaud","year":"2013","journal-title":"Proceedings of the 30th international conference on machine learning"},{"key":"2025111901221066500_ref25","first-page":"607","article-title":"Fast Kronecker inference in gaussian processes with non-gaussian likelihoods","volume":"37","author":"Flaxman","year":"2015","journal-title":"Proceedings of the 32nd international conference on machine learning"},{"key":"2025111901221066500_ref26","article-title":"Sparse gaussian processes using pseudo-inputs","volume":"18","author":"Snelson","year":"2005","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Gaussian Processes for Machine Learning","year":"2006","author":"Rasmussen","key":"2025111901221066500_ref27"},{"key":"2025111901221066500_ref28","doi-asserted-by":"publisher","DOI":"10.24432\/C56S3T","article-title":"Wine quality, UCI machine learning repository","author":"Cortez","year":"2009"},{"key":"2025111901221066500_ref29","doi-asserted-by":"publisher","DOI":"10.24432\/C5VW2C","article-title":"Airfoil self-noise","author":"Brooks","year":"2014"},{"key":"2025111901221066500_ref30","doi-asserted-by":"publisher","DOI":"10.24432\/C55C7W","article-title":"Abalone UCI machine learning repository","author":"Nash","year":"1995"},{"key":"2025111901221066500_ref31","doi-asserted-by":"publisher","DOI":"10.24432\/C5W894","article-title":"Bike sharing UCI machine learning repository","author":"Fanaee-T","year":"2013"},{"key":"2025111901221066500_ref32","doi-asserted-by":"publisher","DOI":"10.24432\/C5NS3V","article-title":"Online news popularity UCI machine learning repository","author":"Cortez","year":"2015"},{"key":"2025111901221066500_ref33","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1093\/comjnl\/bxt004","article-title":"Transductive gaussian processes with applications to object pose estimation","volume":"57","author":"Hyun-Chul","year":"2014","journal-title":"Comput J"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/68\/11\/1682\/63390852\/bxaf066.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/68\/11\/1682\/63390852\/bxaf066.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T06:22:21Z","timestamp":1763533341000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/68\/11\/1682\/8152040"}},"subtitle":[],"editor":[{"given":"Florence","family":"Leroy","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,5,28]]},"references-count":33,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,5,28]]},"published-print":{"date-parts":[[2025,11,13]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxaf066","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"type":"print","value":"0010-4620"},{"type":"electronic","value":"1460-2067"}],"subject":[],"published-other":{"date-parts":[[2025,11]]},"published":{"date-parts":[[2025,5,28]]}}}