{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T08:51:56Z","timestamp":1776329516462,"version":"3.50.1"},"reference-count":59,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2022,4,19]],"date-time":"2022-04-19T00:00:00Z","timestamp":1650326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"Department of Energy Computational Science Graduate Fellowship","award":["DE-FG02-97ER25308"],"award-info":[{"award-number":["DE-FG02-97ER25308"]}]},{"DOI":"10.13039\/100000066","name":"National Institute of Environmental Health Sciences","doi-asserted-by":"publisher","award":["20200065DR"],"award-info":[{"award-number":["20200065DR"]}],"id":[{"id":"10.13039\/100000066","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Laboratory Directed Research and Development program of Los Alamos National Laboratory"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Gaussian processes (GPs) are common components in Bayesian non-parametric models having a rich methodological literature and strong theoretical grounding. The use of exact GPs in Bayesian models is limited to problems containing several thousand observations due to their prohibitive computational demands. We develop a posterior sampling algorithm using H-matrix approximations that scales at O(nlog2n). We show that this approximation's Kullback\u2013Leibler divergence to the true posterior can be made arbitrarily small. Although multidimensional GPs could be used with our algorithm, d-dimensional surfaces are modelled as tensor products of univariate GPs to minimize the cost of matrix construction and maximize computational efficiency. We illustrate the performance of this fast increased fidelity approximate GP, FIFA-GP, using both simulated and non-synthetic data sets.<\/jats:p>","DOI":"10.1111\/rssb.12494","type":"journal-article","created":{"date-parts":[[2022,4,19]],"date-time":"2022-04-19T16:59:23Z","timestamp":1650387563000},"page":"1198-1228","source":"Crossref","is-referenced-by-count":4,"title":["Fast Increased Fidelity Samplers for Approximate Bayesian Gaussian Process Regression"],"prefix":"10.1093","volume":"84","author":[{"given":"Kelly R.","family":"Moran","sequence":"first","affiliation":[{"name":"Los Alamos National Laboratory , Los Alamos , USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew W.","family":"Wheeler","sequence":"additional","affiliation":[{"name":"NIEHS , Research Triangle Park , USA"},{"name":"NIH , Research Triangle Park , USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2022,4,19]]},"reference":[{"issue":"3","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1007\/s10915-013-9714-z","article-title":"An O(nlogn) fast direct solver for partial hierarchically semi-separable matrices","volume":"57","author":"Ambikasaran","year":"2013","journal-title":"Journal of Scientific Computing"},{"key":"2023030906301602500_","volume-title":"Fast symmetric factorization of hierarchical matrices with applications","author":"Ambikasaran","year":"2014"},{"issue":"2","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1109\/TPAMI.2015.2448083","article-title":"Fast direct methods for Gaussian processes","volume":"38","author":"Ambikasaran","year":"2015","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"1167","DOI":"10.21105\/joss.01167","article-title":"Hodlrlib: a library for hierarchical matrices","volume":"4","author":"Ambikasaran","year":"2019","journal-title":"The Journal of Open Source Software"},{"issue":"4","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1111\/j.1467-9868.2008.00663.x","article-title":"Gaussian predictive process models for large spatial data sets","volume":"70","author":"Banerjee","year":"2008","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"issue":"1","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1093\/biomet\/ass068","article-title":"Efficient Gaussian process regression for large datasets","volume":"100","author":"Banerjee","year":"2013","journal-title":"Biometrika"},{"key":"2023030906301602500_","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0653-8","volume-title":"Matrix analysis","author":"Bhatia","year":"1997"},{"key":"2023030906301602500_","first-page":"asw042","article-title":"Fast sampling with Gaussian scale mixture priors in high-dimensional regression","author":"Bhattacharya","year":"2016","journal-title":"Biometrika"},{"issue":"1","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00607-005-0146-y","article-title":"Data-sparse approximation by adaptive H2-matrices","volume":"69","author":"B\u00f6rm","year":"2002","journal-title":"Computing"},{"issue":"4","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1093\/biomet\/ast037","article-title":"Nonparametric Bayes modelling of count processes","volume":"100","author":"Canale","year":"2013","journal-title":"Biometrika"},{"issue":"3","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1007\/s11222-018-9825-3","article-title":"Hierarchical-block conditioning approximations for high-dimensional multivariate normal probabilities","volume":"29","author":"Cao","year":"2019","journal-title":"Statistics and Computing"},{"issue":"2","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1093\/biomet\/asq017","article-title":"The horseshoe estimator for sparse signals","volume":"97","author":"Carvalho","year":"2010","journal-title":"Biometrika"},{"issue":"Feb","key":"2023030906301602500_","first-page":"333","article-title":"A framework for evaluating approximation methods for Gaussian process regression","volume":"14","author":"Chalupka","year":"2013","journal-title":"Journal of Machine Learning Research"},{"issue":"2","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.stamet.2006.07.003","article-title":"Nonparametric binary regression using a Gaussian process prior","volume":"4","author":"Choudhuri","year":"2007","journal-title":"Statistical Methodology"},{"issue":"514","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1080\/01621459.2015.1044091","article-title":"Hierarchical nearest-neighbor Gaussian process models for large geostatistical datasets","volume":"111","author":"Datta","year":"2016","journal-title":"Journal of the American Statistical Association"},{"issue":"5","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1002\/wics.1383","article-title":"On nearest-neighbor Gaussian process models for massive spatial data","volume":"8","author":"Datta","year":"2016","journal-title":"Wiley Interdisciplinary Reviews: Computational Statistics"},{"key":"2023030906301602500_","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-6333-3","volume-title":"A practical guide to splines","author":"De Boor","year":"1978"},{"key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"1984","DOI":"10.1214\/12-EJS735","article-title":"Adaptive estimation of multivariate functions using conditionally Gaussian tensor-product spline priors","volume":"6","author":"De Jonge","year":"2012","journal-title":"Electronic Journal of Statistics"},{"issue":"4","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/BF02243776","article-title":"Algorithms for smoothing data on the sphere with tensor product splines","volume":"32","author":"Dierckx","year":"1984","journal-title":"Computing"},{"key":"2023030906301602500_","first-page":"481","volume-title":"Annales de la Facult\u00e9 des sciences de Toulouse: Math\u00e9matiques","author":"Durrande","year":"2012"},{"key":"2023030906301602500_","first-page":"226","volume-title":"Advances in neural information processing systems","author":"Duvenaud","year":"2011"},{"issue":"6","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1002\/wics.125","article-title":"Splines, knots, and penalties","volume":"2","author":"Eilers","year":"2010","journal-title":"Wiley Interdisciplinary Reviews: Computational Statistics"},{"key":"2023030906301602500_","first-page":"607","volume-title":"Fast Kronecker inference in Gaussian processes with non-Gaussian likelihoods","author":"Flaxman","year":"2015"},{"issue":"2","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1080\/10618600.2017.1375936","article-title":"Hierarchical decompositions for the computation of high-dimensional multivariate normal probabilities","volume":"27","author":"Genton","year":"2018","journal-title":"Journal of Computational and Graphical Statistics"},{"issue":"2","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1080\/10618600.2019.1652616","article-title":"Scalable Gaussian process computations using hierarchical matrices","volume":"29","author":"Geoga","year":"2020","journal-title":"Journal of Computational and Graphical Statistics"},{"issue":"483","key":"2023030906301602500_","doi-asserted-by":"crossref","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":"Journal of the American Statistical Association"},{"issue":"4","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/s00607-003-0019-1","article-title":"Construction and arithmetics of H-matrices","volume":"70","author":"Grasedyck","year":"2003","journal-title":"Computing"},{"key":"2023030906301602500_","volume-title":"Interpolating and approximating scattered 3D-data with hierarchical tensor product B-splines","author":"Greiner","year":"1996"},{"issue":"2","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1007\/s006070050015","article-title":"A sparse matrix arithmetic based on H-matrices. Part I: introduction to H-matrices","volume":"62","author":"Hackbusch","year":"1999","journal-title":"Computing"},{"key":"2023030906301602500_","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-47324-5","volume-title":"Hierarchical matrices: algorithms and analysis","author":"Hackbusch","year":"2015"},{"issue":"1","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00607-002-1450-4","article-title":"Data-sparse approximation by adaptive H2-matrices","volume":"69","author":"Hackbusch","year":"2002","journal-title":"Computing"},{"issue":"2","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1137\/090771806","article-title":"Finding structure with randomness: Stochastic algorithms for constructing approximate matrix decompositions","volume":"53","author":"Halko","year":"2009","journal-title":"SIAM Reviews"},{"key":"2023030906301602500_","volume-title":"Gaussian processes for big data","author":"Hensman","year":"2013"},{"key":"2023030906301602500_","first-page":"625","volume-title":"Advances in neural information processing systems","author":"Herbrich","year":"2003"},{"key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1017\/CBO9781139020411","volume-title":"Matrix analysis","author":"Horn","year":"2012"},{"issue":"1","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/S0377-0427(97)00100-3","article-title":"Surface fitting using convex tensor-product splines","volume":"84","author":"J\u00fcttler","year":"1997","journal-title":"Journal of Computational and Applied Mathematics"},{"issue":"5\u20136","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1002\/mana.201100010","article-title":"Small ball probabilities for smooth Gaussian fields and tensor products of compact operators","volume":"287","author":"Karol'","year":"2014","journal-title":"Mathematische Nachrichten"},{"key":"2023030906301602500_","volume-title":"Application of hierarchical matrices for solving multiscale problems","author":"Litvinenko","year":"2006"},{"key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.csda.2019.02.002","article-title":"Likelihood approximation with hierarchical matrices for large spatial datasets","volume":"137","author":"Litvinenko","year":"2019","journal-title":"Computational Statistics Data Analysis"},{"key":"2023030906301602500_","volume-title":"When Gaussian process meets big data: a review of scalable GPs","author":"Liu","year":"2018"},{"issue":"1","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1109\/LSP.2015.2503725","article-title":"A simple sampler for the horseshoe estimator","volume":"23","author":"Makalic","year":"2015","journal-title":"IEEE Signal Processing Letters"},{"key":"2023030906301602500_","first-page":"1193","volume-title":"Advances in neural information processing systems","author":"Nguyen-Tuong","year":"2009"},{"key":"2023030906301602500_","first-page":"1","article-title":"Highly scalable Bayesian geostatistical modeling via meshed Gaussian processes on partitioned domains","author":"Peruzzi","year":"2020","journal-title":"Journal of the American Statistical Association"},{"issue":"Dec","key":"2023030906301602500_","first-page":"1939","article-title":"A unifying view of sparse approximate Gaussian process regression","volume":"6","author":"Qui\u00f1onero-Candela","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"2023030906301602500_","volume-title":"Gaussian processes for machine learning","author":"Rasmussen","year":"2006"},{"issue":"5","key":"2023030906301602500_","doi-asserted-by":"crossref","DOI":"10.1029\/2011WR011778","article-title":"Efficient methods for large-scale linear inversion using a geostatistical approach","volume":"48","author":"Saibaba","year":"2012","journal-title":"Water Resources Research"},{"key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1016\/j.advwatres.2015.04.012","article-title":"Fast computation of uncertainty quantification measures in the geostatistical approach to solve inverse problems","volume":"82","author":"Saibaba","year":"2015","journal-title":"Advances in Water Resources"},{"issue":"1","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1111\/j.1467-9868.2011.01007.x","article-title":"A full scale approximation of covariance functions for large spatial data sets","volume":"74","author":"Sang","year":"2012","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"key":"2023030906301602500_","first-page":"143","volume-title":"Improved approximation algorithms for large matrices via random projections","author":"Sarlos","year":"2006"},{"key":"2023030906301602500_","first-page":"567","volume-title":"Artificial intelligence and statistics","author":"Titsias","year":"2009"},{"issue":"1","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.jspi.2005.09.005","article-title":"Posterior consistency of logistic Gaussian process priors in density estimation","volume":"137","author":"Tokdar","year":"2007","journal-title":"Journal of Statistical Planning and Inference"},{"key":"2023030906301602500_","first-page":"61","volume-title":"On building fast kd-trees for ray tracing, and on doing that in o (n log n)","author":"Wald","year":"2006"},{"issue":"4","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1007\/BF01456804","article-title":"Das asymptotische verteilungsgesetz der eigenwerte linearer partieller differentialgleichungen (mit einer anwendung auf die theorie der hohlraumstrahlung)","volume":"71","author":"Weyl","year":"1912","journal-title":"Mathematische Annalen"},{"issue":"1","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1111\/biom.12942","article-title":"Bayesian additive adaptive basis tensor product models for modeling high dimensional surfaces: an application to high-throughput toxicity testing","volume":"75","author":"Wheeler","year":"2019","journal-title":"Biometrics"},{"key":"2023030906301602500_","first-page":"682","volume-title":"Advances in neural information processing systems","author":"Williams","year":"2001"},{"key":"2023030906301602500_","first-page":"1775","volume-title":"Kernel interpolation for scalable structured Gaussian processes (kiss-GP)","author":"Wilson","year":"2015"},{"key":"2023030906301602500_","volume-title":"Thoughts on massively scalable Gaussian processes","author":"Wilson","year":"2015"},{"key":"2023030906301602500_","article-title":"Spatial factor modeling: a Bayesian matrix-normal approach for misaligned data","author":"Zhang","year":"2021","journal-title":"Biometrics"},{"issue":"3","key":"2023030906301602500_","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1002\/sam.11413","article-title":"Practical Bayesian modeling and inference for massive spatial data sets on modest computing environments","volume":"12","author":"Zhang","year":"2019","journal-title":"Statistical Analysis and Data Mining: The ASA Data Science Journal"}],"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/rssb.12494","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/rssb.12494","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/84\/4\/1198\/49463193\/jrsssb_84_4_1198.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/84\/4\/1198\/49463193\/jrsssb_84_4_1198.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T05:44:10Z","timestamp":1700459050000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/84\/4\/1198\/7073274"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,19]]},"references-count":59,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,4,19]]},"published-print":{"date-parts":[[2022,9,1]]}},"URL":"https:\/\/doi.org\/10.1111\/rssb.12494","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,9]]},"published":{"date-parts":[[2022,4,19]]}}}