{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:50:46Z","timestamp":1791391846107,"version":"4.3.3"},"reference-count":43,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004052","name":"King Abdullah University of Science and Technology","doi-asserted-by":"publisher","award":["ORFS-2022-CRG11-5069"],"award-info":[{"award-number":["ORFS-2022-CRG11-5069"]}],"id":[{"id":"10.13039\/501100004052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Advancements in information technology have enabled the creation of massive spatial datasets, driving the need for scalable and efficient computational methodologies. Although offering viable solutions, centralized frameworks are limited by vulnerabilities such as single-point failures and communication bottlenecks. This paper presents a fully decentralized framework tailored for parameter inference in spatial low-rank models to address these challenges. A key obstacle arises from the spatial dependence among observations, which prevents the log-likelihood from being expressed as a summation\u2014a critical requirement for decentralized optimization. To overcome this challenge, we propose a novel objective function leveraging the evidence lower bound, which facilitates the use of decentralized optimization techniques. Our approach employs a block descent method integrated with multi-consensus and dynamic consensus averaging for effective optimization. We prove the convexity of the new objective function in the vicinity of the true parameters, ensuring the convergence of the proposed method. We also present the first theoretical results that establish the consistency and asymptotic normality of the estimator within the context of spatial low-rank models. Simulations and real-world data experiments corroborate these theoretical findings, showcasing the robustness and scalability of the framework.<\/jats:p>","DOI":"10.1093\/jrsssb\/qkag113","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T18:35:21Z","timestamp":1783708521000},"source":"Crossref","is-referenced-by-count":1,"title":["Fully decentralized inference for spatial data using low-rank models"],"prefix":"10.1093","author":[{"given":"Jianwei","family":"Shi","sequence":"first","affiliation":[{"name":"Statistics Program, King Abdullah University of Science and Technology , Thuwal 23955 ,","place":["Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sameh","family":"Abdulah","sequence":"additional","affiliation":[{"name":"Applied Mathematics and Computational Sciences Program, King Abdullah University of Science and Technology , Thuwal 23955 ,","place":["Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Sun","sequence":"additional","affiliation":[{"name":"Statistics Program, King Abdullah University of Science and Technology , Thuwal 23955 ,","place":["Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6467-2998","authenticated-orcid":false,"given":"Marc G","family":"Genton","sequence":"additional","affiliation":[{"name":"Statistics Program, King Abdullah University of Science and Technology , Thuwal 23955 ,","place":["Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,10]]},"reference":[{"key":"2026071014351872100_qkag113-B1","author":"Abdulah","year":"2018"},{"key":"2026071014351872100_qkag113-B2","volume-title":"Handbook of mathematical functions with formulas, graphs, and mathematical tables","author":"Abramowitz","year":"1948"},{"issue":"1","key":"2026071014351872100_qkag113-B3","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1093\/biomet\/asp078","article-title":"Cross-covariance functions for multivariate random fields based on latent dimensions","volume":"97","author":"Apanasovich","year":"2010","journal-title":"Biometrika"},{"issue":"4","key":"2026071014351872100_qkag113-B4","doi-asserted-by":"publisher","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":"4","key":"2026071014351872100_qkag113-B5","doi-asserted-by":"publisher","first-page":"2037","DOI":"10.1137\/120887679","article-title":"On the convergence of block coordinate descent type methods","volume":"23","author":"Beck","year":"2013","journal-title":"SIAM Journal on Optimization"},{"issue":"518","key":"2026071014351872100_qkag113-B6","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1080\/01621459.2017.1285773","article-title":"Variational inference: A review for statisticians","volume":"112","author":"Blei","year":"2017","journal-title":"Journal of the American Statistical Association"},{"key":"2026071014351872100_qkag113-B7","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1214\/16-SS115","article-title":"A comparison of spatial predictors when datasets could be very large","volume":"10","author":"Bradley","year":"2016","journal-title":"Statistics Surveys"},{"issue":"541","key":"2026071014351872100_qkag113-B8","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1080\/01621459.2021.1919122","article-title":"Linear-cost covariance functions for gaussian random fields","volume":"118","author":"Chen","year":"2023","journal-title":"Journal of the American Statistical Association"},{"issue":"1","key":"2026071014351872100_qkag113-B9","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1111\/sjos.12722","article-title":"On maximizing the likelihood function of general geostatistical models","volume":"52","author":"Chu","year":"2025","journal-title":"Scandinavian Journal of Statistics"},{"issue":"514","key":"2026071014351872100_qkag113-B10","doi-asserted-by":"publisher","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":"none","key":"2026071014351872100_qkag113-B11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1214\/EJP.v20-3760","article-title":"Tail bounds via generic chaining","volume":"20","author":"Dirksen","year":"2015","journal-title":"Electronic Journal of Probability"},{"issue":"3-4","key":"2026071014351872100_qkag113-B12","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1561\/DBS","article-title":"The era of big spatial data: A survey","volume":"6","author":"Eldawy","year":"2016","journal-title":"Foundations and Trends\u00ae in Databases"},{"issue":"2","key":"2026071014351872100_qkag113-B13","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1080\/10618600.2018.1537924","article-title":"Efficient algorithms for Bayesian nearest neighbor gaussian processes","volume":"28","author":"Finley","year":"2019","journal-title":"Journal of Computational and Graphical Statistics"},{"issue":"3","key":"2026071014351872100_qkag113-B14","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1198\/106186006X132178","article-title":"Covariance tapering for interpolation of large spatial datasets","volume":"15","author":"Furrer","year":"2006","journal-title":"Journal of Computational and Graphical Statistics"},{"issue":"2","key":"2026071014351872100_qkag113-B15","doi-asserted-by":"publisher","first-page":"3050","DOI":"10.1214\/23-EJS2170","article-title":"Asymptotic analysis of ML-covariance parameter estimators based on covariance approximations","volume":"17","author":"Furrer","year":"2023","journal-title":"Electronic Journal of Statistics"},{"key":"2026071014351872100_qkag113-B16","author":"Gabrielli","year":"2023"},{"issue":"1","key":"2026071014351872100_qkag113-B17","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1080\/10618600.2017.1356324","article-title":"Hierarchical low rank approximation of likelihoods for large spatial datasets","volume":"27","author":"Huang","year":"2018","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"2026071014351872100_qkag113-B18","author":"Kang","year":"2024"},{"issue":"517","key":"2026071014351872100_qkag113-B19","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1080\/01621459.2015.1123632","article-title":"A multi-resolution approximation for massive spatial datasets","volume":"112","author":"Katzfuss","year":"2017","journal-title":"Journal of the American Statistical Association"},{"issue":"1","key":"2026071014351872100_qkag113-B20","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1214\/19-STS755","article-title":"A general framework for Vecchia approximations of Gaussian processes","volume":"36","author":"Katzfuss","year":"2021","journal-title":"Statistical Science"},{"issue":"2","key":"2026071014351872100_qkag113-B21","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/s11222-016-9627-4","article-title":"Parallel inference for massive distributed spatial data using low-rank models","volume":"27","author":"Katzfuss","year":"2017","journal-title":"Statistics and Computing"},{"issue":"1","key":"2026071014351872100_qkag113-B22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13174-015-0029-1","article-title":"Want to scale in centralized systems? Think P2P","volume":"6","author":"Kermarrec","year":"2015","journal-title":"Journal of Internet Services and Applications"},{"issue":"470","key":"2026071014351872100_qkag113-B23","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1198\/016214504000002014","article-title":"Analyzing nonstationary spatial data using piecewise gaussian processes","volume":"100","author":"Kim","year":"2005","journal-title":"Journal of the American Statistical Association"},{"issue":"3","key":"2026071014351872100_qkag113-B24","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/MSP.79","article-title":"Federated learning: Challenges, methods, and future directions","volume":"37","author":"Li","year":"2020","journal-title":"IEEE Signal Processing Magazine"},{"issue":"1","key":"2026071014351872100_qkag113-B25","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.orl.2009.09.006","article-title":"Resilience and reliability analysis of P2P network systems","volume":"38","author":"Li","year":"2010","journal-title":"Operations Research Letters"},{"key":"2026071014351872100_qkag113-B26","doi-asserted-by":"publisher","first-page":"Article 104715","DOI":"10.1016\/j.jpdc.2023.104715","article-title":"Tile low-rank approximations of non-gaussian space and space-time Tukey g-and-h random field likelihoods and predictions on large-scale systems","volume":"180","author":"Mondal","year":"2023","journal-title":"Journal of Parallel and Distributed Computing"},{"issue":"2","key":"2026071014351872100_qkag113-B27","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1080\/10618600.2014.914946","article-title":"A multiresolution gaussian process model for the analysis of large spatial datasets","volume":"24","author":"Nychka","year":"2015","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"2026071014351872100_qkag113-B28","author":"Pan","year":"2024"},{"issue":"1","key":"2026071014351872100_qkag113-B29","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1137\/17M1150116","article-title":"A Newton-based method for nonconvex optimization with fast evasion of saddle points","volume":"29","author":"Paternain","year":"2019","journal-title":"SIAM Journal on Optimization"},{"key":"2026071014351872100_qkag113-B30","doi-asserted-by":"publisher","first-page":"Article 110322","DOI":"10.1016\/j.automatica.2022.110322","article-title":"Distributed computation of fast consensus weights using ADMM","volume":"142","author":"Rokade","year":"2022","journal-title":"Automatica"},{"key":"2026071014351872100_qkag113-B31","doi-asserted-by":"crossref","DOI":"10.1017\/9781009160865","volume-title":"Large-scale convex optimization: Algorithms & analyses via monotone operators","author":"Ryu","year":"2022"},{"issue":"11","key":"2026071014351872100_qkag113-B32","doi-asserted-by":"publisher","first-page":"4769","DOI":"10.1109\/TAC.9","article-title":"Decentralized optimization over time-varying directed graphs with row and column-stochastic matrices","volume":"65","author":"Saadatniaki","year":"2020","journal-title":"IEEE Transactions on Automatic Control"},{"key":"2026071014351872100_qkag113-B33","volume-title":"Interpolation of spatial data: Some theory for kriging","author":"Stein","year":"2012"},{"key":"2026071014351872100_qkag113-B34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.spasta.2013.06.003","article-title":"Limitations on low rank approximations for covariance matrices of spatial data","volume":"8","author":"Stein","year":"2014","journal-title":"Spatial Statistics"},{"key":"2026071014351872100_qkag113-B35","doi-asserted-by":"publisher","first-page":"Article 100923","DOI":"10.1016\/j.softx.2021.100923","article-title":"Fast parallel calculation of modified bessel function of the second kind and its derivatives","volume":"17","author":"Takekawa","year":"2022","journal-title":"SoftwareX"},{"key":"2026071014351872100_qkag113-B36","volume-title":"The generic chaining: Upper and lower bounds of stochastic processes","author":"Talagrand","year":"2005"},{"key":"2026071014351872100_qkag113-B37","volume-title":"Asymptotic statistics","author":"Van der Vaart","year":"2000"},{"key":"2026071014351872100_qkag113-B38","doi-asserted-by":"crossref","DOI":"10.1017\/9781108627771","volume-title":"High-dimensional statistics: A non-asymptotic viewpoint","author":"Wainwright","year":"2019"},{"key":"2026071014351872100_qkag113-B39","doi-asserted-by":"publisher","first-page":"Article 100787","DOI":"10.1016\/j.spasta.2023.100787","article-title":"Which parameterization of the mat\u00e9rn covariance function?","volume":"58","author":"Wang","year":"2023","journal-title":"Spatial Statistics"},{"issue":"1","key":"2026071014351872100_qkag113-B40","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.sysconle.2004.02.022","article-title":"Fast linear iterations for distributed averaging","volume":"53","author":"Xiao","year":"2004","journal-title":"Systems & Control Letters"},{"key":"2026071014351872100_qkag113-B41","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.arcontrol.2019.05.006","article-title":"A survey of distributed optimization","volume":"47","author":"Yang","year":"2019","journal-title":"Annual Reviews in Control"},{"issue":"306","key":"2026071014351872100_qkag113-B42","first-page":"1","article-title":"Multi-consensus decentralized accelerated gradient descent","volume":"24","author":"Ye","year":"2023","journal-title":"Journal of Machine Learning Research"},{"issue":"4","key":"2026071014351872100_qkag113-B43","doi-asserted-by":"publisher","first-page":"1863","DOI":"10.5705\/ss.202021.0428","article-title":"Fixed-domain asymptotics under Vecchia\u2019s approximation of spatial process likelihoods","volume":"34","author":"Zhang","year":"2024","journal-title":"Statistica Sinica"}],"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jrsssb\/advance-article-pdf\/doi\/10.1093\/jrsssb\/qkag113\/68756295\/qkag113.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/advance-article-pdf\/doi\/10.1093\/jrsssb\/qkag113\/68756295\/qkag113.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T18:35:23Z","timestamp":1783708523000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/advance-article\/doi\/10.1093\/jrsssb\/qkag113\/8732170"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,10]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1093\/jrsssb\/qkag113","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,10]]},"article-number":"qkag113"}}