{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T07:45:06Z","timestamp":1790495106772,"version":"4.1.0"},"reference-count":60,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2019,10,10]],"date-time":"2019-10-10T00:00:00Z","timestamp":1570665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11,1]]},"abstract":"<jats:title>Summary<\/jats:title>\n                  <jats:p>The paper introduces a multiway tensor generalization of the bigraphical lasso which uses a two-way sparse Kronecker sum multivariate normal model for the precision matrix to model parsimoniously conditional dependence relationships of matrix variate data based on the Cartesian product of graphs. We call this tensor graphical lasso generalization TeraLasso. We demonstrate by using theory and examples that the TeraLasso model can be accurately and scalably estimated from very limited data samples of high dimensional variables with multiway co-ordinates such as space, time and replicates. Statistical consistency and statistical rates of convergence are established for both the bigraphical lasso and TeraLasso estimators of the precision matrix and estimators of its support (non-sparsity) set respectively. We propose a scalable composite gradient descent algorithm and analyse the computational convergence rate, showing that the composite gradient descent algorithm is guaranteed to converge at a geometric rate to the global minimizer of the TeraLasso objective function. Finally, we illustrate TeraLasso by using both simulation and experimental data from a meteorological data set, showing that we can accurately estimate precision matrices and recover meaningful conditional dependence graphs from high dimensional complex data sets.<\/jats:p>","DOI":"10.1111\/rssb.12339","type":"journal-article","created":{"date-parts":[[2019,10,10]],"date-time":"2019-10-10T06:10:59Z","timestamp":1570687859000},"page":"901-931","source":"Crossref","is-referenced-by-count":24,"title":["Tensor Graphical Lasso (TeraLasso)"],"prefix":"10.1093","volume":"81","author":[{"given":"Kristjan","family":"Greenewald","sequence":"first","affiliation":[{"name":"IBM Research , Cambridge , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of California , Riverside , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"suffix":"III","given":"Alfred","family":"Hero","sequence":"additional","affiliation":[{"name":"University of Michigan , Ann Arbor , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2019,10,10]]},"reference":[{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1214\/09-AOAS314","article-title":"Transposable regularized covariance models with an application to missing data imputation","volume":"4","author":"Allen","year":"2010","journal-title":"Ann. Appl. Statist."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1063\/1.52392","article-title":"A matrix representation of lie algebraic methods for design of nonlinear beam lines","volume":"391","author":"Andrianov","year":"1997","journal-title":"AIP Conf. Proc."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"899","DOI":"10.1198\/jasa.2009.ap07058","article-title":"Modeling spatiotemporal forest health monitoring data","volume":"104","author":"Augustin","year":"2009","journal-title":"J. Am. Statist. Ass."},{"key":"2023022002412705200_","first-page":"485","article-title":"Model selection through sparse maximum likelihood estimation for multivariate Gaussian or binary data","volume":"9","author":"Banerjee","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1137\/080716542","article-title":"A fast iterative shrinkage-thresholding algorithm for linear inverse problems","volume":"2","author":"Beck","year":"2009","journal-title":"SIAM J. Imgng Sci."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"3307","DOI":"10.1137\/120900204","article-title":"An error analysis of Galerkin projection methods for linear systems with tensor product structure","volume":"51","author":"Beckermann","year":"2013","journal-title":"SIAM J. Numer. Anal."},{"key":"2023022002412705200_","volume-title":"Convex Optimization","author":"Boyd","year":"2009"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"2668","DOI":"10.1109\/TAC.2014.2328757","article-title":"Controllability and observability of network-of-networks via Cartesian products","volume":"59","author":"Chapman","year":"2014","journal-title":"IEEE Trans. Autom. Control"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"1168","DOI":"10.1137\/050626090","article-title":"Signal recovery by proximal forward-backward splitting","volume":"4","author":"Combettes","year":"2005","journal-title":"Multsc. Modlng Simuln"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1093\/biomet\/68.1.265","article-title":"Some matrix-variate distribution theory: notational considerations and a Bayesian application","volume":"68","author":"Dawid","year":"1981","journal-title":"Biometrika"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1137\/1012045","article-title":"The direct solution of the discrete Poisson equation on a rectangle","volume":"12","author":"Dorr","year":"1970","journal-title":"SIAM Rev."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/S0169-7439(03)00029-7","article-title":"Multivariate calibration with temperature interaction using two-dimensional penalized signal regression","volume":"66","author":"Eilers","year":"2003","journal-title":"Chemometr. Intell. Lab. Syst."},{"key":"2023022002412705200_","first-page":"528","volume-title":"Proc. Association for Computing Machinery Fall Jt Computer Conf.","author":"Ellner","year":"1986"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/S0169-7439(02)00089-8","article-title":"Recent developments in CANDECOMP\/PARAFAC algorithms: a critical review","volume":"65","author":"Faber","year":"2003","journal-title":"Chemometr. Intell. Lab. Syst."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1198\/016214501753382273","article-title":"Variable selection via nonconcave penalized likelihood and its oracle properties","volume":"96","author":"Fan","year":"2001","journal-title":"J. Am. Statist. Ass."},{"key":"2023022002412705200_","first-page":"869","volume-title":"Proc. Conf. Computer Vision and Pattern Recognition","author":"Fey","year":"2018"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1093\/biostatistics\/kxm045","article-title":"Sparse inverse covariance estimation with the graphical Lasso","volume":"9","author":"Friedman","year":"2008","journal-title":"Biostatistics"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1007\/s00607-003-0037-z","article-title":"Existence and computation of low Kronecker-rank approximations for large linear systems of tensor product structure","volume":"72","author":"Grasedyck","year":"2004","journal-title":"Computing"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"6368","DOI":"10.1109\/TSP.2015.2472364","article-title":"Robust Kronecker product PCA for spatio-temporal covariance estimation","volume":"63","author":"Greenewald","year":"2015","journal-title":"IEEE Trans. Signl Process."},{"key":"2023022002412705200_","first-page":"5832","volume-title":"Advances in Neural Information Processing Systems 30","author":"Greenewald","year":"2017"},{"key":"2023022002412705200_","first-page":"1574","volume-title":"Advances in Neural Information Processing Systems","author":"Guillot","year":"2012"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","DOI":"10.1201\/b10959","volume-title":"Handbook of Product Graphs","author":"Hammack","year":"2011"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/0167-9473(94)90132-5","article-title":"PARAFAC: parallel factor analysis","volume":"18","author":"Harshman","year":"1994","journal-title":"Computnl Statist. Data Anal."},{"key":"2023022002412705200_","first-page":"627","article-title":"Equivariant and scale-free Tucker decomposition models","volume":"11","author":"Hoff","year":"2016","journal-title":"Baysn Anal."},{"key":"2023022002412705200_","first-page":"1266","article-title":"Structural growth trajectories and rates of change in the first 3 months of infant brain development","volume":"71","author":"Holland","year":"2014","journal-title":"J. Am. Med. Ass. Neurol."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","DOI":"10.1201\/b10613","volume-title":"Topics in Graph Theory: Graphs and Their Cartesian Product","author":"Imrich","year":"2008"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1214\/15-AOS1414","article-title":"Tensor decompositions and sparse log-linear models","volume":"45","author":"Johndrow","year":"2017","journal-title":"Ann. Statist."},{"key":"2023022002412705200_","first-page":"1229","volume-title":"Proc. Int. Conf. Machine Learning","author":"Kalaitzis","year":"2013"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1137\/07070111X","article-title":"Tensor decompositions and applications","volume":"51","author":"Kolda","year":"2009","journal-title":"SIAM Rev."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1016\/j.acha.2017.10.002","article-title":"Splines and wavelets on circulant graphs","volume":"47","author":"Kotzagiannidis","year":"2019","journal-title":"Appl. Computnl Harm. Anal."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1137\/090756843","article-title":"Krylov subspace methods for linear systems with tensor product structure","volume":"31","author":"Kressner","year":"2010","journal-title":"SIAM J. Matr. Anal. Appl."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1177\/1471082X1001100104","article-title":"P-spline ANOVA-type interaction models for spatio-temporal smoothing","volume":"11","author":"Lee","year":"2011","journal-title":"Statist. Modllng"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1080\/01621459.2012.706133","article-title":"Sparse matrix graphical models","volume":"107","author":"Leng","year":"2012","journal-title":"J. Am. Statist. Ass."},{"key":"2023022002412705200_","first-page":"476","volume-title":"Advances in Neural Information Processing Systems","author":"Loh","year":"2013"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"2455","DOI":"10.1214\/16-AOS1530","article-title":"Support recovery without incoherence: a case for nonconvex regularization","volume":"45","author":"Loh","year":"2017","journal-title":"Ann. Statist."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1109\/TAC.1966.1098323","article-title":"Observers for multivariable systems","volume":"11","author":"Luenberger","year":"1966","journal-title":"IEEE Trans. Autom. Control"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1016\/0005-2795(75)90109-9","article-title":"Comparison of the predicted and observed secondary structure of t4 phage lysozyme","volume":"405","author":"Matthews","year":"1975","journal-title":"Biochim. Biophys. Acta"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"1436","DOI":"10.1214\/009053606000000281","article-title":"High-dimensional graphs and variable selection with the lasso","volume":"34","author":"Meinshausen","year":"2006","journal-title":"Ann. Statist."},{"key":"2023022002412705200_","first-page":"372","article-title":"A method of solving a convex programming problem with convergence rate o (1\/k2)","volume":"27","author":"Nesterov","year":"1983","journal-title":"Sov. Math. Dokl."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4419-8853-9","volume-title":"Introductory Lectures on Convex Optimization: Applied Optimization","author":"Nesterov","year":"2004"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/s10107-012-0629-5","article-title":"Gradient methods for minimizing composite objective function","volume":"140","author":"Nesterov","year":"2013","journal-title":"Math. Programmng"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.dsp.2015.08.014","article-title":"CANDECOMP\/PARAFAC model order selection based on reconstruction error in the presence of Kronecker structured colored noise","volume":"48","author":"Pouryazdian","year":"2016","journal-title":"Digtl Signl Process."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"2421","DOI":"10.1890\/11-1412.1","article-title":"Climate and weather influences on spatial temporal patterns of mountain pine beetle populations in Washington and Oregon","volume":"93","author":"Preisler","year":"2012","journal-title":"Ecology"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1214\/08-EJS176","article-title":"Sparse permutation invariant covariance estimation","volume":"2","author":"Rothman","year":"2008","journal-title":"Electron. J. Statist."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"1699","DOI":"10.1214\/17-EJS1234","article-title":"High dimensional errors-in-variables models with dependent measurements","volume":"11","author":"Rudelson","year":"2017","journal-title":"Electron. J. Statist."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1109\/42.921480","article-title":"Numerical aspects of spatio-temporal current density reconstruction from EEG-\/MEG-data","volume":"20","author":"Schmitt","year":"2001","journal-title":"IEEE Trans. Med. Imgng"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"1436","DOI":"10.1080\/03081087.2012.743541","article-title":"Backward error and perturbation bounds for high order Sylvester tensor equation","volume":"61","author":"Shi","year":"2013","journal-title":"Lin. Multlin. Alg."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/s10107-010-0394-2","article-title":"Approximation accuracy, gradient methods, and error bound for structured convex optim","volume":"125","author":"Tseng","year":"2010","journal-title":"Math. Progrmmng"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"5347","DOI":"10.1109\/TSP.2013.2279355","article-title":"Covariance estimation in high dimensions via Kronecker product expansions","volume":"61","author":"Tsiligkaridis","year":"2013","journal-title":"IEEE Trans. Signl. Process."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"1743","DOI":"10.1109\/TSP.2013.2240157","article-title":"On convergence of Kronecker graphical lasso algorithms","volume":"61","author":"Tsiligkaridis","year":"2013","journal-title":"IEEE Trans. Signl Process."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF02289464","article-title":"Some mathematical notes on three-mode factor analysis","volume":"31","author":"Tucker","year":"1966","journal-title":"Psychometrika"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/S0377-0427(00)00393-9","article-title":"The ubiquitous Kronecker product","volume":"123","author":"Van Loan","year":"2000","journal-title":"J. Computnl Appl. Math."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1109\/TSP.2007.907834","article-title":"On estimation of cov. matrices with Kronecker product structure","volume":"56","author":"Werner","year":"2008","journal-title":"IEEE Trans. Signl. Process."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"1025","DOI":"10.1111\/j.1541-0420.2006.00574.x","article-title":"Low-rank scale-invariant tensor product smooths for generalized additive mixed models","volume":"62","author":"Wood","year":"2006","journal-title":"Biometrics"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1080\/01621459.2016.1180986","article-title":"Smoothing parameter and model selection for general smooth models","volume":"111","author":"Wood","year":"2016","journal-title":"J. Am. Statist. Ass."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1093\/biomet\/asm018","article-title":"Model selection and estimation in the Gaussian graphical model","volume":"94","author":"Yuan","year":"2007","journal-title":"Biometrika"},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1214\/09-AOS729","article-title":"Nearly unbiased variable selection under minimax concave penalty","volume":"38","author":"Zhang","year":"2010","journal-title":"Ann. Statist."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1214\/13-AOS1187","article-title":"Gemini: graph estimation with matrix variate normal instances","volume":"42","author":"Zhou","year":"2014","journal-title":"Ann. Statist."},{"key":"2023022002412705200_","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/s10994-010-5180-0","article-title":"Time varying undirected graphs","volume":"80","author":"Zhou","year":"2010","journal-title":"Mach. Learn."},{"key":"2023022002412705200_","first-page":"2975","article-title":"High-dimensional covariance estimation based on Gaussian graphical models","volume":"12","author":"Zhou","year":"2011","journal-title":"J. Mach. Learn. Res."}],"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Frssb.12339","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/81\/5\/901\/49269807\/jrsssb_81_5_901.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/81\/5\/901\/49269807\/jrsssb_81_5_901.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T08:52:23Z","timestamp":1695286343000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/81\/5\/901\/7048364"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,10]]},"references-count":60,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2019,10,10]]},"published-print":{"date-parts":[[2019,11,1]]}},"URL":"https:\/\/doi.org\/10.1111\/rssb.12339","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,11]]},"published":{"date-parts":[[2019,10,10]]}}}