{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T14:37:53Z","timestamp":1787668673592,"version":"build-2736575974"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T00:00:00Z","timestamp":1668038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8,14]]},"abstract":"<jats:title>Summary<\/jats:title>\n               <jats:p>Structural learning of Gaussian graphical models in the presence of latent variables has long been a challenging problem. Chandrasekaran et al. (2012) proposed a convex program for estimating a sparse graph plus a low-rank term that adjusts for latent variables; however, this approach poses challenges from both computational and statistical perspectives. We propose an alternative, simple solution: apply a hard-thresholding operator to existing graph selection methods. Conceptually simple and computationally attractive, the approach of thresholding the graphical lasso is shown to be graph selection consistent in the presence of latent variables under a simpler minimum edge strength condition and at an improved statistical rate. The results are extended to estimators for thresholded neighbourhood selection and constrained $\\ell_{1}$-minimization for inverse matrix estimation as well. We show that our simple thresholded graph estimators yield stronger empirical results than existing methods for the latent variable graphical model problem, and we apply them to a neuroscience case study on estimating functional neural connections.<\/jats:p>","DOI":"10.1093\/biomet\/asac060","type":"journal-article","created":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T21:43:59Z","timestamp":1667857439000},"page":"681-697","source":"Crossref","is-referenced-by-count":8,"title":["Thresholded graphical lasso adjusts for latent variables"],"prefix":"10.1093","volume":"110","author":[{"given":"Minjie","family":"Wang","sequence":"first","affiliation":[{"name":"School of Statistics, University of Minnesota , 313 Ford Hall, 224 Church St SE, Minneapolis, Minnesota 55455, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Genevera I","family":"Allen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rice University , 6100 Main St., Houston, Texas 77005, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,11,10]]},"reference":[{"key":"2023081420144894100_B1","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":"2023081420144894100_B2","doi-asserted-by":"crossref","first-page":"2577","DOI":"10.1214\/08-AOS600","article-title":"Covariance regularization by thresholding","volume":"36","author":"Bickel,","year":"2008","journal-title":"Ann. Statist."},{"key":"2023081420144894100_B3","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1198\/jasa.2011.tm10560","article-title":"Adaptive thresholding for sparse covariance matrix estimation","volume":"106","author":"Cai,","year":"2011","journal-title":"J. Am. Statist. Assoc."},{"key":"2023081420144894100_B4","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1198\/jasa.2011.tm10155","article-title":"A constrained $\\ell_1$ minimization approach to sparse precision matrix estimation","volume":"106","author":"Cai,","year":"2011","journal-title":"J. Am. Statist. Assoc."},{"key":"2023081420144894100_B5","first-page":"1935","article-title":"Latent variable graphical model selection via convex optimization","volume":"40","author":"Chandrasekaran,","year":"2012","journal-title":"Ann. Statist."},{"key":"2023081420144894100_B6","first-page":"364","article-title":"Graphical lasso and thresholding: Equivalence and closed-form solutions","volume":"20","author":"Fattahi,","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"2023081420144894100_B7","first-page":"604","article-title":"Extended Bayesian information criteria for Gaussian graphical models","volume-title":"Advances in Neural Information Processing Systems 23 (NIPS 2010)","author":"Foygel,","year":"2010"},{"key":"2023081420144894100_B8","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":"2023081420144894100_B9","first-page":"1123","article-title":"Tuning parameter selection for penalized likelihood estimation of Gaussian graphical model","volume":"22","author":"Gao,","year":"2012","journal-title":"Statist. Sinica"},{"key":"2023081420144894100_B10","doi-asserted-by":"crossref","first-page":"1984","DOI":"10.1214\/12-AOS984","article-title":"Discussion: Latent variable graphical model selection via convex optimization","volume":"40","author":"Giraud,","year":"2012","journal-title":"Ann. Statist."},{"key":"2023081420144894100_B11","doi-asserted-by":"crossref","first-page":"2124","DOI":"10.1214\/16-EJS1160","article-title":"Thresholding least-squares inference in high-dimensional regression models","volume":"10","author":"Giurcanu,","year":"2016","journal-title":"Electron. J. Statist."},{"key":"2023081420144894100_B12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-019-53795-x","article-title":"A partial correlation screening approach for controlling the false positive rate in sparse Gaussian graphical models","volume":"9","author":"Lafit,","year":"2019","journal-title":"Sci. Rep."},{"key":"2023081420144894100_B13","article-title":"Thresholded adaptive validation: Tuning the graphical lasso for graph recovery","volume-title":"Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021","author":"Laszkiewicz,","year":"2021"},{"key":"2023081420144894100_B14","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1214\/15-EJS1013","article-title":"On model selection consistency of regularized M-estimators","volume":"9","author":"Lee,","year":"2015","journal-title":"Electron. J. Statist."},{"key":"2023081420144894100_B15","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1038\/nature05453","article-title":"Genome-wide atlas of gene expression in the adult mouse brain","volume":"445","author":"Lein,","year":"2007","journal-title":"Nature"},{"key":"2023081420144894100_B16","first-page":"1432","article-title":"Stability approach to regularization selection (StARS) for high dimensional graphical models","volume-title":"Proc. 23rd Int. Conf. Neural Information Processing Systems (NIPS \u201910)","author":"Liu,","year":"2010"},{"key":"2023081420144894100_B17","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1214\/08-EJS177","article-title":"Sup-norm convergence rate and sign concentration property of lasso and Dantzig estimators","volume":"2","author":"Lounici,","year":"2008","journal-title":"Electron. J. Statist."},{"key":"2023081420144894100_B18","first-page":"781","article-title":"Exact covariance thresholding into connected components for large-scale graphical lasso","volume":"13","author":"Mazumder,","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"2023081420144894100_B19","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":"2023081420144894100_B20","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1214\/07-AOS582","article-title":"Lasso-type recovery of sparse representations for high-dimensional data","volume":"37","author":"Meinshausen,","year":"2009","journal-title":"Ann. Statist."},{"key":"2023081420144894100_B21","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1214\/11-EJS631","article-title":"High-dimensional covariance estimation by minimizing $\\ell_1$-penalized log-determinant divergence","volume":"5","author":"Ravikumar,","year":"2011","journal-title":"Electron. J. Statist."},{"key":"2023081420144894100_B22","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1214\/14-AOS1286","article-title":"Asymptotic normality and optimalities in estimation of large Gaussian graphical models","volume":"43","author":"Ren,","year":"2015","journal-title":"Ann. Statist."},{"key":"2023081420144894100_B23","doi-asserted-by":"crossref","first-page":"1989","DOI":"10.1214\/12-AOS985","article-title":"Discussion: Latent variable graphical model selection via convex optimization","volume":"40","author":"Ren,","year":"2012","journal-title":"Ann. Statist."},{"key":"2023081420144894100_B24","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":"2023081420144894100_B25","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1198\/jasa.2009.0101","article-title":"Generalized thresholding of large covariance matrices","volume":"104","author":"Rothman,","year":"2009","journal-title":"J. Am. Statist. Assoc."},{"key":"2023081420144894100_B26","first-page":"3943","article-title":"Equivalence of graphical lasso and thresholding for sparse graphs","volume":"17","author":"Sojoudi,","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"2023081420144894100_B27","doi-asserted-by":"crossref","first-page":"2133","DOI":"10.1214\/16-AOS1521","article-title":"False discoveries occur early on the lasso path","volume":"45","author":"Su,","year":"2017","journal-title":"Ann. Statist."},{"key":"2023081420144894100_B28","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1214\/11-EJS624","article-title":"The adaptive and the thresholded lasso for potentially misspecified models (and a lower bound for the lasso)","volume":"5","author":"van de Geer,","year":"2011","journal-title":"Electron. J. Statist."},{"key":"2023081420144894100_B29","doi-asserted-by":"crossref","first-page":"1360","DOI":"10.1214\/09-EJS506","article-title":"On the conditions used to prove oracle results for the lasso","volume":"3","author":"van de Geer,","year":"2009","journal-title":"Electron. J. Statist."},{"key":"2023081420144894100_B30","article-title":"Graph quilting: Graphical model selection from partially observed covariances","author":"Vinci,","year":"2019","journal-title":"arXiv: 1912.05573"},{"key":"2023081420144894100_B31","doi-asserted-by":"crossref","first-page":"1978","DOI":"10.1214\/12-AOS981","article-title":"Discussion: Latent variable graphical model selection via convex optimization","volume":"40","author":"Wainwright,","year":"2012","journal-title":"Ann. Statist."},{"key":"2023081420144894100_B32","doi-asserted-by":"crossref","first-page":"2791","DOI":"10.1214\/19-AOS1906","article-title":"Which bridge estimator is the best for variable selection?","volume":"48","author":"Wang,","year":"2020","journal-title":"Ann. Statist."},{"key":"2023081420144894100_B33","doi-asserted-by":"crossref","first-page":"2178","DOI":"10.1214\/08-AOS646","article-title":"High-dimensional variable selection","volume":"37","author":"Wasserman,","year":"2009","journal-title":"Ann. Statist."},{"key":"2023081420144894100_B34","article-title":"A power analysis for model-X knockoffs with $\\ell_p$-regularized statistics","author":"Weinstein,","year":"2022","journal-title":"arXiv: 2007.15346v2"},{"key":"2023081420144894100_B35","first-page":"3813","article-title":"Graphical models via univariate exponential family distributions","volume":"16","author":"Yang,","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"2023081420144894100_B36","doi-asserted-by":"crossref","first-page":"e1004083","DOI":"10.1371\/journal.pcbi.1004083","article-title":"Improved estimation and interpretation of correlations in neural circuits","volume":"11","author":"Yatsenko,","year":"2015","journal-title":"PLoS Comp. Biol."},{"key":"2023081420144894100_B37","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":"2023081420144894100_B38","article-title":"Thresholded lasso for high dimensional variable selection and statistical estimation","author":"Zhou,","year":"2010","journal-title":"arXiv: 1002.1583v2"}],"container-title":["Biometrika"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biomet\/advance-article-pdf\/doi\/10.1093\/biomet\/asac060\/48845209\/asac060.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/110\/3\/681\/51111554\/asac060.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/110\/3\/681\/51111554\/asac060.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T20:36:43Z","timestamp":1692045403000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomet\/article\/110\/3\/681\/6820916"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,10]]},"references-count":38,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2022,11,10]]},"published-print":{"date-parts":[[2023,8,14]]}},"URL":"https:\/\/doi.org\/10.1093\/biomet\/asac060","relation":{},"ISSN":["0006-3444","1464-3510"],"issn-type":[{"value":"0006-3444","type":"print"},{"value":"1464-3510","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,9,1]]},"published":{"date-parts":[[2022,11,10]]}}}