Model selection and estimation in the Gaussian graphical model
The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
We propose penalized likelihood methods for estimating the concentration matrix in the Gaussian graphical model. The methods lead to a sparse and shrinkage estimator of the concentration matrix that is positive definite, and thus conduct model selection and estimation simultaneously. The implementation of the methods is nontrivial because of the positive definite constraint on the concentration matrix, but we show that the computation can be done effectively by taking advantage of the efficient maxdet algorithm developed in convex optimization. We propose a BIC-type criterion for the selection of the tuning parameter in the penalized likelihood methods. The connection between our methods and existing methods is illustrated. Simulations and real examples demonstrate the competitive performance of the new methods.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“These methods have the advantage to be able to recover the off diagonal structure of the covariance matrix.”
From Signal Estimation and Uncertainties Extraction in Terahertz Time-Domain Spectroscopy (2025) · cites this paper as [58]
Citations
Cites
Boyd, S., & Vandenberghe, L. (2004) · doi:10.1017/cbo9780511804441 · Cited by 56,601
Regression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482 · cited 1×
“This is similar to the idea of the lasso in linear regression (Tibshirani, 1996).”
MethodGraphical Models in Applied Multivariate Statistics
Goodall, C. R. (1991) · Technometrics · doi:10.1080/00401706.1991.10484880 · Cited by 1,849
Asymptotics for lasso-type estimators
Fu, W., & Knight, K. (2000) · The Annals of Statistics · doi:10.1214/aos/1015957397 · Cited by 1,276 · cited 2×
“, X(p)) be a p-dimensional random vector following a multivariate normal distribution Np(µ, ) with unknown mean µ and nonsingular covariance matrix .”
BackgroundMethodInfluentialHeuristics of instability and stabilization in model selection
Breiman, L. (1996) · The Annals of Statistics · doi:10.1214/aos/1032181158 · Cited by 1,146 · cited 1×
“As demonstrated by Breiman (1996), the discrete nature of such procedures often leads to instability of the estimator: small changes in the data may result in very different estimates.”
BackgroundBetter Subset Regression Using the Nonnegative Garrote
Breiman, L. (1995) · Technometrics · doi:10.1080/00401706.1995.10484371 · Cited by 1,043 · cited 2×
“As demonstrated by Breiman (1996), the discrete nature of such procedures often leads to instability of the estimator: small changes in the data may result in very different estimates.”
BackgroundMethodIntroduction to Graphical Modelling
Edwards, D. (2000) · Springer Texts in Statistics · doi:10.1007/978-1-4612-0493-0 · Cited by 825
Determinant Maximization with Linear Matrix Inequality Constraints
Vandenberghe, L., Boyd, S., & Wu, S.-P. (1998) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/s0895479896303430 · Cited by 652 · cited 2×
“To use the algorithm of Vandenberghe et al. (1998), it is also required that Fi, i = 1,. .”
MethodMultivariate Dependencies: Models, Analysis and Interpretation.
Murphy, S. A., Cox, D. R., & Wermouth, N. (1998) · Biometrics · doi:10.2307/2534028 · Cited by 487
Sparsistency and rates of convergence in large covariance matrix estimation
Lam, C., & Fan, J. (2009) · The Annals of Statistics · doi:10.1214/09-aos720 · Cited by 418
Cited by
Items 201–300 of 1,000
AUTOMATED ESTIMATION OF VECTOR ERROR CORRECTION MODELS
Liao, Z., & Phillips, P. C. B. (2015) · Econometric Theory · doi:10.1017/s026646661500002x · Cited by 66
Structured Learning of Gaussian Graphical Models.
Mohan, K., Chung, M. J.-Y., Han, S., Witten, D., Lee, S., & Fazel, M. (2012) · PubMed · Cited by 75
Decomposable Principal Component Analysis
Wiesel, A., & Hero, A. O. (2009) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2009.2025806 · Cited by 57
“In some problems approximate conditional independency structure can be learned from the observed data using methods such as [3], [8], and [22].”
MethodModel-based clustering with sparse covariance matrices
Fop, M., Murphy, T. B., & Scrucca, L. (2018) · Statistics and Computing · doi:10.1007/s11222-018-9838-y · Cited by 61
Bayesian graphical models for modern biological applications
Ni, Y., Baladandayuthapani, V., Vannucci, M., & Stingo, F. C. (2021) · Statistical Methods & Applications · doi:10.1007/s10260-021-00572-8 · Cited by 64
Multi-Task Learning of Gaussian Graphical Models
Honorio, J., & Samaras, D. (2010) · International Conference on Machine Learning · Cited by 74
A Log-Linear Graphical Model for inferring genetic networks from high-throughput sequencing data
Allen, G. I., & Liu, Z. (2012) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2012.6392619 · Cited by 71
“Many have developed methods to estimate high-dimensional Markov Networks for Gaussian or binary data by using sparsity to select the edges between genes [4], [5], [6], [7].”
MethodInfluentialInference of dynamic networks using time-course data
Kim, Y., 한승민, Choi, S., & Hwang, D. (2013) · Briefings in Bioinformatics · doi:10.1093/bib/bbt028 · Cited by 60
“Efficient algorithms for the inference using GGM have been developed [33–35].”
MethodJoint estimation of precision matrices in heterogeneous populations
Saegusa, T., & Shojaie, A. (2016) · Electronic Journal of Statistics · doi:10.1214/16-ejs1137 · Cited by 69
“Of particular interest is the use of sparsity inducing penalties, specifically the 1 or lasso penalty [30], which encourages sparsity in off-diagonal elements of the precision matrix [34, 7, 8, 33].”
BackgroundA note on the Lasso for Gaussian graphical model selection
Meinshausen, N. (2007) · Statistics & Probability Letters · doi:10.1016/j.spl.2007.09.014 · Cited by 66
Liang, F., Song, Q., & Qiu, P. (2015) · Journal of the American Statistical Association · doi:10.1080/01621459.2015.1012391 · Cited by 62
“Instead of working on nodewise regression, Yuan and Lin (2007) proposed to directly estimate the concentration matrix C by minimizing the penalized likelihood function where (cid:2) MLE denotes the maximum likelihood estimator of (cid:2) , C (cid:7) denotes the norm of C , and λ is the…”
BackgroundMethodCommunication-Avoiding Parallel Sparse-Dense Matrix-Matrix Multiplication
Koanantakool, P., Azad, A., Buluç, A., Morozov, D., Oh, S., Oliker, L., & Yelick, K. (2016) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps.2016.117 · Cited by 67
“Another application in statistical/machine learning is sparse inverse covariance selection (ICS) and related problems [8], [9], [10], [11], [12].”
BackgroundBlock-Diagonal Covariance Selection for High-Dimensional Gaussian Graphical Models
Devijver, É., & Gallopin, M. (2016) · Journal of the American Statistical Association · doi:10.1080/01621459.2016.1247002 · Cited by 65
Pathwise coordinate optimization for sparse learning: Algorithm and theory
Zhao, T., Liu, H., & Zhang, T. (2018) · The Annals of Statistics · doi:10.1214/17-aos1547 · Cited by 66
Estimating networks with jumps
Kolar, M., & Xing, E. P. (2012) · Electronic Journal of Statistics · doi:10.1214/12-ejs739 · Cited by 70
“Penalized maximum likelihood approach for estimating sparse precision matrix was proposed by [42].”
BackgroundMethodInfluentialStatistical inference of probabilistic origin-destination demand using day-to-day traffic data
Ma, W., & Qian, S. (2018) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2017.12.015 · Cited by 54
“Inspired by [97], a second order approximation to the MLE of the covariance matrix is used in Formulation 29.”
MethodEstimation of high-dimensional graphical models using regularized score matching
Lin, L., Drton, M., & Shojaie, A. (2016) · Electronic Journal of Statistics · doi:10.1214/16-ejs1126 · Cited by 87
“Two widelyused approaches are the graphical lasso or glasso (Yuan and Lin, 2007) and neighborhood selection (Meinshausen and Bühlmann, 2006).”
MethodRobust High-Dimensional Precision Matrix Estimation
Oellerer, V., & Croux, C. (2014) · Springer eBooks · doi:10.1007/978-3-319-22404-6_19 · Cited by 67
Joint Estimation of Multiple Precision Matrices with Common Structures
Liu, Y., & Lee, W. (2015) · PubMed · doi:10.17615/0s85-wh23 · Cited by 78
Chakraborty, S., Zhou, J., Balasubramanian, V. N., Panchanathan, S., Davidson, I. A. K., & Ye, J. (2013) · Proceedings · doi:10.1109/icdm.2013.69 · Cited by 51
“: Sparse inverse covariance estimation is typically achieved using the GLasso algorithm [27], which solves the following problem: K = arg min K0 (− log |K| + tr(KS) + λ||K|| 1 ) (9) where S is the sample covariance matrix of dimension p × p.”
BackgroundInfluentialYang, E., Ravikumar, P., Allen, G. I., & Liu, Z. (2013) · neural information processing systems · Cited by 84
Sparse Gaussian graphical models with unknown block structure
Marlin, B. M., & Murphy, K. P. (2009) · International Conference on Machine Learning · doi:10.1145/1553374.1553465 · Cited by 67
Estimation of Directed Acyclic Graphs Through Two-Stage Adaptive Lasso for Gene Network Inference
Han, S. W., Chen, G., Cheon, M.-S., & Zhong, J. (2016) · Journal of the American Statistical Association · doi:10.1080/01621459.2016.1142880 · Cited by 57
“…the score-and-search approach, several methods have been proposed to estimate the structure of graphical models through penalized likelihood, with most efforts focused on undirected graphs with L 1 -penalty (Yuan and Lin 2007; Friedman, Hastie, and Tibshirani 2008; Meinshausen and Buhlmann 2006).”
MethodCapturing Dynamic Connectivity From Resting State fMRI Using Time-Varying Graphical Lasso
Cai, B., Zhang, G., Zhang, A., Stephen, J. M., Wilson, T. W., Calhoun, V. D., & Wang, Y. (2018) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2018.2880428 · Cited by 57
“It was extended from the classical graphical lasso model [34], [35].”
Accelerated Mini-batch Randomized Block Coordinate Descent Method.
Zhao, T., Yu, M., Wang, Y., Arora, R., & Liu, H. (2014) · PubMed · Cited by 50
A Gaussian graphical model approach to climate networks
Zerenner, T., Friederichs, P., Lehnertz, K., & Hense, A. (2014) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/1.4870402 · Cited by 56
Optimization Algorithms for Graph Laplacian Estimation via ADMM and MM
Zhao, L., Wang, Y., Kumar, S., & Palomar, D. P. (2019) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2019.2925602 · Cited by 60
“In the field of GMRF model estimation, the authors of [12] and [13] adopted the 1 regularization in pursuit of a sparse graphical model.”
MethodSparse Nonparametric Graphical Models
Lafferty, J., Liu, H., & Wasserman, L. (2010) · KiltHub Repository · doi:10.1184/r1/6586907.v1 · Cited by 49
Weighted-lasso for structured network inference from time course dataPreprint
Charbonnier, C., Chiquet, J., & Ambroise, C. (2016) · Cited by 49
Change Point Estimation in High Dimensional Markov Random-Field Models
Roy, S., Atchadé, Y. F., & Michailidis, G. C. (2016) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/rssb.12205 · Cited by 69
Confidence regions for entries of a large precision matrix
Chang, J., Qiu, Y., Yao, Q., & Zou, T. (2018) · Journal of Econometrics · doi:10.1016/j.jeconom.2018.03.020 · Cited by 58
Sparse Regression Incorporating Graphical Structure Among Predictors
Yu, G., & Liu, Y. (2015) · Journal of the American Statistical Association · doi:10.1080/01621459.2015.1034319 · Cited by 51
“If the prior information is not available in some applications, we can construct the predictor graph by sparse estimation of the covariance (or precision) matrix of the predictors (Yuan and Lin 2007; Friedman, Hastie, and Tibshi-rani 2008; Cai, Liu, and Luo 2011).”
MethodMaximum Likelihood Covariance Estimation with a Condition Number Constraint
Won, J. H., & Kim, S.-J. (2006) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2006.354997 · Cited by 46
“In order to exploit sparsity using high-dimensional Gaussian graphical models (Lauritzen, 1996), various l1regularization techniques for the elements of the precision or the covariance matrix (or some function thereof) have also been studied by several researchers (Banerjee et al., 2006; Bickel and Levina, 2006; El Ka…”
MethodBipartite Approximation for Graph Wavelet Signal Decomposition
Zeng, J., Cheung, G., & Ortega, A. (2017) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2017.2733489 · Cited by 51
“[23], [36], [37].”
scLink: Inferring Sparse Gene Co-Expression Networks from Single-Cell Expression Data
Li, W. V., & Li, Y. (2021) · Genomics Proteomics & Bioinformatics · doi:10.1016/j.gpb.2020.11.006 · Cited by 47
“Second, scLink adapts the Gaussian graphical model [29] to distinguish direct associations between genes from indirect ones and leads to sparse networks.”
Chu, H., Ibrahim, J. G., Khondker, Z., Lin, W., & Hongtu Zhu, B. (2013) · Statistics and Its Interface · doi:10.4310/sii.2013.v6.n2.a8 · Cited by 46
“In the frequentist framework, significant work has been done on model selection and precision (covariance) matrix estimation in Gaussian models [1, 8, 11, 12, 31].”
Joint Bayesian variable and graph selection for regression models with network‐structured predictors
Peterson, C. B., Stingo, F. C., & Vannucci, M. (2015) · Statistics in Medicine · doi:10.1002/sim.6792 · Cited by 50
“In particular, the graphical lasso [24, 25, 26], which imposes an L 1 penalty on the sum of the absolute values of the entries of Ω , is a popular method for achieving the desired sparsity in estimation of Ω .”
MethodPartial Gaussian Graphical Model Estimation
Yuan, X., & Zhang, T. (2014) · IEEE Transactions on Information Theory · doi:10.1109/tit.2013.2296784 · Cited by 53
“For GGMs estimation, a popular formulation is maximum likelihood estimation with ℓ1-penalty on the entries of the precision matrix (Yuan & Lin, 2007; Banerjee et al., 2008; Rothman et al., 2008).”
MethodGaussian Graphical Models Identify Networks of Dietary Intake in a German Adult Population
Iqbal, K., Buijsse, B., Wirth, J., Schulze, M. B., Floegel, A., & Boeing, H. (2016) · Journal of Nutrition · doi:10.3945/jn.115.221135 · Cited by 47
“Although a number of methods exist (29, 30) for achieving sparsity in the precision matrix, graphical lasso (31) is a fast, efficient approach for structure”
MethodGlobal Testing and Large-Scale Multiple Testing for High-Dimensional Covariance Structures
Cai, T. (2016) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-060116-053754 · Cited by 58
“…(2008), Rothman et al. (2009), Cai and Liu (2011), and Fan et al. (2011), penalized log-likelihood estimation in Huang et al. (2006), Yuan and Lin (2007), d’Aspremont et al. (2008), Banerjee et al. (2008), Rothman et al. (2008), Lam and Fan (2009), Ravikumar et al. (2011), and Chandrasekaran…”
BackgroundRegularized Gaussian Mixture Model for High-Dimensional Clustering
Zhao, Y., Shrivastava, A. K., & Tsui, K. (2018) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2846404 · Cited by 48
“Two representative sparse estimation are considered: glasso and YL (the method proposed in [40]).”
BackgroundMethodGeneralized Score Matching for Non-Negative Data
Yu, S., Drton, M., & Shojaie, A. (2018) · PubMed · doi:10.48550/arxiv.1812.10551 · Cited by 70
“term in the above display which can be motivated by a prior distribution under which the number of edges in the conditional independence graph is uniformly distributed; see also Żak-Szatkowska and Bogdan (2011) and Barber and Drton (2015).”
BackgroundMethodInfluentialLearning extremal graphical structures in high dimensions
Engelke, S., Lalancette, M., & Stanislav Volgushev, A. (2026) · The Annals of Statistics · doi:10.1214/25-aos2594 · Cited by 46
An Extragradient-Based Alternating Direction Method for Convex Minimization
Lin, T., Ma, S., & Zhang, S. (2015) · Foundations of Computational Mathematics · doi:10.1007/s10208-015-9282-8 · Cited by 50
“The other problem is the so-called sparse inverse covariance selection, which is also known as the graphical lasso problem [1,13,52].”
BackgroundThe degrees of freedom of partly smooth regularizers
Vaiter, S., Deledalle, C., Fadili, J. M., Gabriel Peyré, A., & Dossal, C. (2016) · Annals of the Institute of Statistical Mathematics · doi:10.1007/s10463-016-0563-z · Cited by 59
“Strictly speaking, the `(1)-penalized likelihood formulation of the graphical Lasso in (Yuan and Lin 2007) ((3) or (6) in that reference) does not fall within our framework.”
BackgroundSILGGM: An extensive R package for efficient statistical inference in large-scale gene networks
Zhang, R., Ren, Z., & Chen, W. (2018) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1006369 · Cited by 53
Cancer Genetic Network Inference Using Gaussian Graphical Models
Zhao, H., & Duan, Z.-H. (2019) · Bioinformatics and Biology Insights · doi:10.1177/1177932219839402 · Cited by 55
Discovering Sparse Covariance Structures With the Isomap
Wagaman, A. S., & Levina, E. (2009) · Journal of Computational and Graphical Statistics · doi:10.1198/jcgs.2009.08021 · Cited by 44
“A sparse permutation-invariant estimator of the concentration matrix based on adding an l 1 penalty to the normal likelihood has been studied by d’Aspremont, Banerjee, and El Ghaoui (2008), Yuan and Lin (2007), and Rothman et al. (2008).”
MethodBootstrap inference for network construction with an application to a breast cancer microarray study
Li, S., Hsu, L.-I., Peng, J., & Wang, P. (2013) · The Annals of Applied Statistics · doi:10.1214/12-aoas589 · Cited by 52
“For example, Yuan and Lin (2007) proposed a sparse estimator of the concentration matrix via maximizing the L 1 penalized log-likelihood.”
BackgroundAdaptive First-Order Methods for General Sparse Inverse Covariance Selection
Lu, Z. (2010) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/080742531 · Cited by 44
“All computations are performed on an Intel Xeon 2.66 GHz machine with Red Hat Linux version 8.”
BackgroundInfluentialA Hierarchical Bayesian Framework for Constructing Sparsity-inducing PriorsPreprint
Lee, A., Caron, F., Doucet, A., & Holmes, C. C. (2010) · arXiv (Cornell University) · doi:10.48550/arxiv.1009.1914 · Cited by 45
“For the purpose of covariance matrix estimation, `1-regularization has been used on entries of the precision matrix Ω of a Gaussian graphical model [14, 15].”
MethodIntroduction to correlation networks: Interdisciplinary approaches beyond thresholding
Masuda, N., Boyd, Z. M., Garlaschelli, D., & Mucha, P. J. (2025) · Physics Reports · doi:10.1016/j.physrep.2025.06.002 · Cited by 54
Covariance Estimation in Decomposable Gaussian Graphical Models
Wiesel, A., Eldar, Y. C., & Hero, A. O. (2009) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2009.2037350 · Cited by 43
“A standard benchmark used for testing (inverse) covariance e stimation and covariance selection is the call center data set [35], [21], [27].”
MethodEfficient distributed learning with sparsity
Wang, J., Kolar, M., Srebro, N., & Zhang, T. (2017) · Rare & Special e-Zone (The Hong Kong University of Science and Technology) · Cited by 159
Graphical Models for Ordinal Data
Guo, J., Levina, E., Michailidis, G. C., & Zhu, J. (2014) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2014.889023 · Cited by 53
“Estimation of such models from high dimensional data under a sparsity assumption has attracted a lot of interest in the statistics and machine learning literature, including regularized likelihood and regression methods (see (Yuan and Lin, 2007; Banerjee et al., 2008; Friedman et al., 2008; Rothman et al., 2008; Fan e…”
BackgroundElliptical graphical modelling
Vogel, D., & Fried, R. (2011) · Biometrika · doi:10.1093/biomet/asr037 · Cited by 49
“We want to name a few: • In recent years the research on Gaussian graphical models has been particularly driven by the desire to analyze high-dimensional data sets, (e.g. Drton and Perlman, 2004; Meinshausen and Bühlmann, 2006; Castelo and Roverato, 2006; Yuan and Lin, 2007; Verzelen and Villers, 2009).”
BackgroundA computationally fast alternative to cross-validation in penalized Gaussian graphical models
Vujačić, I., Abbruzzo, A., & Wit, E. C. (2015) · Journal of Statistical Computation and Simulation · doi:10.1080/00949655.2014.992020 · Cited by 44
“where (ω̂ij,λ)1≤i<j≤p are the estimated parameters.[5] As we pointed out in Section 2, unlike the AIC, the (E)BIC has a graph selection consistency property.”
BackgroundState-Space Network Topology Identification From Partial Observations
Coutiño, M., Isufi, E., Maehara, T., & Leus, G. J. T. (2020) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2020.2975393 · Cited by 51
“Despite many works focus on the problem of topology identification [22], [23] or Gaussian graphical modeling [24], [25], most of these approaches only leverage a model based on the so-called graph filters [26], graph signal smoothness [27], [28], or enforce a particular structure by dictonary learning [29] or by a pen…”
BackgroundChen, Z., & Leng, C. (2015) · Journal of the American Statistical Association · doi:10.1080/01621459.2015.1077712 · Cited by 48
“Fourth, it is possible to study dynamic estimation of the inverse of a covariance matrix that elucidates conditional independence structures among the variables (Yuan and Lin 2007).”
BackgroundInnovated scalable efficient estimation in ultra-large Gaussian graphical models
Fan, Y., & Lv, J. (2016) · The Annals of Statistics · doi:10.1214/15-aos1416 · Cited by 55
“The former class includes, for example, [13, 22, 37, 45, 47].”
MethodLauritzen, S. L. (1996) · Oxford University Press eBooks · doi:10.1093/9780191775284.003.0002 · Cited by 41
Variational inference for sparse network reconstruction from count dataPreprint
Chiquet, J., Mariadassou, M., & Robin, S. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.03120 · Cited by 47
“We use the gradients which are given by When λ ą 0 , Problem (9b) is easily shown to be equivalent to solving We recognize a sparse multivariate Gaussian maximum likelihood problem (Yuan and Lin, 2007, Banerjee et al., 2008), efficiently solved by the graphical-Lasso algorithm (Friedman et al., 2008).”
BackgroundMethodGraph Selection with GGMselect
Giraud, C., Huet, S., & Verzélen, N. (2012) · Statistical Applications in Genetics and Molecular Biology · doi:10.1515/1544-6115.1625 · Cited by 44
On Time Varying Undirected Graphs
Kolar, M., & Xing, E. P. (2018) · KiltHub Repository · doi:10.1184/r1/6476213 · Cited by 53
A Proximal Point Algorithm for Log-Determinant Optimization with Group Lasso Regularization
Yang, J., Sun, D., & Toh, K.-C. (2013) · SIAM Journal on Optimization · doi:10.1137/120864192 · Cited by 46
“, in [62] the authors utilized standard IPMs to solve (1.”
BackgroundMethodResultInfluentialTensor Graphical Lasso (TeraLasso)
Greenewald, K. H., Zhou, S., & Hero, A. O. (2019) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/rssb.12339 · Cited by 60
On Joint Estimation of Gaussian Graphical Models for Spatial and Temporal Data
Lin, Z., Wang, T., Yang, C., & Zhao, H. (2017) · Biometrics · doi:10.1111/biom.12650 · Cited by 45
“Various approaches have been proposed to estimate the graph (Meinshausen and Bühlmann, 2006; Yuan and Lin, 2007; Friedman et al., 2008; Cai et al., 2011; Dobra et al., 2011; Wang et al., 2012; Orchard et al., 2013).”
Doubly functional graphical models in high dimensions
Qiao, X., Qian, C., James, G. M., & Guo, S. (2019) · Biometrika · doi:10.1093/biomet/asz072 · Cited by 49
Mohammad-Djafari, A. (2015) · Entropy · doi:10.3390/e17063989 · Cited by 43
“When the order K is fixed, the estimation of the parameters θ is a very well-known problem, and there are likelihood based [66] or Bayesian approaches for that [67].”
MethodA LASSO Chart for Monitoring the Covariance Matrix
Maboudou‐Tchao, E. M., & Diawara, N. (2013) · Quality Technology & Quantitative Management · doi:10.1080/16843703.2013.11673310 · Cited by 39
“Yuan, M. and Lin, Y. (2007).”
MethodInfluentialLearning Temporal Causal Graphs for Relational Time-Series Analysis
Liu, Y., Niculescu-Mizil, A., Lozano, A. C., & Lu, Y. C. (2010) · International Conference on Machine Learning · Cited by 39
High-Dimensional Gaussian Graphical Regression Models with Covariates
Zhang, J., & Li, Y. (2022) · Journal of the American Statistical Association · doi:10.1080/01621459.2022.2034632 · Cited by 51
Differential network analysis from cross-platform gene expression data
Zhang, X.-F., Ou-Yang, L., Zhao, X., & Yan, H. (2016) · Scientific Reports · doi:10.1038/srep34112 · Cited by 41
“To deal with this problem, graphical lasso, which maximize a penalized log-likelihood, has been proposed 21–23 : where S is the sample covariance matrix, λ is a nonnegative tuning parameter, || Θ || 1 denotes the sum of the absolute values of the elements of Θ , det( ⋅ ) is the determinant of a…”
InfluentialDetecting shot boundary with sparse coding for video summarization
Li, J., Yao, T., Ling, Q., & Mei, T. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.04.065 · Cited by 38
MPLasso: Inferring microbial association networks using prior microbial knowledge
Lo, C., & Mărculescu, R. (2017) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1005915 · Cited by 43
ROCKET: Robust confidence intervals via Kendall’s tau for transelliptical graphical models
Barber, R. F., & Kolar, M. (2018) · The Annals of Statistics · doi:10.1214/17-aos1663 · Cited by 47
Loh, P., & Tan, X. T. (2018) · Electronic Journal of Statistics · doi:10.1214/18-ejs1427 · Cited by 65
“Although several methods, notably the graphical Lasso (GLasso) (Yuan and Lin, 2007; Friedman et al., 2008) and the method of constrained `1-minimization for inverse matrix estimation (CLIME) (Cai et al., 2011), have been proposed for high-dimensional precision matrix estimation, robust estimation…”
MethodInfluentialTopology identification of undirected consensus networks via sparse inverse covariance estimation
Hassan-Moghaddam, S., Dhingra, N. K., & Jovanović, M. R. (2016) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2016.7798973 · Cited by 38
Epskamp, S., Waldorp, L., Mõttus, R., & Borsboom, D. (2016) · arXiv (Cornell University) · Cited by 43
Multi‐response phylogenetic mixed models: concepts and application
Halliwell, B., Holland, B. R., & Yates, L. A. (2025) · Biological reviews/Biological reviews of the Cambridge Philosophical Society · doi:10.1111/brv.70001 · Cited by 39
Hypothesis Testing of Matrix Graph Model with Application to Brain Connectivity Analysis
Yin, X., & Li, L. (2016) · Biometrics · doi:10.1111/biom.12633 · Cited by 40
“, 2014), nonparanormal distribution (Meinshausen and Buhlmann, 2006; Yuan and Lin, 2007; Friedman et al., 2008; Cai et al., 2011; Ravikumar et al., 2011), and matrix-valued graph model (Leng and Tang, 2012; Yin and Li, 2012; Zhou, 2014).”
BackgroundDynamic Multivariate Functional Data Modeling via Sparse Subspace Learning
Zhang, C., Yan, H., Lee, S., & Shi, J. (2020) · Technometrics · doi:10.1080/00401706.2020.1800516 · Cited by 40
“In particular, Qiao, Guo, and James (2019) extended the graphical lasso (Yuan and Lin 2007) to multivariate functional data by constructing a penalized log-Gaussian likelihood on the functional PCA scores.”
BackgroundAdaptive estimation in structured factor models with applications to overlapping clustering
Bing, X., Bunea, F., Ning, Y., & Wegkamp, M. H. (2020) · The Annals of Statistics · doi:10.1214/19-aos1877 · Cited by 60
“…tailored to our purpose, and its optimal solution ̂ adds a novel estimator for C−1 to the rich literature on precision matrix estimation (Cai, Liu and Luo (2011), Cai, Liu and Zhou (2016), Friedman, Hastie and Tibshirani (2008), Meinshausen and Bühlmann (2006), Yuan and Lin (2007), to name a few).”
Tan, X., Sirichand, K., Vivian, A. J., & Wang, X. (2021) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2021.07.005 · Cited by 40
Monitoring the covariance matrix with fewer observations than variables
Maboudou‐Tchao, E. M., & Agboto, V. K. (2013) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2013.02.028 · Cited by 37
Graph Estimation From Multi-Attribute Data
Kolar, M., Liu, H., & Xing, E. P. (2012) · PubMed · doi:10.1184/r1/6475742 · Cited by 49
Learning the Dependence Graph of Time Series with Latent FactorsPreprint
Jalali, A., & Sanghavi, S. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1106.1887 · Cited by 38
“While ours problem is, in a sense, also one of sparse linear model selection, two differences between our setting and these papers is that they do not have any latent factors, and theoretical guarantees typically require independent samples.”
BackgroundSparse Logistic Regression Learns All Discrete Pairwise Graphical ModelsPreprint
Wu, S., Sanghavi, S., & Dimakis, A. G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.11905 · Cited by 52
“Others have also considered 1 -regularization (e.g., [LGK07, YL07, BGd08, JRVS11, YALR12, AE12]) for structure learning of Markov random fields but they all require certain assumptions about the graph and hence their methods do not work for general graphs.”
BackgroundLearning Sparse Gaussian Markov Networks Using a Greedy Coordinate Ascent Approach
Scheinberg, K., & Rish, I. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15939-8_13 · Cited by 43
“The consistency result in [21] suggests that for our formulation, to obtain an accurate asymptotic structure recovery, we should pick λ that grows with n, but so that its growth is slower than √ n.”
BackgroundMethodInfluentialTensor Graphical Model: Non-Convex Optimization and Statistical Inference
Lyu, X., Sun, W. W., Wang, Z., Liu, H., Yang, J. Y., & Cheng, G. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2907679 · Cited by 55
Estimating Time-Varying Graphical Models
Yang, J., & Peng, J. (2019) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2019.1647848 · Cited by 49
“…have been proposed to learn GGMs when the number of variables is large (relative to the sample size), including Meinshausen & B¨uhlmann (2006), Yuan & Lin (2007), Friedman et al. (2008), Banerjee et al. (2008), Rothman et al. (2008), Peng et al. (2009), Lam & Fan (2009), Ravikumar et al.…”
BackgroundNonconvex Sparse Graph Learning under Laplacian Constrained Graphical Model
Ying, J., Cardoso, J. V. D. M., & Palomar, D. P. (2020) · Rare & Special e-Zone (The Hong Kong University of Science and Technology) · Cited by 75
Estimation of covariance matrix via the sparse Cholesky factor with lasso
Chang, C., & Tsay, R. S. (2010) · Journal of Statistical Planning and Inference · doi:10.1016/j.jspi.2010.04.048 · Cited by 40
“and Lin [ 22 ] identified the sparse elements in the inverse covariance matrix by imposing the lasso type of”
BackgroundGaussian graphical models with applications to omics analyses
Shutta, K. H., Vito, R. D., Scholtens, D. M., & Balasubramanian, R. (2022) · Statistics in Medicine · doi:10.1002/sim.9546 · Cited by 44
“12,34,35 Around the same time, Yuan and Lin, 12 Banerjee et al, 34 and Friedman et al 35 separately developed methodology for estimating a sparse precision matrix by maximizing the 𝓁 1 penalized likelihood of a GGM with respect to the space of non-negative definite precision matrices Θ : where…”
BackgroundDrew, K., Müller, C. L., Bonneau, R., & Marcotte, E. M. (2017) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1005625 · Cited by 35
Liang, F., Jia, B., Xue, J., Li, Q., & Luo, Y. (2018) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/rssb.12279 · Cited by 39
“This example has been used by many researchers; see, for example, Yuan and Lin (2007), Mazumder and Hastie (2012) and Liang et al. (2015) to illustrate different GGM methods.”
MethodCopula Gaussian Graphical Models for Functional Data
Solea, E., & Li, B. (2020) · Journal of the American Statistical Association · doi:10.1080/01621459.2020.1817750 · Cited by 49
“The functional graphical model is a continuation of the recent research on graphical models for scalar-valued observations (Meinshausen and Bühlmann 2006; Yuan and Lin 2007), which can be traced back to Darroch, Lauritzen, and Speed (1980) and Lauritzen, Speed, and Vijayan (1984).”
MethodA pathway for multivariate analysis of ecological communities using copulas
Anderson, M. J., de Valpine, P., Punnett, A. J., & Miller, A. E. (2019) · Ecology and Evolution · doi:10.1002/ece3.4948 · Cited by 39
“…we are using Gaussian copulas, a variety of methods for regularizing the inverse covariance matrix may be considered (Friedman, Hastie, & Tibshirani, 2008; Schäfer & Strimmer, 2005; Ullah & Jones, 2015; Yuan & Lin, 2007); for simplicity, we shall not pursue the topic of regularization further here.”
MethodSpectral analysis of high-dimensional time series
Fiecas, M. J. A., Leng, C., Liu, W., & Yu, Y. (2019) · Electronic Journal of Statistics · doi:10.1214/19-ejs1621 · Cited by 53
Bank credit risk networks: Evidence from the Eurozone
Brownlees, C. T., Hans, C., & Nualart, E. (2020) · Journal of Monetary Economics · doi:10.1016/j.jmoneco.2020.03.014 · Cited by 35
Metadata
- Authors
- Yuan, M., & Lin, Y.
- Affiliations
- Georgia Institute of Technology (US)
- University of Wisconsin–Madison (US)
- Venue
- Biometrika
- Publisher
- Oxford University Press (OUP)
- Published
- 2007-02-07
- Volume
- 94
- Issue
- 1
- Pages
- 19-35
- ISSN
- 0006-3444 (ISSN-L)
- 1464-3510
- OpenAlex
- W2081746825
- Semantic Scholar
- 20ee888ca9c3bae784f266405b4d6395c6f32955
- Cited by
- 1,627
- References
- 16
- Citations by year
- 2026: 43 · 2025: 66 · 2024: 60 · 2023: 64 · 2022: 86 · 2021: 131 · 2020: 112 · 2019: 147 · 2018: 142 · 2017: 91 · 2016: 123 · 2015: 98 · 2014: 109 · 2013: 86 · 2012: 85
- FWCI
- 38.99
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Biometrika (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- HighWire Press Open Archive (submittedVersion)
- Funders
- National Science Foundation
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Inference
- Physical Sciences › Mathematics › Statistics and Probability › Random Matrices and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Keywords
- Gaussian graphical models, model selection, penalized likelihood, sparse estimation, shrinkage estimation, hyperparameter optimization, covariance structure
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.