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 801–900 of 1,000
Efficient Latent Variable Graphical Model Selection via Split Bregman MethodPreprint
Ye, G., Wang, Y., Chen, Y., & Xie, X. S. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1110.3076 · Cited by 7
“Keywords and phrases:Gaussian graphical models, Variable selection, Alternative direction method of multipliers.”
MethodA Hierarchical Graphical Model for Big Inverse Covariance Estimation with an Application to fMRIPreprint
Luo, X. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1403.4698 · Cited by 8
“ed according three major estimation principals: penalized conditional likelihood or neighborhood selection (Meinshausen and Bu¨hlmann, 2006; Yuan, 2010), penalized full likelihood or Graphical lasso (Yuan and Lin, 2007; Banerjee et al., 2008; Friedman et al., 2008), and algebraic properties (Cai et al., 2011; Liu and…”
BackgroundMethodRobust Inverse Covariance Estimation under Noisy Measurements
Wang, J.-K. (2015) · Cited by 7
A Junction Tree Framework for Undirected Graphical Model SelectionPreprint
Vats, D., & Nowak, R. D. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1304.4910 · Cited by 10
“Equation (32) can be solved using algorithms in Yuan and Lin (2007); Banerjee et al. (2008); Scheinberg et al. (2010); Hsieh et al. (2011).”
BackgroundMethodA Scalable Algorithm for Gaussian Graphical Models with Change-PointsPreprint
Atchadé, Y. F., & Bybee, L. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.04306 · Cited by 7
Predictive Learning on Hidden Tree-Structured Ising ModelsPreprint
Nikolakakis, K. E., Kalogerias, D. S., & Sarwate, A. D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.04700 · Cited by 7
“, 2010), the GLasso (Yuan and Lin, 2007; Banerjee et al., 2008), or coordinate descent approaches (Friedman et al.”
BackgroundMethodSignal Estimation and Uncertainties Extraction in Terahertz Time-Domain Spectroscopy
Denakpo, E., Hannotte, T., Osseiran, N., Orieux, F., & Peretti, R. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3554287 · Cited by 6
“There are also methods that rely on solving the covariance selection problem to approximate sparse inverse covariance matrices with lasso regularization [57], [58], [59].”
Graphical lasso and thresholding: Conditions for equivalence
Sojoudi, S. (2016) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2016.7799354 · Cited by 6
“Graphical lasso is one of the most commonly used techniques for estimating the inverse covariance matrix [8]– [10].”
MethodModule-based regularization improves Gaussian graphical models when observing noisy data
Neuman, M., Calatayud, J., Tasselius, V., & Rosvall, M. (2024) · Applied Network Science · doi:10.1007/s41109-024-00612-8 · Cited by 7
“A common approach to infer a Gaussian graphical model is the graphical lasso (GLASSO) [7, 8], which estimates the precision matrix while ensuring sparsity through l1-regularization.”
MethodGraphical model inference with external network data
Jewson, J., Li, L., Battaglia, L., Hansen, S. E., Rossell, D., & Zwiernik, P. (2024) · Biometrics · doi:10.1093/biomtc/ujae151 · Cited by 11
Estimation of the Error Structure in Multivariate Response Linear Regression Models
Liu, R., & Yu, G. (2025) · Wiley Interdisciplinary Reviews Computational Statistics · doi:10.1002/wics.70021 · Cited by 6
“…another large body of literature has developed in Gaussian graphical models (GGMs, see, e.g., Meinshausen and Bühlmann 2006; Friedman et al. 2007; Yuan and Lin 2007, among others), where the target of estimation and interpretation is the inverse covariance matrix Ω ∗ = Σ ∗− 1 , also widely…”
D-trace estimation of a precision matrix using adaptive Lasso penalties
Avagyan, V., Alonso, A. M., & Nogales, F. J. (2016) · Advances in Data Analysis and Classification · doi:10.1007/s11634-016-0272-8 · Cited by 6
“In addition, we consider other patterns commonly used in the prior literature, such as pattern 4 (Yuan and Lin 2007; Friedman et al. 2008), its modified version (pattern 5) and decay structure [pattern 6— Cai et al.”
MethodStructural learning of causal networks
He, Y., Jia, J., & Geng, Z. (2017) · Behaviormetrika · doi:10.1007/s41237-017-0018-8 · Cited by 6
“But we also point out that they all need incoherent condition such that these algorithms give correct graphical model asymptotically (Mein-shausen and Bu¨hlmann 2006; Yuan and Lin 2007; Cai et al. 2011).”
BackgroundMethodCompositional Stochastic Average Gradient for Machine Learning and Related Applications
Hsieh, T.-Y., EL‐Manzalawy, Y., Sun, Y., & Honavar, V. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03493-1_77 · Cited by 6
Ravikumar, V., Xu, T. W., Al‐Holou, W. N., Fattahi, S., & Rao, A. U. K. (2023) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2023.3282028 · Cited by 7
“This line of work begins by the inference of a single precision matrix, which can be achieved by `1-regularized MLE, also known as Graphical Lasso (GL) [39, 4, 89].”
MethodpISTA: Preconditioned Iterative Soft Thresholding Algorithm for Graphical Lasso
Shalom, G., Treister, E., & Yavneh, I. (2024) · SIAM Journal on Scientific Computing · doi:10.1137/22m1496128 · Cited by 6
Multi-Task Learning for Gaussian Graphical Regressions with High Dimensional Covariates
Zhang, J., & Li, Y. (2024) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2024.2421246 · Cited by 8
“…graphical models is expanding, most existing models assume a homogeneous population with a common graphical model (Meinshausen and Bühlmann 2006; Yuan and Lin 2007; Friedman, Hastie, and Tibshirani 2008; Peng et al. 2009) or several stratified graphical models (Guo et al. 2011; Danaher, Wang,…”
Statistical inference for smoothed quantile regression with streaming data
Xie, J., Yan, X., Jiang, B., & Kong, L. (2024) · Journal of Econometrics · doi:10.1016/j.jeconom.2024.105924 · Cited by 6
Trans-Glasso: A Transfer Learning Approach to Precision Matrix Estimation
Zhao, B., Ma, C., & Kolar, M. (2026) · Journal of the American Statistical Association · doi:10.1080/01621459.2025.2602856 · Cited by 6
Overlapping Decomposition for Gaussian Graphical Modeling
Song, G., Han, L., & Xie, K. (2015) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2015.2407358 · Cited by 6
“Thus, our problem is essentially different from community structure detection.”
BackgroundMitra, R., Müller, P., Qiu, P., & Ji, Y. (2014) · Cancer Informatics · doi:10.4137/cin.s13984 · Cited by 6
“Network analysis of reverse phase protein expression data: characterizing protein signatures in acute myeloid leukemia cytogenetic categories t (8; 21) and inv (16).”
Estimation of high-dimensional partially-observed discrete Markov random fields
Atchadé, Y. F. (2014) · Electronic Journal of Statistics · doi:10.1214/14-ejs946 · Cited by 7
“We derive an estimation error bound that highlights the effect of the misspecification.”
MethodLearning the Dependency Structure of Latent Factors
He, Y., Qi, Y., Kavukcuoglu, K., & Park, H. (2012) · neural information processing systems · Cited by 9
Adjusted regularization of cortical covariance
Vinci, G., Ventura, V., Smith, M. A., & Kass, R. E. (2018) · Journal of Computational Neuroscience · doi:10.1007/s10827-018-0692-x · Cited by 9
Bybee, L., & Atchadé, Y. F. (2018) · Journal of Machine Learning Research · Cited by 6
NExUS: Bayesian simultaneous network estimation across unequal sample sizes
Das, P., Peterson, C. B., Do, K.-A., Akbani, R., & Baladandayuthapani, V. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz636 · Cited by 6
“Various approaches for Gaussian graphical model estimation (Yuan and Lin, 2007; Friedman et al., 2008; Wang, 2012, 2015; Baladandayuthapani et al., 2014) have been proposed over the years.”
MethodPan, Y., & Mai, Q. (2019) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2019.106884 · Cited by 7
Integrating approximate single factor graphical models
Fan, X., Fang, K., Ma, S., & Zhang, Q. (2019) · Statistics in Medicine · doi:10.1002/sim.8408 · Cited by 6
Park, G., & Kim, Y. (2020) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2020.107084 · Cited by 6
Fast and Privacy-Preserving Federated Joint Estimator of Multi-sUGMs
Tan, X. J., Ma, T., & Su, T. (2021) · IEEE Access · doi:10.1109/access.2021.3099400 · Cited by 7
Thi, H. A. L., Phan, D. N., & Dinh, T. P. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.09.039 · Cited by 6
Sun, L., & Liang, F. (2022) · Statistics in Medicine · doi:10.1002/sim.9493 · Cited by 6
“The conditions (6) to (8) imply that the MNR method can be implemented in many different ways.”
InfluentialFrequentist Model Averaging for Undirected Gaussian Graphical Models
Liu, H., & Zhang, X. (2022) · Biometrics · doi:10.1111/biom.13758 · Cited by 6
“Existing methods include the penalized likelihood (Yuan & Lin, 2007; Friedman et al., 2008; Fan et al., 2009; Ravikumar et al., 2011; Zhang & Zou, 2014) and the penalized regression methods (Meinshausen & Bühlmann, 2006; Peng et al., 2009; Yuan, 2010; Cai et al., 2011; Ren et al., 2015; Cai et al.,…”
MethodTime-Varying Graph Learning Under Structured Temporal Priors
Zhang, X., & Wang, Q. (2022) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco55093.2022.9909847 · Cited by 6
Variance Matrix Priors for Dirichlet Process Mixture Models With Gaussian Kernels
Jing, W., Papathomas, M., & Liverani, S. (2024) · International Statistical Review · doi:10.1111/insr.12595 · Cited by 6
“…of a sparse precision or covariance matrix, the graphical and adaptive graphical lasso within the frequentist framework [ Yuan and Lin (2007); Friedman et al. (2008); Fan et al. (2009)] are equivalent to placing the Laplace prior on the off-diagonal elements and the exponential prior on the…”
Statistical Inference for High-Dimensional Spectral Density Matrix
Chang, J., Jiang, Q., McElroy, T., & Shao, X. (2025) · Journal of the American Statistical Association · doi:10.1080/01621459.2025.2468013 · Cited by 6
“The popular regularization approaches used in covariance and precision matrix estimation, such as graphical LASSO (Yuan and Lin 2007), thresholding (Bickel and Levina 2008), and constrained L 1 minimization (Cai, Liu, and Luo 2011), have been extended to estimate either the high-dimensional spectral density matrix or…”
Discriminatively Trained Sparse Inverse Covariance Matrices for Speech Recognition
Zhang, W., & Fung, P. (2014) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2014.2312548 · Cited by 6
“This is what the authors did in [42] and [37], especially on experiments with real-world data.”
BackgroundInference of Regulatory Networks from Microarray Data with R and the Bioconductor Package qpgraph
Castelo, R., & Roverato, A. (2011) · Methods in molecular biology · doi:10.1007/978-1-61779-400-1_14 · Cited by 6
Graph-Guided Banding of the Covariance Matrix
Bien, J. (2018) · Journal of the American Statistical Association · doi:10.1080/01621459.2018.1442720 · Cited by 6
“ARTICLE HISTORY Received May Revised February KEYWORDS Covariance estimation; High-dimensional; Hierarchical group lasso; Network”
BackgroundMethodZhang, H., Zheng, Y., Yoon, G., Zhang, Z., Gao, T., Joyce, B. T., Zhang, W., Schwartz, J. D., Vokonas, P., Colicino, E., et al. (2017) · Statistical Applications in Genetics and Molecular Biology · doi:10.1515/sagmb-2016-0073 · Cited by 6
“Tables 1 and 2 report the results,which include the rate that the correctmodel (CMR) is selected I{S = S}, the false positive rate (FPR) |S∖S|/|S|, the false negative rate (FNR) |S∖S|/(d−|S|), and themodel error (ME) tr[(B̂−B)ΣX(B̂−B)] (Yuan and Lin, 2007).”
BackgroundA Comparison of Methods for Estimating the Determinant of High-Dimensional Covariance Matrix
Hu, Z., Dong, K., Dai, W., & Tong, T. (2017) · The International Journal of Biostatistics · doi:10.1515/ijb-2017-0013 · Cited by 7
“To estimate the high-dimensional precisionmatrixK = G–1, [19] and [20] proposed to solve the following optimization problem: K̂ = argmin K>0 {tr(SnK) – log |K| + +‖K‖1}, where tr(⋅) is the trace, ‖ ⋅ ‖1 is the 1 norm, and + is a tuning parameter.”
BackgroundGraphical nonconvex optimization via an adaptive convex relaxation
Sun, Q., Tan, K. M., Liu, H., & Zhang, T. (2018) · Rare & Special e-Zone (The Hong Kong University of Science and Technology) · Cited by 6
Assisted graphical model for gene expression data analysis
Fan, X., Fang, K., Ma, S., Wang, S., & Zhang, Q. (2019) · Statistics in Medicine · doi:10.1002/sim.8112 · Cited by 6
Estimating sparse networks with hubs
McGillivray, A., Khalili, A., & Stephens, D. A. (2020) · Journal of Multivariate Analysis · doi:10.1016/j.jmva.2020.104655 · Cited by 6
“The HGL applies an L 1 -penalty to the off-diagonal elements of Z , and L 1 and group lasso (Yuan and Lin, 2007) penalties to the columns of V .”
BackgroundMethodInferring large graphs using $$\ell _1$$ ℓ 1 -penalized likelihood
Champion, M., Picheny, V., & Vignes, M. (2017) · Statistics and Computing · doi:10.1007/s11222-017-9769-z · Cited by 8
Multivariate Gaussian network structure learning
Du, X., & Ghosal, S. (2018) · Journal of Statistical Planning and Inference · doi:10.1016/j.jspi.2018.07.009 · Cited by 6
High‐dimensional covariance matrix estimation using a low‐rank and diagonal decomposition
Wu, Y., Qin, Y., & Zhu, M. (2019) · Canadian Journal of Statistics · doi:10.1002/cjs.11532 · Cited by 8
“…in the precision matrix suggest conditional independence; it can be achieved directly by imposing an 𝓁1 penalization on the precision matrix (Yuan & Lin, 2007; Rothman et al., 2008; Banerjee, El Ghaoui, & d’Aspremont, 2008; Friedman, Hastie, & Tibshirani, 2008; Lam & Fan, 2009; Cai, Liu, & Luo,…”
MethodQuadratic Sparse Gaussian Graphical Model Estimation Method for Massive Variables
Zhang, J., Wang, M., Li, Q., Wang, S., Chang, X., & Wang, B. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/410 · Cited by 6
Estimating heterogeneous gene regulatory networks from zero-inflated single-cell expression data
Wu, Q., & Luo, X. (2022) · The Annals of Applied Statistics · doi:10.1214/21-aoas1582 · Cited by 7
“The application of GGM to recover gene regulatory networks from bulk-level expression has received attentions from both perspectives of frequentist (Yuan and Lin (2007), Friedman, Hastie and Tibshirani (2008)) and Bayesian (Dobra, Lenkoski and Rodriguez (2011), Wang (2012), Wang and Li (2012),…”
BackgroundMethodGilbert, H., van der Laan, M. J., & Dudoit, S. (2009) · Collection of Biostatistics Research Archive · Cited by 7
Multiple Response Regression for Gaussian Mixture Models with Known Labels
Lee, W., Du, Y., Sun, W., Hayes, D. N., & Liu, Y. (2012) · Statistical Analysis and Data Mining The ASA Data Science Journal · doi:10.1002/sam.11158 · Cited by 6
“To this end, we use the set-up of Fan and Li [17], Yuan and Lin [12], and Zou [18].”
MethodPrior elicitation and variable selection for bayesian quantile regression
Alhamzawi, R. (2013) · Brunel University Research Archive (BURA) (Brunel University London) · Cited by 6
High-dimensional Principal Component Analysis
Amini, A. (2011) · UC Berkeley · Cited by 8
Bayes Regularized Graphical Model Estimation in High DimensionsPreprint
Kundu, S., Baladandayuthapani, V., & Mallick, B. K. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1308.3915 · Cited by 6
“…traditional methods for covariance/ precision matrix estimation (and hence graphical model estimation) may not perform well (Whittaker 1990; Edward 2000), prompting the development of a number of frequentist approaches (Meinshausen and Buhlmann, 2006; Yuan and Lin; 2007; Peng et al., 2009).”
BackgroundMethodAdaptive Inferential Method for Monotone Graph InvariantsPreprint
Lu, J., Neykov, M., & Liu, H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.09114 · Cited by 6
“The consistency of graph recovery has been shown for many graphical model estimators including CLIME (Cai et al., 2011), neighborhood selection (Meinshausen and Bühlmann, 2006; Zhou et al., 2009), graphical Lasso (Lam and Fan, 2009) and transellipitical graphical model (Liu et al., 2012b) and all these results need t…”
BackgroundMethodInfluentialInter-Subject Analysis: Inferring Sparse Interactions with Dense Intra-GraphsPreprint
Ma, C., Lu, J., & Liu, H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.07036 · Cited by 6
“Estimators for the precision matrix including the maximum likelihood estimator and the column-wise estimator have been considered in (Yuan and Lin, 2007; Banerjee et al., 2008; Rothman et al., 2008; Friedman et al., 2008; Ravikumar et al., 2011; Meinshausen and B¨uhlmann, 2006; Yuan, 2010; Cai et…”
MethodDistributionally Robust Formulation and Model Selection for the Graphical LassoPreprint
Cisneros‐Velarde, P., Oh, S., & Petersen, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.08975 · Cited by 6
“where kij is the (i, j) entry of K and λ > 0 is a userspecified regularization parameter (Banerjee et al., 2008; Friedman et al., 2007; Yuan and Lin, 2007).”
BackgroundHigh-Dimensional Inference for Cluster-Based Graphical ModelsPreprint
Eisenach, C., Bunea, F., Yang, N., & Dinicu, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.05139 · Cited by 16
“…number of observations led to renewed interest in these models, and to a very large body of literature, including Meinshausen and B¨uhlmann (2006); Yuan and Lin (2007); Friedman et al. (2008); Verzelen (2008); Lam and Fan (2009); Rothman et al. (2008); Peng et al. (2009); Ravikumar et al.…”
BackgroundLearning Continuous Exponential Families Beyond GaussianPreprint
Ren, C. X., Misra, S., Vuffray, M., & Lokhov, A. Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.09198 · Cited by 9
“Many efficient algorithms of different types are known for learning Gaussian graphical models Meinshausen and Bühlmann (2006); Tibshirani (1996); Yuan and Lin (2007); d’Aspremont et al. (2008); Ravikumar et al. (2009); Anandkumar et al. (2012); Cai et al. (2011, 2016), including polynomial-time…”
BackgroundMulti-task Learning of Order-Consistent Causal GraphsPreprint
Chen, X., Sun, H., Ellington, C. N., Xing, E. P., & Song, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.02545 · Cited by 16
“Unlike the large literature of research on undirected graphical models [24, 25, 26, 27], statistical guarantees for score-based DAG estimator have been available only in recent years.”
BackgroundExponential Series Approaches for Nonparametric Graphical ModelsPreprint
Janofsky, E. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.03537 · Cited by 6
“As a special case we detail a new approach to sparse precision matrix estimation which has statistical performance competitive with the graphical lasso [Yuan and Lin, 2007] and computational performance competitive with the state-of-the-art glasso algorithm [Friedman et al., 2008].”
MethodInfluentialHierarchical array priors for ANOVA decompositionsPreprint
Volfovsky, A., & Hoff, P. D. (2012) · arXiv (Cornell University) · Cited by 6
Kringle, E. A., Tucker, D., Wu, Y., Lv, N., Kannampallil, T., Barve, A., Dosala, S., Wittels, N. E., Dai, R., & Ma, J. (2023) · Mental health and physical activity · doi:10.1016/j.mhpa.2023.100512 · Cited by 6
Chen, L., & Tsao, H.-S. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae731 · Cited by 5
A novel approach for estimating multi-attribute Gaussian copula graphical models
Li, L., Yu, Y., Liang, W., & Zou, F. (2025) · Statistics & Probability Letters · doi:10.1016/j.spl.2025.110413 · Cited by 5
Reconstructing gene network structure and dynamics from single cell data
Chen, F., & Li, C. (2025) · Bioinformatics · doi:10.1093/bioinformatics/btaf598 · Cited by 5
“We incorporate Lasso regularization into the GGM to enhance the sparsity of the network structure (Friedman et al. 2008, Yuan and Lin 2007).”
Minimax entropy: The statistical physics of optimal models
Carcamo, D. P., Weaver, N., Dixit, P. D., & Lynn, C. W. (2025) · Physical review. E · doi:10.1103/kr9x-q59y · Cited by 5
“For a Gaussian model, computing covariances amounts to inverting the interaction (or precision) matrix, so the maximum entropy problem can be solved efficiently [45,46].”
Pesonen, M., Nevalainen, J., Potter, S. S., Datta, S., & Datta, S. (2017) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2017.2665495 · Cited by 8
“One group of such methods uses sparsity to select the edges (associations) between the nodes (components) of the network [2], [8], [9], [10].”
MethodJoint estimation and regularized aggregation of brain network in FMRI data
Chung, J., Jackson, B. S., McDowell, J. E., & Park, C. (2021) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2021.109374 · Cited by 5
Online Graph Learning In Dynamic Environments
Zhang, X., & Wang, Q. (2022) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco55093.2022.9909808 · Cited by 5
Integration of epigenetic, transcriptomic and proteomic data
Zenere, A. (2023) · Linköping studies in science and technology. Dissertations · doi:10.3384/9789180750691 · Cited by 5
The Influence Function of Graphical Lasso Estimators
Louvet, G., Raymaekers, J., Bever, G. V., & Wilms, I. (2023) · Econometrics and Statistics · doi:10.1016/j.ecosta.2023.03.004 · Cited by 6
Penalized joint models of high-dimensional longitudinal biomarkers and a survival outcome
Sun, J., & Basu, S. (2024) · The Annals of Applied Statistics · doi:10.1214/23-aoas1844 · Cited by 5
Heterogeneous latent transfer learning in Gaussian graphical models
Wu, Q., Wang, C., & Chen, Y. (2024) · Biometrics · doi:10.1093/biomtc/ujae096 · Cited by 5
Learning Temporal Dependence from Time-Series Data with Latent Variables
Hosseini, H., Kannan, S., Zhang, B., & Poovendran, R. (2016) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2016.34 · Cited by 6
Estimation of graphical models using the L1,2 norm
Chiong, K. X., & Moon, H. R. (2017) · Econometrics Journal · doi:10.1111/ectj.12104 · Cited by 5
“Following the argument in the proof of Theorem 1 of Yuan and Lin (2007), we have that: Moreover, we know that when T is large enough, where g ij = u ij sign(Ω 0 ,ij ) 1 (Ω 0 ,ij (cid:54) = 0) + | u ij | 1 (Ω 0 ,ij = 0).”
BackgroundMethodInfluentialRobust Estimation of Tree Structured Gaussian Graphical Models
Katiyar, A., Hoffmann, J., & Caramanis, C. (2019) · International Conference on Machine Learning · Cited by 5
Avagyan, V., & Mei, X. (2019) · Communications in Statistics - Simulation and Computation · doi:10.1080/03610918.2019.1668012 · Cited by 5
“…two popular precision matrix estimation methods: ‘1 norm penalized log-likelihood maximization approach, also known as GLasso (Banerjee et al. 2008; Yuan and Lin 2007; d’Aspremont et al. 2008; Banerjee et al. 2008; Rothman et al. 2008) and ‘1 norm penalized DTrace loss minimization (Zhang and Zou…”
MethodEstimation of Undirected Graph with Finite Mixture of Nonparanormal Distribution
Khalili, A., Eskandari, F., & Nematollahi, N. (2021) · Journal of Statistical Theory and Practice · doi:10.1007/s42519-021-00192-1 · Cited by 5
“[1], and Yuan and Lin [26] propose Gaussian distribution for the graphical model and impose simplicity on the graphical model by putting sparsity constraint on the elements of precision matrix.”
Learning Gaussian graphical models with latent confounders
Wang, K., Franks, A. M., & Oh, S. (2023) · Journal of Multivariate Analysis · doi:10.1016/j.jmva.2023.105213 · Cited by 9
“We focus on estimating Ω = Σ − 1 , the precision matrix encoding the graph structure of interest Yuan and Lin (2007); Friedman et al. (2008); Cai et al. (2011); Parsana et al. (2019).”
BackgroundMethodLiu, J., Wang, H., Sun, W., & Liu, Y. (2021) · Journal of the American Statistical Association · doi:10.1080/01621459.2021.1933495 · Cited by 19
“Traditional Gaussian graphical models (Meinshausen and Bühlmann 2006; Yuan and Lin 2007; Friedman, Hastie, and Tibshirani 2008; Cai, Liu, and Luo 2011) are not appropriate for the sparse count data generated by scRNA-seq.”
BackgroundBayesian estimation of sparse precision matrices in the presence of Gaussian measurement error
Shi, W., Ghosal, S., & Martin, R. (2021) · Electronic Journal of Statistics · doi:10.1214/21-ejs1904 · Cited by 5
“Yuan and Lin [33] and Banerjee, Ghaoui and d’Aspremont [1] proposed to add an 1-type penalty to the negative log-likelihood, leading to the so-called graphical lasso estimator.”
BackgroundRegression‐based Bayesian estimation and structure learning for nonparanormal graphical models
Mulgrave, J. J., & Ghosal, S. (2022) · Statistical Analysis and Data Mining The ASA Data Science Journal · doi:10.1002/sam.11576 · Cited by 5
Foroni, B., Morelli, G., & Petrella, L. (2022) · Energy Systems · doi:10.1007/s12667-022-00530-7 · Cited by 5
“To estimate the optimal value of 𝜌 , we minimize the Extended Bayesian Information Criterion (EBIC, [26]) which has been shown to work particularly well in retrieving the true network structure [14, 53] and it is a computationally efficient alternative to cross-validation [111].”
Estimation of a genetic Gaussian network using GWAS summary data
Yang, Y., Lorincz‐Comi, N. J., & Zhu, X. (2024) · Biometrics · doi:10.1093/biomtc/ujae148 · Cited by 5
“…of Gaussian variables: one scheme estimates the precision matrix through maximum likelihood estimation (MLE) of multivariate Gaussian distribution (Yuan and Lin, 2007), while the other estimates the partial correlation coefficients by solving node-wise lasso regression (Meinshausen and B¨uhlmann,…”
On modeling gene regulatory networks using Markov random fields
Santhanam, N., Dingel, J., & Milenković, O. (2009) · IEEE Information Theory Workshop (ITW) · doi:10.1109/itwnit.2009.5158562 · Cited by 5
“Computationally feasible approximations exist for several classes of Ising models, for example, trees [13], constraint based approaches [14], 1 based relaxations [15], [16], [17].”
MethodSmooth Monotone Covariance for Elliptical Distributions and Applications in Finance
Zhou, X., Malioutov, D., Fabozzi, F. J., & Rachev, S. T. (2014) · Quantitative Finance · doi:10.2139/ssrn.2435435 · Cited by 5
Smooth-projected Neighborhood Pursuit for High-dimensional Nonparanormal Graph Estimation
Zhao, T., Roeder, K., & Liu, H. (2012) · neural information processing systems · Cited by 5
Regression analysis of networked data
Zhou, Y., & Song, P. X. ‐. (2016) · Biometrika · doi:10.1093/biomet/asw003 · Cited by 5
“…sparse partial correlation (Peng et al., 2009), implemented in the R (R Development Core Team, 2016) package space; the graphical lasso (Yuan & Lin, 2007), implemented in the R package glasso; neighbourhood selection (Meinshausen & Buehlmann, 2006), also implemented in the R package glasso;…”
MethodZhang, C., Zhang, L., & Chen, N. (2017) · IEEE International Conference on Industrial Engineering and Engineering Management (IEEM) · doi:10.1109/ieem.2017.8290183 · Cited by 5
Nonparametric Bayesian learning of heterogeneous dynamic transcription factor networks
Luo, X., & Wei, Y. (2018) · The Annals of Applied Statistics · doi:10.1214/17-aoas1129 · Cited by 6
“…networks (Carter et al., 2004; Zhang and Horvath, 2005; Bickel and Levina, 2008) and Gaussian graphical models (Meinshausen and B¨uhlmann, 2006; Yuan and Lin, 2007; Friedman, Hastie and Tibshirani, 2008), measured by covariance and precision matrices, respectively, can characterize different…”
BackgroundFang, E. X., Liu, H., & Wang, M. (2018) · Mathematical Programming · doi:10.1007/s10107-018-1331-z · Cited by 5
“Extensive literatures study this problem from different approaches [3,5,12,13,15,20,21,26].”
BackgroundGraphical Models Over Heterogeneous Domains and for Multilevel Networks
Dimitrova, T., & Kocarev, L. (2018) · IEEE Access · doi:10.1109/access.2018.2880840 · Cited by 6
“This corollary has been used in two classes of efficient algorithms for estimating the Gaussian Markov random field: global methods estimate the whole graph by directly estimating the inverse covariance matrix using a penalized likelihood [7]–[9] and node-wise methods estimate the neighborhood of each node separately…”
MethodBayesian Estimation of Large Precision Matrix Based on Cholesky Decomposition
Li, F. Q., & Zhang, X. S. (2019) · Acta Mathematica Sinica English Series · doi:10.1007/s10114-019-7326-8 · Cited by 5
Giesen, J., Nussbaum, F., & Schneider, C. M. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/330 · Cited by 5
Scalable Bayesian matrix normal graphical models for brain functional networks
Kundu, S., & Risk, B. B. (2020) · Biometrics · doi:10.1111/biom.13319 · Cited by 5
“For BMNGM, eMNGM, and Glasso, these measures are reported under the point estimates of the network that are obtained by minimizing the BIC as in Yuan and Lin (2007).”
MethodMolstad, A. J., Sun, W., & Hsu, L. (2021) · The Annals of Applied Statistics · doi:10.1214/20-aoas1432 · Cited by 5
“For sufficiently large values of the tuning parameter λΩ, this penalty leads to estimates of the precision matrix which will have all off-diagonal entries equal to zero [44, 32].”
BackgroundHigh‐dimensional precision matrix estimation with a known graphical structure
Le, T., & Zhong, P. (2021) · Stat · doi:10.1002/sta4.424 · Cited by 5
“Some regularization approaches estimate the entire precision matrix simultaneously by employing the L 1 -penalized maximum likelihood (see Banerjees et al. (2008), Yuan and Lin (2007), Friedman et al. (2008) and Lam and Fan (2009)).”
MethodImportance-Penalized Joint Graphical Lasso (IPJGL): differential network inference via GGMs
Leng, J., & Wu, L. (2021) · Bioinformatics · doi:10.1093/bioinformatics/btab751 · Cited by 5
“Graphical Lasso (GLasso) was a popular method to estimate the precision matrix H (Banerjee et al., 2008; Friedman et al., 2008; Yuan and Lin, 2007).”
Nanshan, M., Zhang, N., Xun, X., & Cao, J. (2022) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2022.107483 · Cited by 5
“…Yuan and Lin, 2006; Zou, 2006), the smoothly clipped absolute deviation (SCAD) (Fan and Li, 2001) and the minimax concave penalty (MCP) (Zhang, 2010) have been extensively studied and used to recover probabilistic graphical structures (Yuan and Lin, 2007; Fan et al., 2009; Voorman et al., 2014).”
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.