Joint Estimation of Multiple Precision Matrices with Common Structures

Authors: Wonyul Lee, Yufeng Liu

JMLR 2015 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our numerical examples demonstrate that our new estimator can perform better than several existing methods in terms of the entropy loss and Frobenius loss. An application to a glioblastoma cancer data set reveals some interesting gene networks across multiple cancer subtypes. In this section, we carry out simulation studies to assess the numerical performance of our proposed method.
Researcher Affiliation Academia Wonyul Lee EMAIL Department of Statistics and Operations Research University of North Carolina Chapel Hill, NC 27599-3260, USA. Yufeng Liu EMAIL Department of Statistics and Operations Research Department of Genetics Department of Biostatistics Carolina Center for Genome Sciences University of North Carolina Chapel Hill, NC 27599-3260, USA
Pseudocode No The paper describes the steps for the ADMM algorithm mathematically but does not present them in a clearly labeled 'Pseudocode' or 'Algorithm' block. For example, 'min |y|1 s.t. |zm| lambda1, |zg| lambda2, Ay Bz = C, where (5) ... As argminy L(y, zk, uk) = argminy{|y|1 + rho/2||Ay Bzk C + uk||2 2}, the step (a) can be viewed as an L1 penalized least squares problem.'
Open Source Code No For our simulation study and the GBM data analysis, we obtain the solution of (3) using the efficient R-package fastclime, which provides a generic fast linear programming solver (Pang et al., 2014). This refers to a third-party package used by the authors, not their own implementation code being released. There is no explicit statement about releasing their code for the methodology described in this paper.
Open Datasets Yes In this section, we apply our joint method to a Glioblastoma cancer data set. The data set consists of 17814 gene expression levels of 482 GBM patients... (The Cancer Genome Atlas Research Network, 2008).
Dataset Splits Yes For each group in each model, we generate a training sample of size n = 100 from either a multivariate normal distribution N(0, Sigma (g) 0 ) or a multivariate t-distribution with the covariance matrix Sigma (g) 0 and degrees of freedom of 3 or 5. In order to select optimal tuning parameters, an independent validation set of size n = 100 is also generated from the same distribution of the training sample.
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments, such as GPU or CPU models, or memory specifications.
Software Dependencies Yes For our simulation study and the GBM data analysis, we obtain the solution of (3) using the efficient R-package fastclime, which provides a generic fast linear programming solver (Pang et al., 2014). R package version 1.2.4.
Experiment Setup Yes In our proposed method, nu is set to be G 1/2. We also tried different values of nu such as G 1, and the results are similar thus omitted. To produce interpretable graphical models using our JEMP estimator, we set the values of the tuning parameters as lambda1 = 0.30 and lambda2 = 0.40.