<i>Jewel</i>: A Novel Method for Joint Estimation of Gaussian Graphical Models
In this paper, we consider the problem of estimating multiple Gaussian Graphical Models from high-dimensional datasets. We assume that these datasets are sampled from different distributions with the same conditional independence structure, but not the same precision matrix. We propose <i>jewe...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/9/17/2105 |
| _version_ | 1797521093243699200 |
|---|---|
| author | Claudia Angelini Daniela De Canditiis Anna Plaksienko |
| author_facet | Claudia Angelini Daniela De Canditiis Anna Plaksienko |
| author_sort | Claudia Angelini |
| collection | DOAJ |
| description | In this paper, we consider the problem of estimating multiple Gaussian Graphical Models from high-dimensional datasets. We assume that these datasets are sampled from different distributions with the same conditional independence structure, but not the same precision matrix. We propose <i>jewel</i>, a joint data estimation method that uses a node-wise penalized regression approach. In particular, <i>jewel</i> uses a group Lasso penalty to simultaneously guarantee the resulting adjacency matrix’s symmetry and the graphs’ joint learning. We solve the minimization problem using the group descend algorithm and propose two procedures for estimating the regularization parameter. Furthermore, we establish the estimator’s consistency property. Finally, we illustrate our estimator’s performance through simulated and real data examples on gene regulatory networks. |
| first_indexed | 2024-03-10T08:06:47Z |
| format | Article |
| id | doaj.art-51065f1075da4a349904e206ed955f95 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T08:06:47Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-51065f1075da4a349904e206ed955f952023-11-22T10:57:59ZengMDPI AGMathematics2227-73902021-08-01917210510.3390/math9172105<i>Jewel</i>: A Novel Method for Joint Estimation of Gaussian Graphical ModelsClaudia Angelini0Daniela De Canditiis1Anna Plaksienko2Istituto per le Applicazioni del Calcolo “Mauro Picone”, CNR-Napoli, 80131 Naples, ItalyIstituto per le Applicazioni del Calcolo “Mauro Picone”, CNR-Roma, 00185 Rome, ItalyIstituto per le Applicazioni del Calcolo “Mauro Picone”, CNR-Napoli, 80131 Naples, ItalyIn this paper, we consider the problem of estimating multiple Gaussian Graphical Models from high-dimensional datasets. We assume that these datasets are sampled from different distributions with the same conditional independence structure, but not the same precision matrix. We propose <i>jewel</i>, a joint data estimation method that uses a node-wise penalized regression approach. In particular, <i>jewel</i> uses a group Lasso penalty to simultaneously guarantee the resulting adjacency matrix’s symmetry and the graphs’ joint learning. We solve the minimization problem using the group descend algorithm and propose two procedures for estimating the regularization parameter. Furthermore, we establish the estimator’s consistency property. Finally, we illustrate our estimator’s performance through simulated and real data examples on gene regulatory networks.https://www.mdpi.com/2227-7390/9/17/2105Gaussian Graphical Modelgroup Lassojoint estimationnetwork estimation |
| spellingShingle | Claudia Angelini Daniela De Canditiis Anna Plaksienko <i>Jewel</i>: A Novel Method for Joint Estimation of Gaussian Graphical Models Mathematics Gaussian Graphical Model group Lasso joint estimation network estimation |
| title | <i>Jewel</i>: A Novel Method for Joint Estimation of Gaussian Graphical Models |
| title_full | <i>Jewel</i>: A Novel Method for Joint Estimation of Gaussian Graphical Models |
| title_fullStr | <i>Jewel</i>: A Novel Method for Joint Estimation of Gaussian Graphical Models |
| title_full_unstemmed | <i>Jewel</i>: A Novel Method for Joint Estimation of Gaussian Graphical Models |
| title_short | <i>Jewel</i>: A Novel Method for Joint Estimation of Gaussian Graphical Models |
| title_sort | i jewel i a novel method for joint estimation of gaussian graphical models |
| topic | Gaussian Graphical Model group Lasso joint estimation network estimation |
| url | https://www.mdpi.com/2227-7390/9/17/2105 |
| work_keys_str_mv | AT claudiaangelini ijewelianovelmethodforjointestimationofgaussiangraphicalmodels AT danieladecanditiis ijewelianovelmethodforjointestimationofgaussiangraphicalmodels AT annaplaksienko ijewelianovelmethodforjointestimationofgaussiangraphicalmodels |