Skip to contents

Inferring high-dimensional Gaussian graphical networks that change with multiple discrete covariates.

References

Dijkstra L, Godt A, Foraita R Inferring High-Dimensional Dynamic Networks Changing with Multiple Covariates (2024), Arxiv, https://arxiv.org/abs/2407.19978.

Author

Maintainer: Ronja Foraita foraita@leibniz-bips.de (ORCID)

Authors:

Other contributors:

  • Lukas Burk (ORCID) [contributor]

  • DFG [funder]

  • Leibniz Institute for Prevention Research and Epidemiology - BIPS R@leibniz-bips.de (ROR) [copyright holder]

Examples


data(grid)
W <- create_weight_matrix(type = "grid", k=3, l=3, plot = FALSE)

cvn <- CVN(grid, W, lambda1 = 1, lambda2 = 1:2, 
           n_cores = 1,
           eps = 1e-2, maxiter = 1000, verbose = TRUE)
#> Estimating a CVN with 9 graphs...
#> 
#> Number of cores: 1
#> Uses a warmstart...
#> 
#> -------------------------
#> iteration 1  |  2.180956
#> iteration 2  |  0.115992
#> iteration 3  |  0.085702
#> iteration 4  |  0.030387
#> iteration 5  |  0.024326
#> iteration 6  |  0.016685
#> iteration 7  |  0.013629
#> iteration 8  |  0.012361
#> iteration 9  |  0.011060
#> iteration 10  |  0.009923
#> -------------------------
#> iteration 1  |  2.180956
#> iteration 2  |  0.115683
#> iteration 3  |  0.085927
#> iteration 4  |  0.029249
#> iteration 5  |  0.022338
#> iteration 6  |  0.017805
#> iteration 7  |  0.017968
#> iteration 8  |  0.015503
#> iteration 9  |  0.014200
#> iteration 10  |  0.012371
#> -------------------------
#> iteration 11  |  0.011107
#> iteration 12  |  0.010068
#> iteration 13  |  0.009907