Algorithms
Apart from the original parameters of the underlying software, each algorithm module is equipped with an additional parameter, timeout
, which is the maximum time in seconds allowed for the algorithm to run.
After the timeout, the algorithm will be terminated and either an empty file will be created or the current best graph will be saved (if the algorithm supports that).
Modules for MCMC algorithms can be used seamlessly with the other modules. However, apart from the original parameters and timeout
, these modules have four additional fields:
mcmc_seed
is the random seed for the algorithm.mcmc_estimator
specifies which estimator to use (threshold or map).threshold
specifies the threshold for the posterior edge probabilities ifmcmc_estimator
is set to threshold.burnin_frac
is a value in (0, 1) that specifies the fraction of the samples at the beginning of the graph trajectory to be discarded as burn-in.
The available modules are listed below. To add new modules, see Adding new modules.
Algorithm |
Graph |
Package |
Module |
---|---|---|---|
Chordal graph samplers |
|||
BDgraph |
|||
Iterative MCMC |
|||
Order MCMC |
|||
Partition MCMC |
|||
Fast IAMB |
|||
Grow-shrink |
|||
H2PC |
|||
HC |
|||
HPC |
|||
IAMB |
|||
IAMB-FDR |
|||
INTER-IAMB |
|||
MMHC |
|||
MMPC |
|||
PC |
|||
RSMAX2 |
|||
S-I HITON-PC |
|||
Tabu |
|||
GSP |
|||
GRaSP |
|||
Corrmat thresh |
|||
Dual PC |
|||
Psi-learning |
|||
ANM |
|||
CORL |
|||
Direct LINGAM |
|||
GAE |
|||
GOLEM |
|||
GraNDAG |
|||
ICALiNGAM |
|||
MCSL |
|||
NO TEARS |
|||
NO TEARS low rank |
|||
NO TEARS non-linear |
|||
PC |
|||
RL |
|||
GOBNILP |
|||
GrUES |
|||
Graphical lasso |
|||
Meinshausen & Buhlmann cov est |
|||
TIGER |
|||
Parallel DG |
|||
GIES |
|||
PC |
|||
Precmat thresh |
|||
ASOBS |
|||
Graphical Lasso |
|||
BOSS |
|||
FASK |
|||
FGES |
|||
FOFC |
|||
FTFC |
|||
GRaSP |
|||
ICA-LINGAM |
|||
PC |
|||
Particle Gibbs |