I'm working on a project with datasets where the number of variables is 3000+ for which a bayesian network would be ideal choice to model the data. Unfortunately, as we all know, structure learning for Bayes Nets is exponential and consequently, unfeasible for such a wide dataset.
In my research, I've come across this paper which looks very encouraging as a method for addressing the exponential complexity of structure learning.
Is there a straightforward way to implement the parent constraint method described in the paper using the existing structure learning framework in the package?
Hi,
Great package. I really enjoy using it!
I'm working on a project with datasets where the number of variables is 3000+ for which a bayesian network would be ideal choice to model the data. Unfortunately, as we all know, structure learning for Bayes Nets is exponential and consequently, unfeasible for such a wide dataset.
In my research, I've come across this paper which looks very encouraging as a method for addressing the exponential complexity of structure learning.
Is there a straightforward way to implement the parent constraint method described in the paper using the existing structure learning framework in the package?
Any insights or direction is much appreciated
Thanks!
Andrew