Learning High-dimensional Directed Acyclic Graphs with Mixed Data-types

Bryan Andrews, Joseph Ramsey, Gregory F. Cooper
Proceedings of Machine Learning Research, PMLR 104:4-21, 2019.

Abstract

In recent years, great strides have been made for causal structure learning in the high- dimensional setting and in the mixed data-type setting when there are both discrete and continuous variables. However, due to the complications involved with modeling continuous-discrete variable interactions, the intersection of these two settings has been relatively understudied. The current paper explores the problem of efficiently extending causal structure learning algorithms to high-dimensional data with mixed data-types. First, we characterize a model over continuous and discrete variables. Second, we derive a de- generate Gaussian (DG) score for mixed data-types and discuss its asymptotic properties. Lastly, we demonstrate the practicality of the DG score on learning causal structures from simulated data sets.

Cite this Paper


BibTeX
@InProceedings{pmlr-v104-andrews19a, title = {Learning High-dimensional Directed Acyclic Graphs with Mixed Data-types}, author = {Andrews, Bryan and Ramsey, Joseph and Cooper, Gregory F.}, booktitle = {Proceedings of Machine Learning Research}, pages = {4--21}, year = {2019}, editor = {}, volume = {104}, series = {Proceedings of Machine Learning Research}, month = {05 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v104/andrews19a/andrews19a.pdf}, url = {https://proceedings.mlr.press/v104/andrews19a.html}, abstract = {In recent years, great strides have been made for causal structure learning in the high- dimensional setting and in the mixed data-type setting when there are both discrete and continuous variables. However, due to the complications involved with modeling continuous-discrete variable interactions, the intersection of these two settings has been relatively understudied. The current paper explores the problem of efficiently extending causal structure learning algorithms to high-dimensional data with mixed data-types. First, we characterize a model over continuous and discrete variables. Second, we derive a de- generate Gaussian (DG) score for mixed data-types and discuss its asymptotic properties. Lastly, we demonstrate the practicality of the DG score on learning causal structures from simulated data sets.} }
Endnote
%0 Conference Paper %T Learning High-dimensional Directed Acyclic Graphs with Mixed Data-types %A Bryan Andrews %A Joseph Ramsey %A Gregory F. Cooper %B Proceedings of Machine Learning Research %C Proceedings of Machine Learning Research %D 2019 %E %F pmlr-v104-andrews19a %I PMLR %P 4--21 %U https://proceedings.mlr.press/v104/andrews19a.html %V 104 %X In recent years, great strides have been made for causal structure learning in the high- dimensional setting and in the mixed data-type setting when there are both discrete and continuous variables. However, due to the complications involved with modeling continuous-discrete variable interactions, the intersection of these two settings has been relatively understudied. The current paper explores the problem of efficiently extending causal structure learning algorithms to high-dimensional data with mixed data-types. First, we characterize a model over continuous and discrete variables. Second, we derive a de- generate Gaussian (DG) score for mixed data-types and discuss its asymptotic properties. Lastly, we demonstrate the practicality of the DG score on learning causal structures from simulated data sets.
APA
Andrews, B., Ramsey, J. & Cooper, G.F.. (2019). Learning High-dimensional Directed Acyclic Graphs with Mixed Data-types. Proceedings of Machine Learning Research, in Proceedings of Machine Learning Research 104:4-21 Available from https://proceedings.mlr.press/v104/andrews19a.html.

Related Material