Learning Linear Non-Gaussian Polytree Models
File(s)
Published version
Author(s)
Tramontano, Daniele
Monod, Anthea
Drton, Mathias
Type
Conference Paper
Abstract
In the context of graphical causal discovery, we adapt the versatile
framework of linear non-Gaussian acyclic models (LiNGAMs) to propose new
algorithms to efficiently learn graphs that are polytrees. Our approach
combines the Chow--Liu algorithm, which first learns the undirected tree
structure, with novel schemes to orient the edges. The orientation schemes
assess algebraic relations among moments of the data-generating distribution
and are computationally inexpensive. We establish high-dimensional consistency
results for our approach and compare different algorithmic versions in
numerical experiments.
framework of linear non-Gaussian acyclic models (LiNGAMs) to propose new
algorithms to efficiently learn graphs that are polytrees. Our approach
combines the Chow--Liu algorithm, which first learns the undirected tree
structure, with novel schemes to orient the edges. The orientation schemes
assess algebraic relations among moments of the data-generating distribution
and are computationally inexpensive. We establish high-dimensional consistency
results for our approach and compare different algorithmic versions in
numerical experiments.
Date Issued
2022-08-13
Date Acceptance
2022-08-01
Citation
2022, 180, pp.1-10
Publisher
PMLR
Start Page
1
End Page
10
Volume
180
Identifier
http://arxiv.org/abs/2208.06701v1
Source
38th Conference on Uncertainty in Artificial Intelligence
Subjects
cs.LG
stat.ML
stat.ML
Publication Status
Published
Start Date
2022-08-01
Finish Date
2022-08-05
Coverage Spatial
Eindhoven, Netherlands
Date Publish Online
2022-08-01