.png){kind=icon}
Return
A PC Algorithm for Max-Linear Bayesian Networks
.png){kind=icon}
PRE
AI
DOI：10.1080/10618600.2026.2673046.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Max-linear Bayesian networks (MLBNs) are a relatively recent class of structural equation models which arise when the random variables involved have heavy-tailed distributions. Unlike most directed graphical models, MLBNs are typically not faithful to d-separation and thus classical causal discovery algorithms such as the PC algorithm or greedy equivalence search can not be used to accurately recover the true graph structure. In this paper, we begin the study of constraint-based discovery algorithms for MLBNs given an oracle for testing conditional independence in the true, unknown graph. We show that if the oracle is given by the & lowast; -separation criteria in the true graph, then the PC algorithm remains consistent despite the presence of additional CI statements implied by & lowast; -separation. We also introduce a new causal discovery algorithm named PCstar which assumes faithfulness to C & lowast; -separation and is able to orient additional edges which cannot be oriented with only d- or & lowast; -separation. Supplementary materials for this article are available online
Keywords:
Causal discovery
Conditional independence
Extreme value theory
Graphical models
Separation criteria
Journal
J
IF:
1.8
Papers:
141
Citations:
6.4K
Organization
Cited Papers
No cited papers available