Characterizing Distribution Equivalence and Structure Learning for Cyclic and Acyclic Directed Graphs
Authors:
- AmirEmad GhassamiAGAmirEmad Ghassami
- Alan YangAYAlan Yang
- Negar KiyavashNKNegar Kiyavash
- Kun ZhangKZKun Zhang
Preprint
Abstract
The main approach to defining equivalence among acyclic directed causal graphical models is based on the conditional independence relationships in the distributions that the causal models can generate, in terms of the Markov equivalence. However, it is known that when cycles are allowed in the causal structure, conditional independence may not be a suitable notion for equivalence of two structures, as it does not reflect all the information in the distribution that is useful for identification of the underlying structure. In this paper, we present a general, unified notion of equivalence for linear Gaussian causal directed graphical models, whether they are cyclic or acyclic. In our proposed definition of equivalence, two structures are equivalent if they can generate the same set of data distributions. We also propose a weaker notion of equivalence called quasi-equivalence, which we show is the extent of identifiability from observational data. We propose analytic as well as graphical methods for characterizing the equivalence of two structures. Additionally, we propose a score-based method for learning the structure from observational data, which successfully deals with both acyclic and cyclic structures.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Equivalence and Synthesis of Causal Models2022
- Consistency guarantees for greedy permutation-based causal inference algorithmsBiometrika, 2021
- A constraint-based algorithm for causal discovery with cycles, latent variables and selection biasInternational Journal of Data Science and Analytics, 2018
- Learning directed acyclic graph models based on sparsest permutationsStat, 2018
- $\ell_{0}$-penalized maximum likelihood for sparse directed acyclic graphsThe Annals of Statistics, 2013
- Learning Sparse Causal Gaussian Networks With Experimental Intervention: Regularization and Coordinate DescentJournal of the American Statistical Association, 2013
- The hippocampus and memory: insights from spatial processingNature Reviews Neuroscience, 2008
- The max-min hill-climbing Bayesian network structure learning algorithmMachine Learning, 2006
- On Deducing Conditional Independence from d-Separation in Causal Graphs with Feedback (Research Note)Journal of Artificial Intelligence Research, 2000
- Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference.The Journal of Philosophy, 1991