August 31, 2024Open Access

Learning linear acyclic causal model including Gaussian noise using ancestral relationships

View Full Paper

Ask AI

Bookmark

A novel causal discovery algorithm identifies distribution-equivalence patterns in linear causal models with lower time complexity than PC-LiNGAM.
Theoretical model generalizes the causal ancestor finding algorithm of Maeda and Shimizu, allowing distribution equivalence identification with Gaussian noise.
Supports scalable causal DAG discovery across complex networks, overcoming the factorial worst-case time complexity seen in prior hybrid approaches.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Theoretical analysis demonstrates reduced time complexity for linear causal DAG discovery, indicating improved scalability in the presence of Gaussian disturbances.

Cite This Study

Cai et al. (2024) studied this question.

synapsesocial.com/papers/68e5a2bab6db64358753ce13 https://doi.org/10.48550/arxiv.2409.00417

View Full Paper

Ask AI

Bookmark

Implication

Theoretical analysis demonstrates reduced time complexity for linear causal DAG discovery, indicating improved scalability in the presence of Gaussian disturbances.

Learning linear acyclic causal model including Gaussian noise using ancestral relationships

Key Points

Discussion

Implication

Cite This Study

Learning linear acyclic causal model including Gaussian noise using ancestral relationships

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider