Faster Generic Identification in Tree-Shaped Structural Causal Models

Yasmine Briefs, Markus Bläser

Keywords: causality, generic identification, structural causal models, linear structural equation models

TL;DR: We provide a faster algorithm for generic identification in tree-shaped linear structural causal models.

Abstract: Linear structural causal models (SCMs) are used to analyze the relationships between random variables. Directed edges represent direct causal effects and bidirected edges represent hidden confounders. Generically identifying the causal parameters from observed correlations between the random variables is an open problem in causality. Gupta and Bl\"aser solve the case of SCMs in which the directed edges form a tree by giving a randomized polynomial time algorithm with running time $O(n^6)$. We present an improved algorithm with running time $O(n^3 \log^2 n)$ and demonstrate its feasibility by providing an implementation that outperforms existing state-of-the-art implementations.

Primary Area: Probabilistic methods (e.g., variational inference, causal inference, Gaussian processes)

Submission Number: 9204