English

Cyclic functional causal models beyond unique solvability with a graph separation theorem

Statistics Theory 2025-02-10 v2 Quantum Physics Machine Learning Statistics Theory

Abstract

Functional causal models (fCMs) specify functional dependencies between random variables associated to the vertices of a graph. In directed acyclic graphs (DAGs), fCMs are well-understood: a unique probability distribution on the random variables can be easily specified, and a crucial graph-separation result called the d-separation theorem allows one to characterize conditional independences between the variables. However, fCMs on cyclic graphs pose challenges due to the absence of a systematic way to assign a unique probability distribution to the fCM's variables, the failure of the d-separation theorem, and lack of a generalization of this theorem that is applicable to all consistent cyclic fCMs. In this work, we develop a causal modeling framework applicable to all cyclic fCMs involving finite-cardinality variables, except inconsistent ones admitting no solutions. Our probability rule assigns a unique distribution even to non-uniquely solvable cyclic fCMs and reduces to the known rule for uniquely solvable fCMs. We identify a class of fCMs, called averagely uniquely solvable, that we show to be the largest class where the probabilities admit a Markov factorization. Furthermore, we introduce a new graph-separation property, p-separation, and prove this to be sound and complete for all consistent finite-cardinality cyclic fCMs while recovering the d-separation theorem for DAGs. These results are obtained by considering classical post-selected teleportation protocols inspired by analogous protocols in quantum information theory. We discuss further avenues for exploration, linking in particular problems in cyclic fCMs and in quantum causality.

Keywords

Cite

@article{arxiv.2502.04171,
  title  = {Cyclic functional causal models beyond unique solvability with a graph separation theorem},
  author = {Carla Ferradini and Victor Gitton and V. Vilasini},
  journal= {arXiv preprint arXiv:2502.04171},
  year   = {2025}
}

Comments

33+16 pages. A companion paper by the same authors, focussing on cyclic quantum causal models has been submitted to the arXiv concurrently with primary class [quant-ph], v2 only differs from v1 in including the arXiv number of the companion paper. Comments are welcome

R2 v1 2026-06-28T21:34:57.253Z