On the Equivalence of Causal Models: A Category-Theoretic Approach

01/18/2022
by   Jun Otsuka, et al.
0

We develop a category-theoretic criterion for determining the equivalence of causal models having different but homomorphic directed acyclic graphs over discrete variables. Following Jacobs et al. (2019), we define a causal model as a probabilistic interpretation of a causal string diagram, i.e., a functor from the “syntactic” category _G of graph G to the category of finite sets and stochastic matrices. The equivalence of causal models is then defined in terms of a natural transformation or isomorphism between two such functors, which we call a Φ-abstraction and Φ-equivalence, respectively. It is shown that when one model is a Φ-abstraction of another, the intervention calculus of the former can be consistently translated into that of the latter. We also identify the condition under which a model accommodates a Φ-abstraction, when transformations are deterministic.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/27/2013

On the Equivalence of Causal Models

Scientists often use directed acyclic graphs (days) to model the qualita...
research
04/11/2022

Markov categories, causal theories, and the do-calculus

We give a category-theoretic treatment of causal models that formalizes ...
research
03/29/2021

Compositional Abstraction Error and a Category of Causal Models

Interventional causal models describe joint distributions over some vari...
research
03/28/2023

On Causal Equivalence by Tracing in String Rewriting

We introduce proof terms for string rewrite systems and, using these, sh...
research
05/04/2023

String Diagrams with Factorized Densities

A growing body of research on probabilistic programs and causal models h...
research
04/23/2019

A Category Theoretic Interpretation of Gandy's Principles for Mechanisms

Based on Gandy's principles for models of computation we give category-t...
research
06/13/2012

Almost Optimal Intervention Sets for Causal Discovery

We conjecture that the worst case number of experiments necessary and su...

Please sign up or login with your details

Forgot password? Click here to reset