Identifiability of Causal Graphs using Functional Models

02/14/2012
by   Jonas Peters, et al.
0

This work addresses the following question: Under what assumptions on the data generating process can one infer the causal graph from the joint distribution? The approach taken by conditional independence-based causal discovery methods is based on two assumptions: the Markov condition and faithfulness. It has been shown that under these assumptions the causal graph can be identified up to Markov equivalence (some arrows remain undirected) using methods like the PC algorithm. In this work we propose an alternative by defining Identifiable Functional Model Classes (IFMOCs). As our main theorem we prove that if the data generating process belongs to an IFMOC, one can identify the complete causal graph. To the best of our knowledge this is the first identifiability result of this kind that is not limited to linear functional relationships. We discuss how the IFMOC assumption and the Markov and faithfulness assumptions relate to each other and explain why we believe that the IFMOC assumption can be tested more easily on given data. We further provide a practical algorithm that recovers the causal graph from finitely many data; experiments on simulated data support the theoretical findings.

READ FULL TEXT
research
07/22/2021

Typing assumptions improve identification in causal discovery

Causal discovery from observational data is a challenging task to which ...
research
10/27/2020

A Weaker Faithfulness Assumption based on Triple Interactions

One of the core assumptions in causal discovery is the faithfulness assu...
research
03/24/2021

Conditions and Assumptions for Constraint-based Causal Structure Learning

The paper formalizes constraint-based structure learning of the "true" c...
research
12/14/2020

A Single Iterative Step for Anytime Causal Discovery

We present a sound and complete algorithm for recovering causal graphs f...
research
11/29/2021

A Fast Non-parametric Approach for Causal Structure Learning in Polytrees

We study the problem of causal structure learning with no assumptions on...
research
06/14/2022

Towards a Solution to Bongard Problems: A Causal Approach

To date, Bongard Problems (BP) remain one of the few fortresses of AI hi...
research
09/09/2011

Ignorability in Statistical and Probabilistic Inference

When dealing with incomplete data in statistical learning, or incomplete...

Please sign up or login with your details

Forgot password? Click here to reset