On the Complexity of Identification in Linear Structural Causal Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dörfler, Julian, van der Zander, Benito, Bläser, Markus, Liskiewicz, Maciej
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916328367980544
author Dörfler, Julian
van der Zander, Benito
Bläser, Markus
Liskiewicz, Maciej
author_facet Dörfler, Julian
van der Zander, Benito
Bläser, Markus
Liskiewicz, Maciej
contents Learning the unknown causal parameters of a linear structural causal model is a fundamental task in causal analysis. The task, known as the problem of identification, asks to estimate the parameters of the model from a combination of assumptions on the graphical structure of the model and observational data, represented as a non-causal covariance matrix. In this paper, we give a new sound and complete algorithm for generic identification which runs in polynomial space. By standard simulation results, this algorithm has exponential running time which vastly improves the state-of-the-art double exponential time method using a Gröbner basis approach. The paper also presents evidence that parameter identification is computationally hard in general. In particular, we prove, that the task asking whether, for a given feasible correlation matrix, there are exactly one or two or more parameter sets explaining the observed matrix, is hard for $\forall R$, the co-class of the existential theory of the reals. In particular, this problem is $coNP$-hard. To our best knowledge, this is the first hardness result for some notion of identifiability.
format Preprint
id arxiv_https___arxiv_org_abs_2407_12528
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On the Complexity of Identification in Linear Structural Causal Models
Dörfler, Julian
van der Zander, Benito
Bläser, Markus
Liskiewicz, Maciej
Artificial Intelligence
Computational Complexity
Learning the unknown causal parameters of a linear structural causal model is a fundamental task in causal analysis. The task, known as the problem of identification, asks to estimate the parameters of the model from a combination of assumptions on the graphical structure of the model and observational data, represented as a non-causal covariance matrix. In this paper, we give a new sound and complete algorithm for generic identification which runs in polynomial space. By standard simulation results, this algorithm has exponential running time which vastly improves the state-of-the-art double exponential time method using a Gröbner basis approach. The paper also presents evidence that parameter identification is computationally hard in general. In particular, we prove, that the task asking whether, for a given feasible correlation matrix, there are exactly one or two or more parameter sets explaining the observed matrix, is hard for $\forall R$, the co-class of the existential theory of the reals. In particular, this problem is $coNP$-hard. To our best knowledge, this is the first hardness result for some notion of identifiability.
title On the Complexity of Identification in Linear Structural Causal Models
topic Artificial Intelligence
Computational Complexity
url https://arxiv.org/abs/2407.12528