Causal Discovery with Continuous Additive Noise Models

09/26/2013
by   Jonas Peters, et al.
0

We consider the problem of learning causal directed acyclic graphs from an observational joint distribution. One can use these graphs to predict the outcome of interventional experiments, from which data are often not available. We show that if the observational distribution follows a structural equation model with an additive noise structure, the directed acyclic graph becomes identifiable from the distribution under mild conditions. This constitutes an interesting alternative to traditional methods that assume faithfulness and identify only the Markov equivalence class of the graph, thus leaving some edges undirected. We provide practical algorithms for finitely many samples, RESIT (Regression with Subsequent Independence Test) and two methods based on an independence score. We prove that RESIT is correct in the population setting and provide an empirical evaluation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/11/2012

Identifiability of Gaussian structural equation models with equal error variances

We consider structural equation models in which variables can be written...
research
11/25/2013

Score-based Causal Learning in Additive Noise Models

Given data sampled from a number of variables, one is often interested i...
research
07/22/2021

Efficient Neural Causal Discovery without Acyclicity Constraints

Learning the structure of a causal graphical model using both observatio...
research
05/10/2023

Causal Inference in Directed, Possibly Cyclic, Graphical Models

We consider the problem of learning a directed graph G^⋆ from observatio...
research
02/28/2023

Practical Algorithms for Orientations of Partially Directed Graphical Models

In observational studies, the true causal model is typically unknown and...
research
08/20/2018

Causal Discovery by Telling Apart Parents and Children

We consider the problem of inferring the directed, causal graph from obs...
research
03/13/2018

SAM: Structural Agnostic Model, Causal Discovery and Penalized Adversarial Learning

We present the Structural Agnostic Model (SAM), a framework to estimate ...

Please sign up or login with your details

Forgot password? Click here to reset