On causal discovery with an equal-variance assumption
From MaRDI portal
Publication:5212918
DOI10.1093/BIOMET/ASZ049zbMATH Open1435.62166arXiv1807.03419OpenAlexW2831193409WikidataQ114633429 ScholiaQ114633429MaRDI QIDQ5212918FDOQ5212918
Authors: Wenyu Chen, Mathias Drton, Y. Samuel Wang 
Publication date: 30 January 2020
Published in: Biometrika (Search for Journal in Brave)
Abstract: Prior work has shown that causal structure can be uniquely identified from observational data when these follow a structural equation model whose error terms have equal variances. We show that this fact is implied by an ordering among (conditional) variances. We demonstrate that ordering estimates of these variances yields a simple yet state-of-the-art method for causal structure learning that is readily extendable to high-dimensional problems.
Full work available at URL: https://arxiv.org/abs/1807.03419
Recommendations
- Identifiability of Gaussian structural equation models with equal error variances
- scientific article
- High-dimensional causal discovery under non-Gaussianity
- Learning instrumental variables with structural and non-Gaussianity assumptions
- DirectLiNGAM: a direct method for learning a linear non-Gaussian structural equation model
Statistical aspects of big data and data science (62R07) Order statistics; empirical distribution functions (62G30)
Cited In (19)
- Causal discovery in heavy-tailed models
- A uniformly consistent estimator of causal effects under the \(k\)-triangle-faithfulness assumption
- Identifiability of Gaussian structural equation models with equal error variances
- Learning high-dimensional Gaussian linear structural equation models with heterogeneous error variances
- Recursive max-linear models with propagating noise
- High-dimensional Poisson structural equation model learning via \(\ell_1\)-regularized regression
- Identifiability of additive noise models using conditional variances
- Computationally Efficient Learning of Gaussian Linear Structural Equation Models with Equal Error Variances
- Title not available (Why is that?)
- Causal discovery from heterogeneous/nonstationary data
- Robust estimation of Gaussian linear structural equation models with equal error variances
- Algorithmic Learning Theory
- Learning instrumental variables with structural and non-Gaussianity assumptions
- Identifiability and Consistent Estimation for Gaussian Chain Graph Models
- Identifiability of homoscedastic linear structural equation models using algebraic matroids
- Efficient Learning of Quadratic Variance Function Directed Acyclic Graphs via Topological Layers
- Efficient learning of nonparametric directed acyclic graph with statistical guarantee
- Densely connected sub-Gaussian linear structural equation model learning via \(\ell_1\)- and \(\ell_2\)-regularized regressions
- High-dimensional causal discovery under non-Gaussianity
This page was built for publication: On causal discovery with an equal-variance assumption
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5212918)
