User: Guest  Login
Title:

Causal Discovery with Unobserved Confounding and Non-Gaussian Data

Document type:
Zeitschriftenaufsatz
Author(s):
Wang, Y. Samuel; Drton, Mathias
Abstract:
We consider recovering causal structure from multivariate observational data. We assume the data arise from a linear structural equation model (SEM) in which the idiosyncratic errors are allowed to be dependent in order to capture possible latent confounding. Each SEM can be represented by a graph where vertices represent observed variables, directed edges represent direct causal effects, and bidirected edges represent dependence among error terms. Specifically, we assume that the true model cor...     »
Keywords:
Causal discovery, Graphical model, Latent variables, Non-Gaussian data, Structural equation model
Dewey Decimal Classification:
510 Mathematik
Journal title:
Journal of Machine Learning Research
Year:
2023
Journal volume:
24
Year / month:
2023-08
Quarter:
3. Quartal
Month:
Aug
Journal issue:
271
Pages contribution:
1−61
Language:
en
Fulltext / DOI:
doi:10.48550/arXiv.2007.11131
WWW:
Journal of Machine Learning Research
Status:
Erstveröffentlichung
Submitted:
01.11.2021
Date of publication:
01.08.2023
Semester:
SS 23
TUM Institution:
Lehrstuhl für Mathematische Statistik
Format:
Text
 BibTeX