User: Guest  Login
Title:

Partial Homoscedasticity in Causal Discovery with Linear Models

Document type:
Zeitschriftenaufsatz
Author(s):
Wu, Jun; Drton, Mathias
Abstract:
Recursive linear structural equation models and the associated directed acyclic graphs (DAGs) play an important role in causal discovery. The classic identifiability result for this class of models states that when only observational data is available, each DAG can be identified only up to a Markov equivalence class. In contrast, recent work has shown that the DAG can be uniquely identified if the errors in the model are homoscedastic, i.e., all have the same variance. This equal variance assump...     »
Keywords:
Causal discovery, covariance matrix, equal variance, graphical model, structural equation model
Dewey Decimal Classification:
510 Mathematik
Journal title:
IEEE Journal on Selected Areas in Information Theory
Year:
2023
Year / month:
2023-11
Quarter:
4. Quartal
Month:
Nov
Pages contribution:
639 - 650
Language:
en
Fulltext / DOI:
doi:10.1109/jsait.2023.3328476
WWW:
IEEE Xplore
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
E-ISSN:
2641-8770
Notes:
Early Access
Date of publication:
01.11.2023
Semester:
WS 23-24
TUM Institution:
Lehrstuhl für Mathematische Statistik
Format:
Text
 BibTeX