On deducing conditional independence from d-separation in causal graphs with feedback

被引：21

作者：

Neal, RM ^{[1
]}

机构：

[1] Univ Toronto, Dept Stat, Toronto, ON, Canada

[2] Univ Toronto, Dept Comp Sci, Toronto, ON, Canada

来源：

JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH | 2000年 / 12卷

关键词：

D O I：

10.1613/jair.689

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Pearl and Dechter (1996) claimed that the d-separation criterion for conditional independence in acyclic causal networks also applies to networks of discrete variables that have feedback cycles, provided that the variables of the system are uniquely determined by the random disturbances. I show by example that this is not true in general. Some condition stronger than uniqueness is needed, such as the existence of a causal dynamics guaranteed to lead to the unique solution.

引用

页码：87 / 91

页数：5

共 7 条

[1] On Deducing Conditional Independence from d-Separation in Causal Graphs with Feedback
Neal, Radford M.
Journal of Artificial Intelligence Research, 2001, 12 (00):
[2] Exploiting Symmetry of Independence in d-Separation
Butz, Cory J.
dos Santos, Andre E.
Oliveira, Jhonatan S.
Madsen, Anders L.
ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, 11489 : 42 - 54
[3] Independence and D-separation in Abstract Argumentation
Rienstra, Tjitze
Thimm, Matthias
Kersting, Kristian
Shao, Xiaoting
KR2020: PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PRINCIPLES OF KNOWLEDGE REPRESENTATION AND REASONING, 2020, : 713 - 722
[4] D-Separation for Causal Self-Explanation
Liu, Wei
Wang, Jun
Wang, Haozhao
Li, Ruixuan
Deng, Zhiying
Zhang, Yuankai
Qiu, Yang
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
[5] Independence relationships implied by D-separation in the Bayesian model of a causal tree are preserved by the maximum entropy model
Holmes, DE
BAYESIAN INFERENCE AND MAXIMUM ENTROPY METHODS IN SCIENCE AND ENGINEERING, 2001, 567 : 296 - 307
[6] Pearl's D-separation: One more step into causal thinking
Hayduk, L
Cummings, G
Stratkotter, R
Nimmo, M
Grygoryev, K
Dosman, D
Gillespie, M
Pazderka-Robinson, H
Boadu, K
STRUCTURAL EQUATION MODELING, 2003, 10 (02): : 289 - 311
[7] GENERATION OF CAUSAL AND SEMICAUSAL 2-D IIR STRUCTURES FROM FIR STRUCTURES VIA STATE FEEDBACK
LEHNER, D
UNBEHAUEN, R
INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS, 1987, 15 (04) : 391 - 398

← 1 →