Projects per year
Abstract
One of the common obstacles for learning causal models from data is that highorder conditional independence (CI) relationships between random variables are difficult to estimate. Since CI tests with conditioning sets of low order can be performed accurately even for a small number of observations, a reasonable approach to determine casual structures is to base merely on the loworder CIs. Recent research has confirmed that, e.g. in the case of sparse true causal models, structures learned even from zero and firstorder conditional independencies yield good approximations of the models. However, a challenging task here is to provide methods that faithfully explain a given set of loworder CIs. In this paper, we propose an algorithm which, for a given set of conditional independencies of order less or equal to k, where k is a small fixed number, computes a faithful graphical representation of the given set. Our results complete and generalize the previous work on learning from pairwise marginal independencies. Moreover, they enable to improve upon the 01 graph model which, e.g. is heavily used in the estimation of genome networks.
Original language  English 

Pages  1030210309 
Number of pages  8 
DOIs  
Publication status  Published  03.04.2020 
Event  The ThirtyFourth AAAI Conference on Artificial Intelligence  New York, United States Duration: 07.02.2020 → 12.02.2020 
Conference
Conference  The ThirtyFourth AAAI Conference on Artificial Intelligence 

Abbreviated title  AAAI20 
Country/Territory  United States 
City  New York 
Period  07.02.20 → 12.02.20 
DFG Research Classification Scheme
 4.4301 Theoretical Computer Science
Fingerprint
Dive into the research topics of 'Recovering Causal Structures from LowOrder Conditional Independencies'. Together they form a unique fingerprint.Projects
 1 Finished

Causality: an algorithmic framework and a computational complexity perspective
Liskiewicz, M. & Textor, J.
01.01.16 → 31.12.22
Project: DFG Projects › DFG Individual Projects