PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Causal graphical models with latent variables: Learning and inference
Stijn Meganck, Philippe Leray and B. Manderick
In: Ninth European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty ECSQARU 2007, Tunisia(2007).

Abstract

Several paradigms exist for modeling causal graphical models for discrete variables that can handle latent variables without explicitly modeling them quantitatively. Applying them to a problem domain con- sists of different steps: structure learning, parameter learning and using them for probabilistic or causal inference. We discuss two well-known formalisms, namely semi-Markovian causal models and maximal ances- tral graphs and indicate their strengths and limitations. Previously an algorithm has been constructed that by combining elements from both techniques allows to learn a semi-Markovian causal models from a mix- ture of observational and experimental data. The goal of this paper is to recapitulate the integral learning process from observational and experi- mental data and to demonstrate how different types of inference can be performed efficiently in the learned models. We will do this by proposing an alternative representation for semi-Markovian causal models.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:3771
Deposited By:Philippe Leray
Deposited On:21 February 2008