Order-independent structure learning of multivariate regression chain graphs

DOI10.1007/978-3-030-35514-2_24MaRDI QIDQ3297816zbMATH OpenOpenAlexFDO

Authors Mohammad Ali Javidian, Marco Valtorta, Pooyan Jamshidi

Publication date 20 July 2020

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1910.01067

zbMATH Keywords

high-dimensional datastructural learningorder independencemultivariate regression chain graphscalable machine learning techniques

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Abstract: This paper deals with multivariate regression chain graphs (MVR CGs), which were introduced by Cox and Wermuth [3,4] to represent linear causal models with correlated errors. We consider the PC-like algorithm for structure learning of MVR CGs, which is a constraint-based method proposed by Sonntag and Pe~{n}a in [18]. We show that the PC-like algorithm is order-dependent, in the sense that the output can depend on the order in which the variables are given. This order-dependence is a minor issue in low-dimensional settings. However, it can be very pronounced in high-dimensional settings, where it can lead to highly variable results. We propose two modifications of the PC-like algorithm that remove part or all of this order-dependence. Simulations under a variety of settings demonstrate the competitive performance of our algorithms in comparison with the original PC-like algorithm in low-dimensional settings and improved performance in high-dimensional settings.

Recommendations

• A decomposition-based algorithm for learning the structure of multivariate regression chain graphs
• Order-independent constraint-based causal structure learning
• AMP chain graphs: minimal separators and structure learning algorithms
• Chain graph models of multivariate regression type for categorical data
• Sequences of regressions and their independences

Cites work

• scientific article; zbMATH DE number 5968958 (Why is no real title available?)
• scientific article; zbMATH DE number 4174001 (Why is no real title available?)
• scientific article; zbMATH DE number 3859178 (Why is no real title available?)
• scientific article; zbMATH DE number 48812 (Why is no real title available?)
• Causality. Models, reasoning, and inference
• Causation, prediction, and search
• Chain graph interpretations and their relations revisited
• Discrete chain graph models
• Estimating high-dimensional directed acyclic graphs with the PC-algorithm
• Graphical models for associations between variables, some of which are qualitative and some quantitative
• Linear dependencies represented by chain graphs. With comments and a rejoinder by the authors
• Markov Properties for Acyclic Directed Mixed Graphs
• Order-independent constraint-based causal structure learning
• Sequences of regressions and their independences
• The max-min hill-climbing Bayesian network structure learning algorithm

Cited in

(5)

• AMP chain graphs: minimal separators and structure learning algorithms
• scientific article; zbMATH DE number 5968958 (Why is no real title available?)
• Chain graph structure learning based on minimal c-separation trees
• Order-independent constraint-based causal structure learning
• A decomposition-based algorithm for learning the structure of multivariate regression chain graphs

Describes a project that uses

Uses Software

• TETRAD

This page was built for publication: Order-independent structure learning of multivariate regression chain graphs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3297816)