Learning Bounded Treewidth Bayesian Networks with Thousands of Variables

TL;DR

This paper introduces a scalable algorithm for learning Bayesian networks with bounded treewidth from large datasets, significantly improving efficiency and performance over existing methods.

Contribution

A novel algorithm capable of learning large-scale bounded treewidth Bayesian networks, outperforming current state-of-the-art approaches on datasets with up to ten thousand variables.

Findings

Outperforms existing methods on large datasets

Scales effectively to thousands of variables

Maintains low inference complexity

Abstract

We present a method for learning treewidth-bounded Bayesian networks from data sets containing thousands of variables. Bounding the treewidth of a Bayesian greatly reduces the complexity of inferences. Yet, being a global property of the graph, it considerably increases the difficulty of the learning process. We propose a novel algorithm for this task, able to scale to large domains and large treewidths. Our novel approach consistently outperforms the state of the art on data sets with up to ten thousand variables.