Scaling Up Bayesian DAG Sampling

TL;DR

This paper introduces two techniques to enhance Bayesian network structure sampling efficiency, including optimized move implementation and parent set pruning, leading to significant performance improvements.

Contribution

The paper presents novel methods for faster Bayesian DAG sampling by optimizing move operations and pruning parent sets, reducing computational costs.

Findings

Significant efficiency gains over previous methods.

Effective pruning of parent sets preserves sampling accuracy.

Optimized move implementation accelerates DAG sampling.

Abstract

Bayesian inference of Bayesian network structures is often performed by sampling directed acyclic graphs along an appropriately constructed Markov chain. We present two techniques to improve sampling. First, we give an efficient implementation of basic moves, which add, delete, or reverse a single arc. Second, we expedite summing over parent sets, an expensive task required for more sophisticated moves: we devise a preprocessing method to prune possible parent sets so as to approximately preserve the sums. Our empirical study shows that our techniques can yield substantial efficiency gains compared to previous methods.