Heron Inference for Bayesian Graphical Models

TL;DR

This paper introduces Heron, a deterministic inference method for Bayesian graphical models that improves efficiency and convergence assessment, outperforming traditional Gibbs sampling and state augmentation methods.

Contribution

Heron extends Gibbs sampling with a deterministic approach, enhancing efficiency and convergence monitoring in Bayesian graphical model inference.

Findings

Heron significantly outperforms baseline methods in real-world data inference.

Heron improves computational efficiency and convergence assessment.

Experimental results validate Heron's superior performance.

Abstract

Bayesian graphical models have been shown to be a powerful tool for discovering uncertainty and causal structure from real-world data in many application fields. Current inference methods primarily follow different kinds of trade-offs between computational complexity and predictive accuracy. At one end of the spectrum, variational inference approaches perform well in computational efficiency, while at the other end, Gibbs sampling approaches are known to be relatively accurate for prediction in practice. In this paper, we extend an existing Gibbs sampling method, and propose a new deterministic Heron inference (Heron) for a family of Bayesian graphical models. In addition to the support for nontrivial distributability, one more benefit of Heron is that it is able to not only allow us to easily assess the convergence status but also largely improve the running efficiency. We evaluate Heron against the standard collapsed Gibbs sampler and state-of-the-art state augmentation method in inference for well-known graphical models. Experimental results using publicly available real-life data have demonstrated that Heron significantly outperforms the baseline methods for inferring Bayesian graphical models.