Approximate Mean Field for Dirichlet-Based Models

Variational inference is an important class of approximate inference techniques that has been applied to many graphical models, including topic models. We propose to improve the efficiency of mean field inference for Dirichlet-based models by introducing an approximative framework that converts weighted geometric means in the updates into weighted arithmetic means. This paper also discusses a close resemblance between our approach and other methods, such as the factorized neighbors algorithm and belief propagation. Empirically, we find that our approach is accurate and efficient compared to standard mean field.