Theoretical and Computational Guarantees of Mean Field Variational Inference for Community Detection
This addresses the lack of theoretical justification for mean field variational inference in high-dimensional complex models, specifically for community detection problems.
The authors provided theoretical guarantees for mean field variational inference applied to community detection under the Stochastic Block Model, showing that the Batch Coordinate Ascent Variational Inference algorithm achieves linear convergence and reaches the minimax rate within log n iterations.
The mean field variational Bayes method is becoming increasingly popular in statistics and machine learning. Its iterative Coordinate Ascent Variational Inference algorithm has been widely applied to large scale Bayesian inference. See Blei et al. (2017) for a recent comprehensive review. Despite the popularity of the mean field method there exist remarkably little fundamental theoretical justifications. To the best of our knowledge, the iterative algorithm has never been investigated for any high dimensional and complex model. In this paper, we study the mean field method for community detection under the Stochastic Block Model. For an iterative Batch Coordinate Ascent Variational Inference algorithm, we show that it has a linear convergence rate and converges to the minimax rate within $\log n$ iterations. This complements the results of Bickel et al. (2013) which studied the global minimum of the mean field variational Bayes and obtained asymptotic normal estimation of global model parameters. In addition, we obtain similar optimality results for Gibbs sampling and an iterative procedure to calculate maximum likelihood estimation, which can be of independent interest.