# A provably convergent alternating minimization method for mean field inference

arXiv: https://arxiv.org/abs/1502.05832 · HTML: https://mlsanity.com/paper/1502.05832/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2015.

## Built on by (most cited first, 1 of 1)

- [ADMM Algorithms for Residual Network Training: Convergence Analysis and Parallel Implementation](https://mlsanity.com/paper/2310.15334/) (2023)

## Abstract (arXiv)

Mean-Field is an efficient way to approximate a posterior distribution in complex graphical models and constitutes the most popular class of Bayesian variational approximation methods. In most applications, the mean field distribution parameters are computed using an alternate coordinate minimization. However, the convergence properties of this algorithm remain unclear. In this paper, we show how, by adding an appropriate penalization term, we can guarantee convergence to a critical point, while keeping a closed form update at each step. A convergence rate estimate can also be derived based on recent results in non-convex optimization.