This project provides a group of new algorithms designed to deliver globally optimal solutions for Gaussian mixture models. The Expectation-Maximization algorithm is definitely a popular and straightforward way for the estimation of Gaussian mixture models along with its natural extension, model-based clustering. Having said that, although the algorithm is not hard to use and numerically it is very stable but it provides solutions which are locally optimal.
The Expectation-Maximization (EM) algorithm is a popular and convenient tool for the estimation of Gaussian mixture models and its natural extension, model-based clustering. However, while the algorithm is convenient to implement and numerically very stable, it only produces solutions that are locally