Statistical Physics, Mixtures of Distributions, and the EM Algorithm
Alan Yuille, Paul Stolorz, Joachim Utans · Neural Computation · 1994
We show that there are strong relationships between approaches to optmization and learning based on statistical physics or mixtures of experts. In particular, the EM algorithm can be interpreted as converging either to a local maximum of the mixtures model or to a saddle point solution to the statistical physics system. An advantage of the statistical physics approach is that it naturally gives rise to a heuristic continuation method, deterministic annealing, for finding good solutions.