The -Divergence Expectation Iteration Scheme
Abstract
This paper introduces the -EI algorithm, a novel iterative algorithm which operates on measures and performs -divergence minimisation in a Bayesian framework. We prove that for a rich family of values of this algorithm leads at each step to a systematic decrease in the -divergence and show that we achieve an optimum. In the particular case where we consider a weighted sum of Dirac measures and the -divergence, we obtain that the calculations involved in the -EI algorithm simplify to gradient-based computations. Empirical results support the claim that the -EI algorithm serves as a powerful tool to assist Variational methods.
View on arXivComments on this paper