15
1

The ff-Divergence Expectation Iteration Scheme

Abstract

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

View on arXiv
Comments on this paper