ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1909.12239
17
1

The fff-Divergence Expectation Iteration Scheme

26 September 2019
Kamélia Daudel
Randal Douc
Franccois Portier
François Roueff
ArXivPDFHTML
Abstract

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

View on arXiv
Comments on this paper