Infinite-dimensional gradient-based descent for alpha-divergence minimisation

15 Oct 2020 Daudel Kamélia Douc Randal Portier François

This paper introduces the $(\alpha, \Gamma)$-descent, an iterative algorithm which operates on measures and performs $\alpha$-divergence minimisation in a Bayesian framework. This gradient-based procedure extends the commonly-used variational approximation by adding a prior on the variational parameters in the form of a measure... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Categories


  • STATISTICS THEORY
  • STATISTICS THEORY