Poster
in
Workshop: Duality Principles for Modern Machine Learning

On the Fisher-Rao Gradient of the Evidence Lower Bound

Jesse van Oostrum ⋅ Nihat Ay

Keywords: evidence lower bound information geometry natural gradient variational autoencoder

Abstract

This article studies the Fisher-Rao gradient, also referred to as the natural gradient, of the evidence lower bound, known from machine learning. Based on invariance properties of gradients within information geometry, it derives conditions on the underlying model that ensure the exactness for this bound. Information geometry is naturally based on duality concepts from differential geometry.

Video

Chat is not available.