Search Results for author: Jesse van Oostrum

Found 3 papers, 0 papers with code

On the Fisher-Rao Gradient of the Evidence Lower Bound

no code implementations20 Jul 2023 Nihat Ay, Jesse van Oostrum

This article studies the Fisher-Rao gradient, also referred to as the natural gradient, of the evidence lower bound, the ELBO, which plays a crucial role within the theory of the Variational Autonecoder, the Helmholtz Machine and the Free Energy Principle.

Inversion of Bayesian Networks

no code implementations20 Dec 2022 Jesse van Oostrum, Peter van Hintum, Nihat Ay

Variational autoencoders and Helmholtz machines use a recognition network (encoder) to approximate the posterior distribution of a generative model (decoder).

Invariance Properties of the Natural Gradient in Overparametrised Systems

no code implementations30 Jun 2022 Jesse van Oostrum, Johannes Müller, Nihat Ay

The natural gradient field is a vector field that lives on a model equipped with a distinguished Riemannian metric, e. g. the Fisher-Rao metric, and represents the direction of steepest ascent of an objective function on the model with respect to this metric.

Cannot find the paper you are looking for? You can Submit a new open access paper.