PhD course on Information Geometry in Learning and Optimization – Københavns Universitet

PhD course on Information Geometry in Learning and Optimization

Background

Principles of Information Geometry have been successfully applied in all major areas of machine learning, including supervised, unsupervised, and reinforcement learning, as well as in stochastic optimization. Information Geometry comes into play when we consider parametrized probabilistic models (e.g., in the context of stochastic behavioral policies, search distributions, stochastic neural networks, ...) and their adaptation. Technically speaking, in Information Geometry the space of probability distributions that can be represented by a parametrized probabilistic model is described as a manifold, on which the Fisher information metric defines a Riemannian structure. Through the geometry of the Riemannian manifold of distributions, optimization and statistics can be done directly on the space of distributions.

Read more at the course page.