Dual Connections in Nonparametric Classical Information Geometry

Abstract

We construct an infinite-dimensional information manifold based on exponential Orlicz spaces without using the notion of exponential convergence. We then show that convex mixtures of probability densities lie on the same connected component of this manifold, and characterize the class of densities for which this mixture can be extended to an open segment containing the extreme points. For this class, we define an infinite-dimensional analogue of the mixture parallel transport and prove that it is dual to the exponential parallel transport with respect to the Fisher information. We also define α-derivatives and prove that they are convex mixtures of the extremal (\pm 1)-derivatives.

Cited by in corpus (7)

• Examples of Application of Nonparametric Information Geometry to Statistical Physics
• Quantum Statistical Manifolds
• Infinite-dimensional statistical manifolds based on a balanced chart
• Parameter-free description of the manifold of non-degenerate density matrices
• Exponential arcs in manifolds of quantum states
• The exponential Orlicz space in quantum information geometry
• Variational Representations of Annealing Paths: Bregman Information under Monotonic Embedding