Transport information Bregman divergences

Abstract

We study Bregman divergences in probability density space embedded with the $L^2$-Wasserstein metric. Several properties and dualities of transport Bregman divergences are provided. In particular, we derive the transport Kullback-Leibler (KL) divergence by a Bregman divergence of negative Boltzmann-Shannon entropy in $L^2$-Wasserstein space. We also derive analytical formulas and generalizations of transport KL divergence for one-dimensional probability densities and Gaussian families.

Typos are corrected

References in corpus (7)

• On a generalization of the Jensen-Shannon divergence and the JS-symmetrization of distances relying on abstract means
• Transport information geometry I: Riemannian calculus on probability simplex
• Geometric hydrodynamics and infinite-dimensional Newton's equations
• Semi-invariant Riemannian metrics in hydrodynamics
• Application of Optimal Transport and the Quadratic Wasserstein Metric to Full-Waveform Inversion
• Pseudo-Riemannian geometry embeds information geometry in optimal transport
• Ambiguity set and learning via Bregman and Wasserstein

Cited by in corpus (1)

• Transport information Hessian distances