Transport information Bregman divergences
From MaRDI portal
Publication:2064256
Abstract: We study Bregman divergences in probability density space embedded with the --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 --Wasserstein space. We also derive analytical formulas and generalizations of transport KL divergence for one-dimensional probability densities and Gaussian families.
Recommendations
- Information geometry of Wasserstein divergence
- Information geometry for regularized optimal transport and barycenters of patterns
- Information geometry connecting Wasserstein distance and Kullback-Leibler divergence via the entropy-relaxed transportation problem
- Hessian transport gradient flows
- Metrics defined by Bregman divergences
Cites work
- A convexity principle for interacting gases
- Bregman Iterative Algorithms for \ell₁-Minimization with Applications to Compressed Sensing
- Combinatorial optimization with information geometry: the Newton method
- Computational optimal transport. With applications to data sciences
- Diffeomorphisms and Nonlinear Heat Flows
- Families of alpha-, beta- and gamma-divergences: flexible and robust measures of similarities
- Geometric hydrodynamics via Madelung transform
- Geometry of matrix decompositions seen through optimal transport and information geometry
- Gradient flows in metric spaces and in the space of probability measures
- scientific article; zbMATH DE number 107482 (Why is no real title available?)
- scientific article; zbMATH DE number 3894218 (Why is no real title available?)
- scientific article; zbMATH DE number 3252891 (Why is no real title available?)
- Information geometry
- Information geometry and its applications
- Information geometry connecting Wasserstein distance and Kullback-Leibler divergence via the entropy-relaxed transportation problem
- Logarithmic divergences from optimal transport and Rényi geometry
- Natural gradient flow in the mixture geometry of a discrete exponential family
- Natural gradient via optimal transport
- Optimal Transport
- Ricci curvature for parametric statistics via optimal transport
- Semi-invariant Riemannian metrics in hydrodynamics
- The Density Manifold and Configuration Space Quantization
- THE GEOMETRY OF DISSIPATIVE EVOLUTION EQUATIONS: THE POROUS MEDIUM EQUATION
- The Variational Formulation of the Fokker--Planck Equation
- Towards a canonical divergence within information geometry
- Wasserstein geometry of Gaussian measures
Cited in
(13)- Metrics defined by Bregman divergences
- Information geometry of Wasserstein divergence
- On a prior based on the Wasserstein information matrix
- When optimal transport meets information geometry
- Hessian transport gradient flows
- Relation between the Kantorovich-Wasserstein metric and the Kullback-Leibler divergence
- (f,)-divergences: interpolating between f-divergences and integral probability metrics
- Information geometry for regularized optimal transport and barycenters of patterns
- Bregman divergence and density integration
- Hessian metric via transport information geometry
- Geometric calculations on density manifolds from reciprocal relations in hydrodynamics
- Information geometry of the Otto metric
- Expansive natural neural gradient flows for energy minimization
This page was built for publication: Transport information Bregman divergences
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2064256)