Transport information geometry: Riemannian calculus on probability simplex
From MaRDI portal
Publication:2154659
Abstract: We formulate the Riemannian calculus of the probability set embedded with -Wasserstein metric. This is an initial work of transport information geometry. Our investigation starts with the probability simplex (probability manifold) supported on vertices of a finite graph. The main idea is to embed the probability manifold as a submanifold of the positive measure space with a nonlinear metric tensor. Here the nonlinearity comes from the linear weighted Laplacian operator. By this viewpoint, we establish torsion-free Christoffel symbols, Levi-Civita connections, curvature tensors and volume forms in the probability manifold by Euclidean coordinates. As a consequence, the Jacobi equation, Laplace-Beltrami and Hessian operators on the probability manifold are derived. These geometric computations are also provided in the infinite-dimensional density space (density manifold) supported on a finite-dimensional manifold. In particular, an identity is given connecting the Baker-{'E}mery operator (carr{'e} du champ it{'e}r{'e}) by connecting Fisher-Rao information metric and optimal transport metric. Several examples are demonstrated.
Recommendations
Cites work
- scientific article; zbMATH DE number 3818206 (Why is no real title available?)
- scientific article; zbMATH DE number 3897897 (Why is no real title available?)
- scientific article; zbMATH DE number 1077733 (Why is no real title available?)
- scientific article; zbMATH DE number 1111349 (Why is no real title available?)
- scientific article; zbMATH DE number 3894218 (Why is no real title available?)
- A gradient structure for reaction–diffusion systems and for energy-drift-diffusion systems
- Conservative diffusions
- Constrained steepest descent in the 2-Wasserstein metric
- Contractions in the 2-Wasserstein length space and thermalization of granular media
- Entropic measure and Wasserstein diffusion
- Fokker-Planck equations for a free energy functional or Markov process on a graph
- Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
- Geodesics of minimal length in the set of probability measures on graphs
- Gradient flows of the entropy for finite Markov chains
- Information geometry
- Natural gradient via optimal transport
- On harmonic and Killing vector fields
- On the Volume Elements on a Manifold
- On the geometry of metric measure spaces. I
- Optimal Transport
- Polar factorization of maps on Riemannian manifolds
- Ricci curvature for metric-measure spaces via optimal transport
- Ricci curvature for parametric statistics via optimal transport
- Some geometric calculations on Wasserstein space
- THE GEOMETRY OF DISSIPATIVE EVOLUTION EQUATIONS: THE POROUS MEDIUM EQUATION
- The Density Manifold and Configuration Space Quantization
- The Variational Formulation of the Fokker--Planck Equation
Cited in
(10)- Riemann-Finsler geometry with applications to information geometry
- Diffusion hypercontractivity via generalized density manifold
- When optimal transport meets information geometry
- Wasserstein Riemannian geometry of Gamma densities
- Exponential entropy dissipation for weakly self-consistent Vlasov-Fokker-Planck equations
- Wasserstein information matrix
- Hessian metric via transport information geometry
- Tracial smooth functions of non-commuting variables and the free Wasserstein manifold
- Geometric thermodynamics for the Fokker-Planck equation: stochastic thermodynamic links between information geometry and optimal transport
- Geometry of matrix decompositions seen through optimal transport and information geometry
This page was built for publication: Transport information geometry: Riemannian calculus on probability simplex
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2154659)
