Transport information geometry: Riemannian calculus on probability simplex

DOI10.1007/S41884-021-00059-1zbMATH Open1493.49047arXiv1803.06360OpenAlexW3212574796WikidataQ115371023 ScholiaQ115371023MaRDI QIDQ2154659FDOQ2154659

Authors: Wuchen Li 

Publication date: 20 July 2022

Published in: Information Geometry (Search for Journal in Brave)

Abstract: We formulate the Riemannian calculus of the probability set embedded with $L^2$-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 $Gamm{a}_2$ operator (carr{'e} du champ it{'e}r{'e}) by connecting Fisher-Rao information metric and optimal transport metric. Several examples are demonstrated.

Full work available at URL: https://arxiv.org/abs/1803.06360

Recommendations

• Wasserstein Riemannian geometry of Gamma densities
• Hessian metric via transport information geometry
• Information geometry
• Some geometric calculations on Wasserstein space
• Information geometry of Wasserstein divergence

zbMATH Keywords

graphoptimal transportinformation geometrylinear weighted Laplacianprobability manifold

Mathematics Subject Classification ID

Optimal transportation (49Q22) Information theory (general) (94A15) Transportation, logistics and supply chain management (90B06)

Cites Work

• Optimal Transport
• Title not available (Why is that?)
• Ricci curvature for metric-measure spaces via optimal transport
• On the geometry of metric measure spaces. I
• THE GEOMETRY OF DISSIPATIVE EVOLUTION EQUATIONS: THE POROUS MEDIUM EQUATION
• Title not available (Why is that?)
• The Variational Formulation of the Fokker--Planck Equation
• Title not available (Why is that?)
• On the Volume Elements on a Manifold
• Contractions in the 2-Wasserstein length space and thermalization of granular media
• Fokker-Planck equations for a free energy functional or Markov process on a graph
• A gradient structure for reaction–diffusion systems and for energy-drift-diffusion systems
• Polar factorization of maps on Riemannian manifolds
• Gradient flows of the entropy for finite Markov chains
• Constrained steepest descent in the 2-Wasserstein metric
• Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
• On harmonic and Killing vector fields
• Title not available (Why is that?)
• Conservative diffusions
• Some geometric calculations on Wasserstein space
• The Density Manifold and Configuration Space Quantization
• Title not available (Why is that?)
• Entropic measure and Wasserstein diffusion
• Natural gradient via optimal transport
• Information Geometry
• Ricci curvature for parametric statistics via optimal transport
• Geodesics of minimal length in the set of probability measures on graphs

Cited In (7)

• Diffusion hypercontractivity via generalized density manifold
• Geometric thermodynamics for the Fokker-Planck equation: stochastic thermodynamic links between information geometry and optimal transport
• Riemann-Finsler geometry with applications to information geometry
• Wasserstein information matrix
• Tracial smooth functions of non-commuting variables and the free Wasserstein manifold
• Exponential entropy dissipation for weakly self-consistent Vlasov-Fokker-Planck equations
• When optimal transport meets 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)