Ricci curvature for parametric statistics via optimal transport
From MaRDI portal
Publication:2006199
Abstract: We elaborate the notion of a Ricci curvature lower bound for parametrized statistical models. Following the seminal ideas of Lott-Strum-Villani, we define this notion based on the geodesic convexity of the Kullback-Leibler divergence in a Wasserstein statistical manifold, that is, a manifold of probability distributions endowed with a Wasserstein metric tensor structure. Within these definitions, the Ricci curvature is related to both, information geometry and Wasserstein geometry. These definitions allow us to formulate bounds on the convergence rate of Wasserstein gradient flows and information functional inequalities in parameter space. We discuss examples of Ricci curvature lower bounds and convergence rates in exponential family models.
Recommendations
- Ricci curvature for metric-measure spaces via optimal transport
- Optimal transport and Ricci curvature
- scientific article
- scientific article; zbMATH DE number 1053583
- Diffusion, optimal transport and Ricci curvature for metric measure space
- Ricci curvature, entropy, and optimal transport
- Statistics on Riemannian manifolds: asymptotic distribution and curvature
- Diffusion, optimal transport and Ricci curvature
- Optimal transport and Ricci curvature in Finsler geometry
- Embedding optimal transports in statistical manifolds
Cites work
- scientific article; zbMATH DE number 3894218 (Why is no real title available?)
- A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
- A curved Brunn-Minkowski inequality on the discrete hypercube, or: what is the Ricci curvature of the discrete hypercube?
- A fast scoring algorithm for maximum likelihood estimation in unbalanced mixed models with nested random effects
- Constrained steepest descent in the 2-Wasserstein metric
- Discrete Ricci curvature bounds for Bernoulli-Laplace and random transposition models
- Earth mover's distances on discrete surfaces
- Entropic Ricci curvature bounds for discrete interacting systems
- 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
- Generalized Iterative Scaling for Log-Linear Models
- Geodesic convexity of the relative entropy in reversible Markov chains
- Geometric analysis aspects of infinite semiplanar graphs with nonnegative curvature
- Gradient flow formulation and longtime behaviour of a constrained Fokker-Planck equation
- Gradient flows of the entropy for finite Markov chains
- Information Theory and Statistics: A Tutorial
- Information geometry
- Information geometry and its applications
- Natural gradient via optimal transport
- Ollivier's Ricci curvature, local clustering and curvature-dimension inequalities on graphs
- On the geometry of metric measure spaces. I
- Optimal Transport
- Poincaré, modified logarithmic Sobolev and isoperimetric inequalities for Markov chains with non-negative Ricci curvature
- Ricci curvature and eigenvalue estimate on locally finite graphs
- Ricci curvature bounds for weakly interacting Markov chains
- Ricci curvature for metric-measure spaces via optimal transport
- Ricci curvature of Markov chains on metric spaces
- Ricci curvature of finite Markov chains via convexity of the entropy
- Ricci curvature of graphs
- Super Ricci flows for weighted graphs
- 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
(20)- Wasserstein statistics in one-dimensional location scale models
- Wasserstein statistics in one-dimensional location-scale models
- Diffusion hypercontractivity via generalized density manifold
- scientific article; zbMATH DE number 1053583 (Why is no real title available?)
- Optimal transport natural gradient for statistical manifolds with continuous sample space
- Wasserstein proximal of GANs
- Quantum statistical learning via quantum Wasserstein natural gradient
- Neural parametric Fokker-Planck equation
- Natural gradient for combined loss using wavelets
- Wasserstein information matrix
- Transport information geometry: Riemannian calculus on probability simplex
- Hessian transport gradient flows
- Wasserstein Riemannian geometry on statistical manifold
- Transport information Bregman divergences
- On some connections between Esscher's tilting, saddlepoint approximations, and optimal transportation: a statistical perspective
- When optimal transport meets information geometry
- Information geometry of Wasserstein statistics on shapes and affine deformations
- Hessian metric via transport information geometry
- Logarithmic divergences from optimal transport and Rényi geometry
- Natural gradient via optimal transport
This page was built for publication: Ricci curvature for parametric statistics via optimal transport
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2006199)