Hessian transport gradient flows
From MaRDI portal
Publication:2336045
Abstract: We derive new gradient flows of divergence functions in the probability space embedded with a class of Riemannian metrics. The Riemannian metric tensor is built from the transported Hessian operator of an entropy function. The new gradient flow is a generalized Fokker-Planck equation and is associated with a stochastic differential equation that depends on the reference measure. Several examples of Hessian transport gradient flows and the associated stochastic differential equations are presented, including the ones for the reverse Kullback--Leibler divergence, alpha-divergence, Hellinger distance, Pearson divergence, and Jenson--Shannon divergence.
Recommendations
- Hessian metric via transport information geometry
- Wasserstein space over the Wiener space
- Transport information Bregman divergences
- \{Euclidean, metric, and Wasserstein\} gradient flows: an overview
- Gradient flows in metric spaces and in the spaces of probability measures, and applications to Fokker-Planck equations with respect to log-concave measures
Cites work
- scientific article; zbMATH DE number 3897897 (Why is no real title available?)
- scientific article; zbMATH DE number 107482 (Why is no real title available?)
- A new class of transport distances between measures
- A unified formulation for the Bures-Wasserstein and log-Euclidean/log-Hilbert-Schmidt distances between positive definite operators
- Affine natural proximal learning
- An interpolating distance between optimal transport and Fisher-Rao metrics
- Asymmetry in crystal facet dynamics of homoepitaxy by a continuum model
- Diffeomorphic density matching by optimal information transport
- Entropy dissipation of Fokker-Planck equations on graphs
- Exponential decay of Rényi divergence under Fokker-Planck equations
- Free Fisher information for non-tracial states.
- Information Theory and Statistics: A Tutorial
- Information geometry
- Information geometry and its applications
- Information geometry connecting Wasserstein distance and Kullback-Leibler divergence via the entropy-relaxed transportation problem
- Natural gradient via optimal transport
- Nonlinear mobility continuity equations and generalized displacement convexity
- ON CONVEX SOBOLEV INEQUALITIES AND THE RATE OF CONVERGENCE TO EQUILIBRIUM FOR FOKKER-PLANCK TYPE EQUATIONS
- Optimal Transport
- Optimal entropy-transport problems and a new Hellinger-Kantorovich distance between positive measures
- Possible generalization of Boltzmann-Gibbs statistics.
- Ricci curvature for parametric statistics via optimal transport
- Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime
- Semi-invariant Riemannian metrics in hydrodynamics
- Stochastic processes and applications. Diffusion processes, the Fokker-Planck and Langevin equations
- 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
- Wasserstein Riemannian geometry of Gaussian densities
- Wasserstein proximal of GANs
- deBruijn identities: From Shannon, Kullback-Leibler and Fisher to generalized φ-entropies, φ-divergences and φ-Fisher informations
Cited in
(10)- Diffusion hypercontractivity via generalized density manifold
- Spherical Hellinger-Kantorovich gradient flows
- Computational mean-field information dynamics associated with reaction-diffusion equations
- Huygens' equations and the gradient-flow equations in information geometry
- Controlling conservation laws. I: entropy-entropy flux
- Hessian metric via transport information geometry
- Covariance-modulated optimal transport and gradient flows
- Transport information Bregman divergences
- Hessian Riemannian Gradient Flows in Convex Programming
- Unconditionally energy stable and bound-preserving schemes for phase-field surfactant model with moving contact lines
This page was built for publication: Hessian transport gradient flows
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2336045)
