An interpolating distance between optimal transport and Fisher-Rao metrics
From MaRDI portal
Publication:1704812
convex variational problemFisher-Rao metricgeodesicspositive Radon measuresunbalanced optimal transportWasserstein \(L^2\)~metric
Spaces of measures, convergence of measures (28A33) Integration theory via linear functionals (Radon measures, Daniell integrals, etc.), representing set functions and measures (28C05) Variational problems in a geometric measure-theoretic setting (49Q20) Variational problems in applications to the theory of geodesics (problems in one independent variable) (58E10) Transportation, logistics and supply chain management (90B06)
Abstract: This paper defines a new transport metric over the space of non-negative measures. This metric interpolates between the quadratic Wasserstein and the Fisher-Rao metrics and generalizes optimal transport to measures with different masses. It is defined as a generalization of the dynamical formulation of optimal transport of Benamou and Brenier, by introducing a source term in the continuity equation. The influence of this source term is measured using the Fisher-Rao metric, and is averaged with the transportation term. This gives rise to a convex variational problem defining our metric. Our first contribution is a proof of the existence of geodesics (i.e. solutions to this variational problem). We then show that (generalized) optimal transport and Fisher-Rao metrics are obtained as limiting cases of our metric. Our last theoretical contribution is a proof that geodesics between mixtures of sufficiently close Diracs are made of translating mixtures of Diracs. Lastly, we propose a numerical scheme making use of first order proximal splitting methods and we show an application of this new distance to image interpolation.
Recommendations
- Unbalanced optimal transport: dynamic and Kantorovich formulations
- A new optimal transport distance on the space of finite Radon measures
- A new class of transport distances between measures
- Optimal entropy-transport problems and a new Hellinger-Kantorovich distance between positive measures
- Computations of optimal transport distance with Fisher information regularization
Cites work
- A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
- A generalized model for optimal transport of images including dissipation and density modulation
- A new class of transport distances between measures
- A new optimal transport distance on the space of finite Radon measures
- A new transportation distance between non-negative measures, with applications to gradients flows with Dirichlet boundary conditions
- Computing large deformation metric mappings via geodesic flows of diffeomorphisms
- Duality and stability in extremum problems involving convex functions
- Dynamic formulation of optimal transport problems
- Eulerian models and algorithms for unbalanced optimal transport
- Free boundaries in optimal transport and Monge-Ampère obstacle problems
- Generalized Wasserstein distance and its application to transport equations with source
- Geodesics for a class of distances in the space of probability measures
- Gradient flows in metric spaces and in the space of probability measures
- scientific article; zbMATH DE number 1909499 (Why is no real title available?)
- scientific article; zbMATH DE number 3106666 (Why is no real title available?)
- Information geometry and sufficient statistics
- Integrals which are convex functionals. II
- Kantorovich-Rubinstein Norm and Its Application in the Theory of Lipschitz Spaces
- Metamorphoses through Lie group action
- Mixed L^2-Wasserstein optimal mapping between prescribed density functions
- New lower semicontinuity results for nonconvex functionals defined on measures
- Numerical resolution of an “unbalanced” mass transport problem
- On properties of the generalized Wasserstein distance
- Optimal mass transport for registration and warping
- Optimal transport with proximal splitting
- Proximal splitting methods in signal processing
- The optimal partial transport problem
- Uniqueness of the Fisher-Rao metric on the space of smooth densities
Cited in
(only showing first 100 items - show all)- Computations of optimal transport distance with Fisher information regularization
- Unbalanced and partial \(L_1\) Monge-Kantorovich problem: a scalable parallel first-order method
- Optimal entropy-transport problems and a new Hellinger-Kantorovich distance between positive measures
- A transportation \(L^p\) distance for signal analysis
- Unbalanced optimal transport: dynamic and Kantorovich formulations
- Geometric properties of cones with applications on the Hellinger-Kantorovich space, and a new distance on the space of probability measures
- Semi-invariant Riemannian metrics in hydrodynamics
- Contraction and regularizing properties of heat flows in metric measure spaces
- Nonlinear Fokker-Planck equations with reaction as gradient flows of the free energy
- Ground metric learning on graphs
- Metrics, quantization and registration in varifold spaces
- Kantorovich-Rubinstein distance and barycenter for finitely supported measures: foundations and algorithms
- Data-driven gradient flows
- Partial differential equations with quadratic nonlinearities viewed as matrix-valued optimal ballistic transport problems
- Generalized unnormalized optimal transport and its fast algorithms
- The square root normal field distance and unbalanced optimal transport
- Weight metamorphosis of varifolds and the LDDMM-Fisher-Rao metric
- Sparse optimization on measures with over-parameterized gradient descent
- When optimal transport meets information geometry
- Pseudo-Riemannian geometry encodes information geometry in optimal transport
- Tropical optimal transport and Wasserstein distances
- Computational mean-field information dynamics associated with reaction-diffusion equations
- Unnormalized optimal transport
- The Schrödinger problem on the non-commutative Fisher-Rao space
- Optimal transport: discretization and algorithms
- Optimal interpolants on Grassmann manifolds
- Convex Sobolev inequalities related to unbalanced optimal transport
- Generalized compressible flows and solutions of the \(H(\text{div})\) geodesic problem
- Multi-species optimal transportation
- Second-order models for optimal transport and cubic splines on the Wasserstein Space
- Hessian transport gradient flows
- On geodesic completeness for Riemannian metrics on smooth probability densities
- Darcy's law with a source term
- A note on the differentiability of the Hellinger-Kantorovich distances
- Optimal transport in competition with reaction: the Hellinger-Kantorovich distance and geodesic curves
- A fitness-driven cross-diffusion system from population dynamics as a gradient flow
- Scaling algorithms for unbalanced optimal transport problems
- Entropic and displacement interpolation: a computational approach using the Hilbert metric
- Transport between RGB images motivated by dynamic optimal transport
- Barycenters for the Hellinger-Kantorovich distance over \(\mathbb{R}^d\)
- Geodesic PCA versus Log-PCA of Histograms in the Wasserstein Space
- Topological data assimilation using Wasserstein distance
- Indirect image registration with large diffeomorphic deformations
- A framework for Wasserstein-1-type metrics
- Leader formation with mean-field birth and death models
- Nonlinear model reduction on metric spaces. Application to one-dimensional conservative PDEs in Wasserstein spaces
- An optimal transport approach for solving dynamic inverse problems in spaces of measures
- A minimizing movement approach to a class of scalar reaction-diffusion equations
- The quadratic Wasserstein metric for inverse data matching
- On the extremal points of the ball of the Benamou-Brenier energy
- The Linearized Hellinger--Kantorovich Distance
- A superposition principle for the inhomogeneous continuity equation with Hellinger–Kantorovich-regular coefficients
- An unbalanced optimal transport splitting scheme for general advection-reaction-diffusion problems
- Dynamic models of Wasserstein-1-type unbalanced transport
- On Optimal Transport of Matrix-Valued Measures
- Unconditional convergence for discretizations of dynamical optimal transport
- A Newton algorithm for semidiscrete optimal transport with storage fees
- Interpolation of matrices and matrix-valued densities: the unbalanced case
- Stabilized Sparse Scaling Algorithms for Entropy Regularized Transport Problems
- Spherical Hellinger-Kantorovich gradient flows
- Penalization of barycenters in the Wasserstein space
- \{Euclidean, metric, and Wasserstein\} gradient flows: an overview
- Quantum entropic regularization of matrix-valued optimal transport
- A JKO splitting scheme for Kantorovich-Fisher-Rao gradient flows
- A tumor growth model of Hele-Shaw type as a gradient flow
- Obstructions to extension of Wasserstein distances for variable masses
- The Wasserstein-Fisher-Rao Metric for Waveform Based Earthquake Location
- Template-based CT reconstruction with optimal transport and total generalized variation
- Birth–death dynamics for sampling: global convergence, approximations and their asymptotics
- Nonlocal Cross-Interaction Systems on Graphs: Nonquadratic Finslerian Structure and Nonlinear Mobilities
- A generalized conditional gradient method for dynamic inverse problems with optimal transport regularization
- Hellinger–Kantorovich barycenter between Dirac measures
- On the Convergence of Continuous and Discrete Unbalanced Optimal Transport Models for 1-Wasserstein Distance
- Dynamical programming for off-the-grid dynamic inverse problems
- Square Root Normal Fields for Lipschitz Surfaces and the Wasserstein Fisher Rao Metric
- Dynamic Optimal Transport on Networks
- Efficient Approximation of Gromov-Wasserstein Distance Using Importance Sparsification
- Fine properties of geodesics and geodesic \(\lambda\)-convexity for the Hellinger-Kantorovich distance
- A machine learning framework for geodesics under spherical Wasserstein-Fisher-Rao metric and its application for weighted sample generation
- Efficient preconditioners for solving dynamical optimal transport via interior point methods
- Linearized optimal transport on manifolds
- A relaxation viewpoint to unbalanced optimal transport: duality, optimality and Monge formulation
- On the convergence of discrete dynamic unbalanced transport models
- Learning Gaussian mixtures using the Wasserstein-Fisher-Rao gradient flow
- Information geometry of Wasserstein statistics on shapes and affine deformations
- Constrained Hellinger-Kantorovich barycenters: least-cost soft and conic multimarginal formulations
- Quantum optimal transport with convex regularization
- Numerical computation of generalized Wasserstein distances with applications to traffic model analysis
- On a general matrix-valued unbalanced optimal transport problem
- Strong c-concavity and stability in optimal transport
- Unbalanced optimal transport, from theory to numerics
- Path constrained unbalanced optimal transport
- Unbalanced L^1 optimal transport for vector valued measures and application to full waveform inversion
- Domain decomposition for entropic unbalanced optimal transport
- Sharp convergence rates of empirical unbalanced optimal transport for spatio-temporal point processes
- Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space
- Gradient flows and Riemannian structure in the Gromov-Wasserstein geometry
- Flows on measure spaces and applications in machine learning. Abstracts from the workshop held March 22--27, 2026
- Wasserstein geometry of nonnegative measures on finite Markov chains. I: Gradient flow
- Vector-valued optimal transport: from dynamic to static formulations
This page was built for publication: An interpolating distance between optimal transport and Fisher-Rao metrics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1704812)
