Computations of optimal transport distance with Fisher information regularization

DOI10.1007/s10915-017-0599-0zbMath1415.49030arXiv1704.04605OpenAlexW2613550700MaRDI QIDQ1651332

Penghang Yin, Wuchen Li, Stanley J. Osher

Publication date: 12 July 2018

Published in: Journal of Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1704.04605

zbMATH Keywords

Newton's methodFisher informationoptimal transportSchrödinger bridge problem

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Variational problems in a geometric measure-theoretic setting (49Q20) Measures of information, entropy (94A17)

Related Items (28)

A Continuation Multiple Shooting Method for Wasserstein Geodesic Equation ⋮ Generalized unnormalized optimal transport and its fast algorithms ⋮ Supervised Optimal Transport ⋮ An efficient algorithm for matrix-valued and vector-valued optimal mass transport ⋮ Quadratically Regularized Optimal Transport on Graphs ⋮ A structure-preserving finite element discretization for the time-dependent Nernst-Planck equation ⋮ Primal dual methods for Wasserstein gradient flows ⋮ A mixed finite element discretization of dynamical optimal transport ⋮ A mean field game inverse problem ⋮ Time discretizations of Wasserstein–Hamiltonian flows ⋮ Quantum statistical learning via quantum Wasserstein natural gradient ⋮ Dynamical Schrödinger bridge problems on graphs ⋮ Extremal flows in Wasserstein space ⋮ The Most Likely Evolution of Diffusing and Vanishing Particles: Schrödinger Bridges with Unbalanced Marginals ⋮ DeepParticle: learning invariant measure by a deep neural network minimizing Wasserstein distance on data generated from an interacting particle method ⋮ A second order equation for Schrödinger bridges with applications to the hot gas experiment and entropic transportation cost ⋮ Techniques for continuous optimal transport problem ⋮ Scaling Limits of Discrete Optimal Transport ⋮ An optimal transport approach for the Schrödinger bridge problem and convergence of Sinkhorn algorithm ⋮ Natural gradient via optimal transport ⋮ Hopf-Cole transformation via generalized Schrödinger bridge problem ⋮ Lagrangian schemes for Wasserstein gradient flows ⋮ Topological data assimilation using Wasserstein distance ⋮ Computation of optimal transport with finite volumes ⋮ Fast Entropic Regularized Optimal Transport Using Semidiscrete Cost Approximation ⋮ Algorithm for Hamilton-Jacobi equations in density space via a generalized Hopf formula ⋮ Stochastic Control Liaisons: Richard Sinkhorn Meets Gaspard Monge on a Schrödinger Bridge ⋮ Fisher information regularization schemes for Wasserstein gradient flows

Uses Software

• EMD

Cites Work

• Unnamed Item
• Nonlinear total variation based noise removal algorithms
• On the relation between optimal transport and Schrödinger bridges: a stochastic control viewpoint
• Gradient flows of the entropy for finite Markov chains
• An interpolating distance between optimal transport and Fisher-Rao metrics
• The earth mover's distance as a metric for image retrieval
• A first-order primal-dual algorithm for convex problems with applications to imaging
• A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
• Fokker-Planck equations for a free energy functional or Markov process on a graph
• Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
• An optimal transport approach for seismic tomography: application to 3D full waveform inversion
• Optimal Transport with Proximal Splitting
• Entropic and Displacement Interpolation: A Computational Approach Using the Hilbert Metric
• A Multilevel Method for the Solution of Time Dependent Optimal Transport
• Differential equations methods for the Monge-Kantorovich mass transfer problem
• Science from Fisher Information
• Optimal Transport
• Stochastic calculus of variations

This page was built for publication: Computations of optimal transport distance with Fisher information regularization