An Interpolating Distance Between Optimal Transport and Fisher–Rao Metrics

  • Lénaïc Chizat
  • Gabriel Peyré
  • Bernhard Schmitzer
  • François-Xavier Vialard


This paper defines a new transport metric over the space of nonnegative 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 the new 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 Hellinger metrics are obtained as limiting cases of our metric. Our last theoretical contribution is a proof that geodesics between mixtures of sufficiently close Dirac measures are made of translating mixtures of Dirac masses. 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.


Unbalanced optimal transport Wasserstein \(L^2\) metric Fisher–Rao metric Positive Radon measures 

Mathematics Subject Classification




The work of Bernhard Schmitzer has been supported by the Fondation Sciences Mathématiques de Paris. The work of Gabriel Peyré has been supported by the European Research Council (ERC project SIGMA-Vision). We would like to thank Yann Brenier and Jean-David Benamou for stimulating discussions.


  1. 1.
    L. Ambrosio, N. Gigli, and G. Savaré. Gradient flows: in metric spaces and in the space of probability measures. Springer Science & Business Media, 2008.Google Scholar
  2. 2.
    N. Ay, J. Jost, H. V. Lê, and L. Schwachhöfer. Information geometry and sufficient statistics. Probability Theory and Related Fields, 162(1):327–364, 2015.MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    M. Bauer, M. Bruveris, and P. W. Michor. Uniqueness of the Fisher–Rao metric on the space of smooth densities. Bull. Lond. Math. Soc., 48(3):499–506, 2016.MathSciNetCrossRefMATHGoogle Scholar
  4. 4.
    M. F. Beg, M. I. Miller, A. Trouvé, and L. Younes. Computing large deformation metric mappings via geodesic flows of diffeomorphisms. International journal of computer vision, 61(2):139–157, 2005.CrossRefGoogle Scholar
  5. 5.
    J.-D. Benamou. Numerical resolution of an “unbalanced” mass transport problem. ESAIM: Mathematical Modelling and Numerical Analysis, 37(05):851–868, 2003.MathSciNetCrossRefMATHGoogle Scholar
  6. 6.
    J.-D. Benamou and Y. Brenier. A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem. Numerische Mathematik, 84(3):375–393, 2000.MathSciNetCrossRefMATHGoogle Scholar
  7. 7.
    J.-D. Benamou and Y. Brenier. Mixed L2-Wasserstein optimal mapping between prescribed density functions. Journal of Optimization Theory and Applications, 111(2):255–271, 2001.MathSciNetCrossRefMATHGoogle Scholar
  8. 8.
    G. Bouchitté and G. Buttazzo. New lower semicontinuity results for nonconvex functionals defined on measures. Nonlinear Analysis: Theory, Methods & Applications, 15(7):679–692, 1990.MathSciNetCrossRefMATHGoogle Scholar
  9. 9.
    L. Caffarelli and R. J. McCann. Free boundaries in optimal transport and Monge-Ampere obstacle problems. Annals of mathematics, 171(2):673–730, 2010.MathSciNetCrossRefMATHGoogle Scholar
  10. 10.
    P. Cardaliaguet, G. Carlier, and B. Nazaret. Geodesics for a class of distances in the space of probability measures. Calculus of Variations and Partial Differential Equations, 48(3-4):395–420, 2013.MathSciNetCrossRefMATHGoogle Scholar
  11. 11.
    P. Combettes and J.-C. Pesquet. Proximal splitting methods in signal processing. In Fixed-point algorithms for inverse problems in science and engineering, pages 185–212. Springer, 2011.Google Scholar
  12. 12.
    P. L. Combettes and J.-C. Pesquet. A Douglas–Rachford splitting approach to nonsmooth convex variational signal recovery. Selected Topics in Signal Processing, IEEE Journal of, 1(4):564–574, 2007.CrossRefGoogle Scholar
  13. 13.
    J. Dolbeault, B. Nazaret, and G. Savaré. A new class of transport distances between measures. Calculus of Variations and Partial Differential Equations, 34(2):193–231, 2009.MathSciNetCrossRefMATHGoogle Scholar
  14. 14.
    A. Figalli. The optimal partial transport problem. Archive for rational mechanics and analysis, 195(2):533–560, 2010.MathSciNetCrossRefMATHGoogle Scholar
  15. 15.
    A. Figalli and N. Gigli. A new transportation distance between non-negative measures, with applications to gradients flows with dirichlet boundary conditions. Journal de mathématiques pures et appliquées, 94(2):107–130, 2010.MathSciNetCrossRefMATHGoogle Scholar
  16. 16.
    K. Guittet. Extended Kantorovich norms: a tool for optimization. Technical report, Tech. Rep. 4402, INRIA, 2002.Google Scholar
  17. 17.
    S. Haker, L. Zhu, A. Tannenbaum, and S. Angenent. Optimal mass transport for registration and warping. International Journal of computer vision, 60(3):225–240, 2004.CrossRefGoogle Scholar
  18. 18.
    L. G. Hanin. Kantorovich-Rubinstein norm and its application in the theory of Lipschitz spaces. Proceedings of the American Mathematical Society, 115(2):345–352, 1992.MathSciNetCrossRefMATHGoogle Scholar
  19. 19.
    C. Jimenez. Dynamic formulation of optimal transport problems. Journal of Convex Analysis, 15(3):593, 2008.MathSciNetMATHGoogle Scholar
  20. 20.
    L. Kantorovich. On the transfer of masses (in russian). Doklady Akademii Nauk, 37(2):227–229, 1942.Google Scholar
  21. 21.
    S. Kondratyev, L. Monsaingeon, and D. Vorotnikov. A new optimal transport distance on the space of finite Radon measures. Technical report, Pre-print, 2015.MATHGoogle Scholar
  22. 22.
    D. Lombardi and E. Maitre. Eulerian models and algorithms for unbalanced optimal transport. ESAIM: M2AN, 49(6):1717 – 1744, 2015.MathSciNetCrossRefMATHGoogle Scholar
  23. 23.
    J. Maas, M. Rumpf, C. Schönlieb, and S. Simon. A generalized model for optimal transport of images including dissipation and density modulation. ESAIM: M2AN, 49(6):1745–1769, 2015.MathSciNetCrossRefMATHGoogle Scholar
  24. 24.
    N. Papadakis, G. Peyré, and E. Oudet. Optimal transport with proximal splitting. SIAM Journal on Imaging Sciences, 7(1):212–238, 2014.MathSciNetCrossRefMATHGoogle Scholar
  25. 25.
    B. Piccoli and F. Rossi. On properties of the Generalized Wasserstein distance. arXiv:1304.7014, 2013.
  26. 26.
    B. Piccoli and F. Rossi. Generalized Wasserstein distance and its application to transport equations with source. Archive for Rational Mechanics and Analysis, 211(1):335–358, 2014.MathSciNetCrossRefMATHGoogle Scholar
  27. 27.
    C. Rao. Information and accuracy attainable in the estimation of statistical parameters. Bulletin of the Calcutta Mathematical Society, 37(3):81–91, 1945.MathSciNetMATHGoogle Scholar
  28. 28.
    R. Rockafellar. Duality and stability in extremum problems involving convex functions. Pacific Journal of Mathematics, 21(1):167–187, 1967.MathSciNetCrossRefMATHGoogle Scholar
  29. 29.
    R. Rockafellar. Integrals which are convex functionals. ii. Pacific Journal of Mathematics, 39(2):439–469, 1971.MathSciNetCrossRefMATHGoogle Scholar
  30. 30.
    A. Trouvé and L. Younes. Metamorphoses through lie group action. Foundations of Computational Mathematics, 5(2):173–198, 2005.MathSciNetCrossRefMATHGoogle Scholar
  31. 31.
    C. Villani. Topics in optimal transportation. Number 58. American Mathematical Soc., 2003.Google Scholar

Copyright information

© SFoCM 2016

Authors and Affiliations

  • Lénaïc Chizat
    • 1
  • Gabriel Peyré
    • 1
  • Bernhard Schmitzer
    • 1
  • François-Xavier Vialard
    • 1
  1. 1.Project team Mokaplan, CEREMADE, CNRS, INRIAUniversité Paris-DauphineParisFrance

Personalised recommendations