Skip to main content
SpringerLink
Log in

Wasserstein Riemannian geometry of Gaussian densities

  • Research Paper
  • Published:
Information Geometry Aims and scope Submit manuscript

Abstract

The Wasserstein distance on multivariate non-degenerate Gaussian densities is a Riemannian distance. After reviewing the properties of the distance and the metric geodesic, we present an explicit form of the Riemannian metrics on positive-definite matrices and compute its tensor form with respect to the trace inner product. The tensor is a matrix which is the solution to a Lyapunov equation. We compute the explicit formula for the Riemannian exponential, the normal coordinates charts and the Riemannian gradient. Finally, the Levi-Civita covariant derivative is computed in matrix form together with the differential equation for the parallel transport. While all computations are given in matrix form, nonetheless we discuss also the use of a special moving frame.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Absil, P.A., Mahony, R., Sepulchre, R.: Optimization Algorithms on Matrix Manifolds. Princeton University Press, Princeton (2008). (with a foreword by Paul Van Dooren)

    Book  Google Scholar 

  2. Aliprantis, C.D., Border, K.C.: Infinite Dimensional Analysis. A Hitchhiker’s Guide, 3rd edn. Springer, Berlin (2006)

    MATH  Google Scholar 

  3. Amari, S., Nagaoka, H.: Methods of information geometry. American Mathematical Society, Providence (2000). (translated from the 1993 Japanese original by Daishi Harada)

    MATH  Google Scholar 

  4. Amari, S.I.: Natural gradient works efficiently in learning. Neural Comput. 10(2), 251–276 (1998). https://doi.org/10.1162/089976698300017746

    Article  Google Scholar 

  5. Amari, S.I.: Information geometry and its applications. Appl. Math. Sci. 194 (2016). https://doi.org/10.1007/978-4-431-55978-8

    Book  Google Scholar 

  6. Anderson, T.W.: An Introduction to Multivariate Statistical Analysis. Wiley Series in Probability and Statistics, 3rd edn. Wiley, Hoboken (2003)

    MATH  Google Scholar 

  7. Bhatia, R.: Positive Definite Matrices. Princeton Series in Applied Mathematics. Princeton University Press, Princeton (2007). ([2015] paperback edition of the 2007 original [MR2284176])

    MATH  Google Scholar 

  8. Bhatia, R., Jain, T., Lim, Y.: On the Bures-Wasserstein distance between positive definite matrices. Expositiones Mathematicae (2018). https://doi.org/10.1016/j.exmath.2018.01.002 arXiv:1712.01504 (in press)

  9. Brenier, Y.: Polar factorization and monotone rearrangement of vector-valued functions. Comm. Pure Appl. Math. 44(4), 375–417 (1991). https://doi.org/10.1002/cpa.3160440402

    Article  MathSciNet  MATH  Google Scholar 

  10. do Carmo, M.P.: Riemannian geometry. Mathematics: Theory and Applications. Birkhuser Boston Inc., Cambridge (1992). (translated from the second Portuguese edition by Francis Flaherty)

    Book  Google Scholar 

  11. Chevallier, E., Kalunga, E., Angulo, J.: Kernel density estimation on spaces of Gaussian distributions and symmetric positive definite matrices. SIAM J. Imaging Sci. 10(1), 191–215 (2017). https://doi.org/10.1137/15M1053566

    Article  MathSciNet  MATH  Google Scholar 

  12. Dowson, D.C., Landau, B.V.: The Fréchet distance between multivariate normal distributions. J. Multivar. Anal. 12(3), 450–455 (1982). https://doi.org/10.1016/0047-259X(82)90077-X

    Article  MATH  Google Scholar 

  13. Gelbrich, M.: On a formula for the \(L^2\) Wasserstein metric between measures on Euclidean and Hilbert spaces. Math. Nachr. 147, 185–203 (1990). https://doi.org/10.1002/mana.19901470121

    Article  MathSciNet  MATH  Google Scholar 

  14. Givens, C.R., Shortt, R.M.: A class of Wasserstein metrics for probability distributions. Michigan Math. J. 31(2), 231–240 (1984). https://doi.org/10.1307/mmj/1029003026

    Article  MathSciNet  MATH  Google Scholar 

  15. Halmos, P.R.: Finite-dimensional vector spaces. The University Series in Undergraduate Mathematics, 2nd edn. D. Van Nostrand Co., Inc., Princeton-Toronto-New York-London (1958)

    MATH  Google Scholar 

  16. Hyvrinen, A.: Estimation of non-normalized statistical models by score matching. J. Mach. Learn. Res. 6, 695–709 (2005)

    MathSciNet  Google Scholar 

  17. Klingenberg, W.P.A.: Riemannian Geometry, De Gruyter Studies in Mathematics, vol. 1, 2nd edn. Walter de Gruyter & Co., Berlin (1995). https://doi.org/10.1515/9783110905120

  18. Knott, M., Smith, C.S.: On the optimal mapping of distributions. J. Optim. Theory Appl. 43(1), 39–49 (1984). https://doi.org/10.1007/BF00934745

    Article  MathSciNet  MATH  Google Scholar 

  19. Lafferty, J.D.: The density manifold and configuration space quantization. Trans. Am. Math. Soc. 305(2), 699–741 (1988). https://doi.org/10.2307/2000885

    Article  MathSciNet  MATH  Google Scholar 

  20. Lang, S.: Differential and Riemannian manifolds, Graduate Texts in Mathematics, vol. 160, 3rd edn. Springer, Berlin Heidelberg (1995)

    Book  Google Scholar 

  21. Lott, J.: Some geometric calculations on Wasserstein space. Comm. Math. Phys. 277(2), 423–437 (2008). https://doi.org/10.1007/s00220-007-0367-3

    Article  MathSciNet  MATH  Google Scholar 

  22. Magnus, J.R., Neudecker, H.: Matrix Differential Calculus with Applications in Statistics and Econometrics. Wiley Series in Probability and Statistics. Wiley, Chichester (1999). (Revised reprint of the 1988 original)

    MATH  Google Scholar 

  23. Malagò, L., Pistone, G.: Combinatorial optimization with information geometry: Newton method. Entropy 16, 4260–4289 (2014)

    Article  MathSciNet  Google Scholar 

  24. Malagò, L., Pistone, G.: Information geometry of the Gaussiandistributionin view of stochastic optimization. In: Proceedings of FOGA’15, held on January 17-20, 2015, Aberystwyth,Wales, 2015 (2015)

  25. Mangasarian, O.L., Fromovitz, S.: The Fritz John necessary optimality conditions in the presence of equality and inequality constraints. J. Math. Anal. Appl. 17, 37–47 (1967). https://doi.org/10.1016/0022-247X(67)90163-1

    Article  MathSciNet  MATH  Google Scholar 

  26. McCann, R.J.: A convexity principle for interacting gases. Adv. Math. 128(1), 153–179 (1997). https://doi.org/10.1006/aima.1997.1634

    Article  MathSciNet  MATH  Google Scholar 

  27. McCann, R.J.: Polar factorization of maps on Riemannian manifolds. Geom. Funct. Anal. 11(3), 589–608 (2001). https://doi.org/10.1007/PL00001679

    Article  MathSciNet  MATH  Google Scholar 

  28. Olkin, I., Pukelsheim, F.: The distance between two random vectors with given dispersion matrices. Linear Algebra Appl. 48, 257–263 (1982). https://doi.org/10.1016/0024-3795(82)90112-4

    Article  MathSciNet  MATH  Google Scholar 

  29. Otto, F.: The geometry of dissipative evolution equations: the porous medium equation. Comm. Partial Differential Equations 26(1-2), 101–174 (2001)

    Article  MathSciNet  Google Scholar 

  30. Papadopoulos, A.: Metric spaces, convexity and non-positive curvature, IRMA Lectures in Mathematics and Theoretical Physics, vol. 6, 2nd edn. European Mathematical Society (EMS), Zürich (2014). https://doi.org/10.4171/132

  31. Parry, M., Dawid, A.P., Lauritzen, S.: Proper local scoring rules. Ann. Stat. 40(1), 561–592 (2012). https://doi.org/10.1214/12-AOS971

    Article  MathSciNet  MATH  Google Scholar 

  32. Pistone, G.: Nonparametric information geometry. In: F. Nielsen, F. Barbaresco (eds.) Geometric Science of Information, Lecture Notes in Comput. Sci., vol. 8085, pp. 5–36. Springer, Heidelberg (2013). First International Conference, GSI 2013 Paris, France, August 28-30 (2013) (proceedings)

  33. Pistone, G., Sempi, C.: An infinite-dimensional geometric structure on the space of all the probability measures equivalent to a given one. Ann. Stat. 23(5), 1543–1561 (1995)

    Article  MathSciNet  Google Scholar 

  34. Simoncini, V.: Computational methods for linear matrix equations. SIAM Rev. 58(3), 377–441 (2016). https://doi.org/10.1137/130912839

    Article  MathSciNet  MATH  Google Scholar 

  35. Skovgaard, L.T.: A Riemannian geometry of the multivariate normal model. Scand. J. Stat. 11(4), 211–223 (1984)

    MathSciNet  MATH  Google Scholar 

  36. Takatsu, A.: Wasserstein geometry of Gaussian measures. Osaka J. Math. 48(4), 1005–1026 (2011)

    MathSciNet  MATH  Google Scholar 

  37. Villani, C.: Optimal Transport: Old and New. Grundlehren der mathematischen Wissenschaften. Springer, Berlin Heidelberg (2008)

    Google Scholar 

  38. Wachspress, E.L.: Trail to a Lyapunov equation solver. Comput. Math. Appl. 55(8), 1653–1659 (2008). https://doi.org/10.1016/j.camwa.2007.04.048

    Article  MathSciNet  MATH  Google Scholar 

Download references

Acknowledgements

The authors wish to thank two anonymous referees for helpful comments. G. Pistone acknowledges the support of de Castro Statistics and Collegio Carlo Alberto. He is a member of GNAMPA-INdAM.

Author information

Authors and Affiliations

  1. Romanian Institute of Science and Technology, RIST, Str. Virgil Fulicea nr. 17, 400022, Cluj-Napoca, Romania

    Luigi Malagò

  2. Collegio Carlo Alberto, Piazza Vincenzo Arbarello 8, 10122, Turin, Italy

    Luigi Montrucchio

  3. de Castro Statistics, Collegio Carlo Alberto, Piazza Vincenzo Arbarello 8, 10122, Turin, Italy

    Giovanni Pistone

Authors
  1. Luigi Malagò
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Luigi Montrucchio
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Giovanni Pistone
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Giovanni Pistone.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Malagò, L., Montrucchio, L. & Pistone, G. Wasserstein Riemannian geometry of Gaussian densities. Info. Geo. 1, 137–179 (2018). https://doi.org/10.1007/s41884-018-0014-4

Download citation

  • Received:

  • Revised:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s41884-018-0014-4

Keywords

Mathematics Subject Classification

Search

Navigation