Abstract
We consider the manifold of rank-p positive-semidefinite matrices of size n, seen as a quotient of the set of full-rank n-by-p matrices by the orthogonal group in dimension p. The resulting distance coincides with the Wasserstein distance between centered degenerate Gaussian distributions. We obtain expressions for the Riemannian curvature tensor and the sectional curvature of the manifold. We also provide tangent vectors spanning planes associated with the extreme values of the sectional curvature.
This work was supported by (i) the Fonds de la Recherche Scientifique – FNRS and the Fonds Wetenschappelijk Onderzoek – Vlaanderen under EOS Project no 30468160, (ii) “Communauté française de Belgique - Actions de Recherche Concertées” (contract ARC 14/19-060), (iii) the WBI-World Excellence Fellowship.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Absil, P.A., Gousenbourger, P.-Y., Striewski, P., Wirth, B.: Differentiable piecewise-Bézier surfaces on Riemannian manifolds. SIAM J. Imaging Sci. 9(4), 1788–1828 (2016). http://dx.doi.org/10.1137/16M1057978
Afsari, B., Tron, R., Vidal, R.: On the convergence of gradient descent for finding the Riemannian center of mass. SIAM J. Control Optim. 51(3), 2230–2260 (2013). https://doi.org/10.1137/12086282X
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
Bonnabel, S.: Stochastic gradient descent on Riemannian manifolds. IEEE Trans. Autom. Control 58(9), 2217–2229 (2013). https://doi.org/10.1109/TAC.2013.2254619
Bhatia, R., Rosenthal, P.: How and why to solve the operator equation AX- XB= Y. Bull. Lond. Math. Soc. 29(1), 1–21 (1997)
Bonnabel, S., Sepulchre, R.: Riemannian metric and geometric mean for positive semidefinite matrices of fixed rank. SIAM J. Matrix Anal. Appl. 31(3), 1055–1070 (2009). https://doi.org/10.1137/080731347
Dittmann, J.: On the Riemannian metric on the space of density matrices. Rep. Math. Phys. 36(2–3), 309–315 (1995). https://doi.org/10.1016/0034-4877(96)83627-5
Gelbrich, G.: On a formula for the \(L^2\) Wasserstein metric between measures on Euclidean and Hilbert spaces. Math. Nachr. 147(1), 185–203 (1990). https://doi.org/10.1002/mana.19901470121
Gousenbourger, P.-Y., et al.: Piecewise-Bézier \(C^1\) smoothing on manifolds with application to wind field estimation. In: Proceedings of the 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), pp. 305–310 (2017)
Journée, M., Bach, F., Absil, P.-A., Sepulchre, R.: Low-rank optimization on the cone of positive semidefinite matrices. SIAM J. Opti. 20(5), 2327–2351 (2010). https://doi.org/10.1137/080731359
Kacem, A., Daoudi, M., Amor, B.B, Berretti, S., Alvarez-Paiva, J.C.: A Novel geometric framework on gram matrix trajectories for human behavior understanding. IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI) (2018). https://doi.org/10.1109/tpami.2018.2872564
Li, X.-B., Burkowski, F.J.: Conformational transitions and principal geodesic analysis on the positive semidefinite matrix manifold. In: Basu, M., Pan, Y., Wang, J. (eds.) ISBRA 2014. LNCS, vol. 8492, pp. 334–345. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-08171-7_30
Massart, E., Absil, P.-A.: Quotient geometry of the manifold of fixed-rank positive-semidefinite matrices. Technical report UCL-INMA-2018.06, UCLouvain, November 2018, Preprint. http://sites.uclouvain.be/absil/2018.06
Meyer, G., Bonnabel, S., Sepulchre, R.: Regression on fixed-rank positive semidefinite matrices: a Riemannian approach. J. Mach. Learn. Res. 12, 593–625 (2011)
Massart, E., Gousenbourger, P.-Y., Son, N.T., Stykel, T., Absil, P.-A.: Interpolation on the manifold of fixed-rank positive-semidefinite matrices for parametric model order reduction: preliminary results. In: Proceedings of the 27th European Symposium on Artifical Neural Networks, Computational Intelligence and Machine Learning (ESANN2019), pp. 281–286 (2019)
Marchand, M., Huang, W., Browet, A., Van Dooren, P., Gallivan, K.A.: A Riemannian optimization approach for role model extraction. In: Proceedings of the 22nd International Symposium on Mathematical Theory of Networks and Systems, pp. 58–64 (2016)
Malagò, L., Montrucchio, L., Pistone, G.: Wasserstein Riemannian geometry of Gaussian densities. Inf. Geom. 1(2), 137–179 (2018). https://doi.org/10.1007/s41884-018-0014-4
Mishra, B., Meyer, G., Sepulchre, R.: Low-rank optimization for distance matrix completion. In: Proceedings of the 50th IEEE Conference on Decision and Control and European Control Conference (CDC-ECC), pp. 4455–4460 (2011). https://doi.org/10.1109/CDC.2011.6160810
O’Neill, B.: The fundamental equations of a submersion. Mich. Math. J. 13(4), 459–469 (1966). https://doi.org/10.1307/mmj/1028999604
O’Neill, B.: Semi-Riemannian geometry. In: Pure and Applied Mathematics, vol. 103. Academic Press Inc., Harcourt Brace Jovanovich Publishers, New York (1983)
Samir, C., Absil, P.-A., Srivastava, A., Klassen, E.: A gradient-descent method for curve fitting on Riemannian manifolds. Found. Comput. Math. 12(1), 49–73 (2012)
Smith, S.T.: Covariance, subspace, and intrinsic Cramér-Rao bounds. IEEE Trans. Signal Process 53(5), 1610–1630 (2005)
Takatsu, A.: Wasserstein geometry of Gaussian measures. Osaka J. Math. 48(4), 1005–1026 (2011)
Vandereycken, B., Absil, P.-A., Vandewalle, S.: Embedded geometry of the set of symmetric positive semidefinite matrices of fixed rank. In: IEEE/SP 15th Workshop on Statistical Signal Processing, pp. 389–392 (2009). https://doi.org/10.1109/SSP.2009.5278558
Vandereycken, B., Absil, P.-A., Vandewalle, S.: A Riemannian geometry with complete geodesics for the set of positive semidefinite matrices of fixed rank. IMA J. Numer. Anal. 33(2), 481–514 (2013). https://doi.org/10.1093/imanum/drs006
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Massart, E., Hendrickx, J.M., Absil, PA. (2019). Curvature of the Manifold of Fixed-Rank Positive-Semidefinite Matrices Endowed with the Bures–Wasserstein Metric. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2019. Lecture Notes in Computer Science(), vol 11712. Springer, Cham. https://doi.org/10.1007/978-3-030-26980-7_77
Download citation
DOI: https://doi.org/10.1007/978-3-030-26980-7_77
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-26979-1
Online ISBN: 978-3-030-26980-7
eBook Packages: Computer ScienceComputer Science (R0)