Abstract
This paper is an overview of results that have been obtain in [2] on the convex regularization of Wasserstein barycenters for random measures supported on \({\mathbb R}^{d}\). We discuss the existence and uniqueness of such barycenters for a large class of regularizing functions. A stability result of regularized barycenters in terms of Bregman distance associated to the convex regularization term is also given. Additionally we discuss the convergence of the regularized empirical barycenter of a set of n iid random probability measures towards its population counterpart in the real line case, and we discuss its rate of convergence. This approach is shown to be appropriate for the statistical analysis of discrete or absolutely continuous random measures. In this setting, we propose an efficient minimization algorithm based on accelerated gradient descent for the computation of regularized Wasserstein barycenters.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Agueh, M., Carlier, G.: Barycenters in the Wasserstein space. SIAM J. Math. Anal. 43(2), 904–924 (2011)
Bigot, J., Cazelles, E., Papadakis, N.: Penalized barycenters in the Wasserstein space. Submitted. https://128.84.21.199/abs/1606.01025
Bobkov, S., Ledoux, M.: One-dimensional empirical measures, order statistics and Kantorovich transport distances (2014). Book in preparation. http://perso.math.univ-toulouse.fr/ledoux/files/2013/11/Order.statistics.10.pdf
Burger, M., Osher, S.: Convergence rates of convex variational regularization. Inverse Prob. 20(5), 1411 (2004)
Cuturi, M., Peyré, G.: A smoothed dual approach for variational Wasserstein problems. SIAM J. Imaging Sci. 9(1), 320–343 (2016)
Fréchet, M.: Les éléments aléatoires de nature quelconque dans un espace distancié. Ann. Inst. H. Poincaré Sect. B Prob. Stat. 10, 235–310 (1948)
Kneip, A., Utikal, K.J.: Inference for density families using functional principal component analysis. J. Am. Stat. Assoc. 96(454), 519–542 (2001). With comments and a rejoinder by the authors
Panaretos, V.M., Zemel, Y.: Amplitude and phase variation of point processes. Ann. Stat. 44(2), 771–812 (2016)
Petersen, A., Müller, H.G.: Functional data analysis for density functions by transformation to a Hilbert space. Ann. Stat. 44(1), 183–218 (2016)
Wu, W., Srivastava, A.: An information-geometric framework for statistical inferences in the neural spike train space. J. Comput. Neurosci. 31(3), 725–748 (2011)
Zhang, Z., Müller, H.-G.: Functional density synchronization. Comput. Stat. Data Anal. 55(7), 2234–2249 (2011)
Acknowledgment
This work has been carried out with financial support from the French State, managed by the French National Research Agency (ANR) in the frame of the GOTMI project (ANR-16-CE33-0010-01).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Cazelles, E., Bigot, J., Papadakis, N. (2017). Regularized Barycenters in the Wasserstein Space. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2017. Lecture Notes in Computer Science(), vol 10589. Springer, Cham. https://doi.org/10.1007/978-3-319-68445-1_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-68445-1_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68444-4
Online ISBN: 978-3-319-68445-1
eBook Packages: Computer ScienceComputer Science (R0)