Abstract
There are two geometrical structures in a manifold of probability distributions. One is invariant, based on the Fisher information, and the other is based on the Wasserstein distance of optimal transportation. We propose a unified framework which connects the Wasserstein distance and the Kullback-Leibler (KL) divergence to give a new information-geometrical theory. We consider the discrete case consisting of n elements and study the geometry of the probability simplex \(S_{n-1}\), the set of all probability distributions over n atoms. The Wasserstein distance is introduced in \(S_{n-1}\) by the optimal transportation of commodities from distribution \({\varvec{p}} \in S_{n-1}\) to \({\varvec{q}} \in S_{n-1}\). We relax the optimal transportation by using entropy, introduced by Cuturi (2013) and show that the entropy-relaxed transportation plan naturally defines the exponential family and the dually flat structure of information geometry. Although the optimal cost does not define a distance function, we introduce a novel divergence function in \(S_{n-1}\), which connects the relaxed Wasserstein distance to the KL-divergence by one parameter.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amari, S.: Information Geometry and Its Applications. Springer, Tokyo (2016)
Chentsov, N.N.: Statistical Decision Rules and Optimal Inference. Nauka (1972). Translated in English. AMS (1982)
Cuturi, M.: Sinkhorn distances: light speed computation of optimal transport. In: Advances in Neural Information Processing Systems, pp. 2292–2300 (2013)
Cuturi, M., Avis, D.: Ground metric learning. J. Mach. Learn. Res. 15, 533–564 (2014)
Cuturi, M., Peyré, G.: A smoothed dual formulation for variational Wasserstein problems. SIAM J. Imaging Sci. 9, 320–343 (2016)
Rao, C.R.: Information and accuracy attainable in the estimation of statistical parameters. Bull. Calcutta Math. Soc. 37, 81–91 (1945)
Villani, C.: Topics in Optimal Transportation. Graduate Studies in Math. AMS (2013)
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
Karakida, R., Amari, Si. (2017). Information Geometry of Wasserstein Divergence. 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_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-68445-1_14
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)