Abstract
We discuss the statistical bundle of the manifold of two-variate stricly positive probability functions with given marginals. The fiber associated to each coupling turns out to be the vector space of interacions in the ANOVA decomposition with respect to the given weight. In this setting, we derive the form of the gradient flow equation for the Kantorovich optimal transport problem.
The author is supported by de Castro Statistics, Collegio Carlo Alberto. He is a member of INdAM-GNAMPA.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amari, S., Nagaoka, H.: Methods of Information Geometry. American Mathematical Society (2000). Translated from the 1993 Japanese original by Daishi Harada
Chirco, G., Malagò, L., Pistone, G.: Lagrangian and Hamiltonian dynamics for probabilities on the statistical bundle, arXiv:2009.09431 (2020)
Montrucchio, L., Pistone, G.: Kantorovich distance on a weighted graph (2019). arXiv:1905.07547 [math.PR]
Peyré, G., Cuturi, M.: Computational optimal transport. Found. Trends Mach. Learn. 11(5–6), 355–607 (2019). arXiv:1803.00567v2
Pistone, G.: Lagrangian function on the finite state space statistical bundle. Entropy 20(2), 139 (2018). https://doi.org/10.3390/e20020139. http://www.mdpi.com/1099-4300/20/2/139
Pistone, G.: Information geometry of the probability simplex. A short course. Nonlinear Phenomena Complex Syst. 23(2), 221–242 (2020)
Pistone, G., Rapallo, F., Rogantin, M.P.: Finite space Kantorovich problem with an MCMC of table moves. Electron. J. Stat. 15(1), 880–907 (2021). https://doi.org/10.1214/21-EJS1804
Pistone, G., Rogantin, M.P.: The gradient flow of the polarization measure. With an appendix (2015). arXiv:1502.06718
Santambrogio, F.: Optimal Transport for Applied Mathematicians: Calculus of Variations, PDEs, and Modeling. Birkhäuser (2015)
Acknowledgments
The author thanks three anonymous referees whose comments suggested a complete revision of the first version. The author thanks L. Malagò and L. Montrucchio for valuable suggestions. We first presented the gradient flow argument of Sect. 3 to the “Computational information geometry for image and signal processing” Conference, Sep 21–25 2015 ICMS, Edinburgh.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Pistone, G. (2021). Statistical Bundle of the Transport Model. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2021. Lecture Notes in Computer Science(), vol 12829. Springer, Cham. https://doi.org/10.1007/978-3-030-80209-7_81
Download citation
DOI: https://doi.org/10.1007/978-3-030-80209-7_81
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-80208-0
Online ISBN: 978-3-030-80209-7
eBook Packages: Computer ScienceComputer Science (R0)