Abstract
We first explain how the information geometry of Bregman manifolds brings a natural generalization of scalar quasi-arithmetic means that we term quasi-arithmetic centers. We study the invariance and equivariance properties of quasi-arithmetic centers from the viewpoint of the Fenchel-Young canonical divergences. Second, we consider statistical quasi-arithmetic mixtures and define generalizations of the Jensen-Shannon divergence according to geodesics induced by affine connections.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
The squared Euclidean/Mahalanobis divergence are not metric distances since they fail the triangle inequality.
References
Alić, M., Mond, B., Pečarić, J., Volenec, V.: The arithmetic-geometric-harmonic-mean and related matrix inequalities. Linear Algebra Appl. 264, 55–62 (1997)
Amari, S.i.: Differential-geometrical methods in statistics. Lecture Notes on Statistics 28, 1 (1985). https://doi.org/10.1007/978-1-4612-5056-2
Amari, S.i.: Integration of stochastic models by minimizing \(\alpha \)-divergence. Neural Comput. 19(10), 2780–2796 (2007)
Amari, S.: Information Geometry and Its Applications. AMS, vol. 194. Springer, Tokyo (2016). https://doi.org/10.1007/978-4-431-55978-8
Banerjee, A., Merugu, S., Dhillon, I.S., Ghosh, J., Lafferty, J.: Clustering with Bregman divergences. J. Mach. Learn. Res. 6(10) (2005)
Ben-Tal, A., Charnes, A., Teboulle, M.: Entropic means. J. Math. Anal. Appl. 139(2), 537–551 (1989)
Bhatia, R., Gaubert, S., Jain, T.: Matrix versions of the Hellinger distance. Lett. Math. Phys. 109(8), 1777–1804 (2019). https://doi.org/10.1007/s11005-019-01156-0
Boyd, S., Boyd, S.P., Vandenberghe, L.: Convex optimization. Cambridge University Press (2004)
Bregman, L.M.: The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming. USSR Comput. Math. Math. Phys. 7(3), 200–217 (1967)
Clarke, F.: On the inverse function theorem. Pac. J. Math. 64(1), 97–102 (1976)
Dontchev, A.L., Rockafellar, R.T.: Implicit Functions and Solution Mappings. SMM, Springer, New York (2009). https://doi.org/10.1007/978-0-387-87821-8
Hardy, G.H., Littlewood, J.E., Pólya, G., Pólya, G.: Inequalities. Cambridge University Press (1952)
Masrani, V., et al.: \(q\)-paths: Generalizing the geometric annealing path using power means. In: Uncertainty in Artificial Intelligence, pp. 1938–1947. PMLR (2021)
Nakajima, N., Ohmoto, T.: The dually flat structure for singular models. Inform. Geometry 4(1), 31–64 (2021). https://doi.org/10.1007/s41884-021-00044-8
Nakamura, Y.: Algorithms associated with arithmetic, geometric and harmonic means and integrable systems. J. Comput. Appl. Math. 131(1–2), 161–174 (2001)
Niculescu, C.P., Persson, L.-E.: Convex Functions and Their Applications. CBM, Springer, New York (2006). https://doi.org/10.1007/0-387-31077-0
Nielsen, F.: On the Jensen-Shannon symmetrization of distances relying on abstract means. Entropy 21(5), 485 (2019)
Nielsen, F.: Statistical divergences between densities of truncated exponential families with nested supports: duo bregman and duo jensen divergences. Entropy 24(3), 421 (2022)
Nielsen, F.: Beyond scalar quasi-arithmetic means: Quasi-arithmetic averages and quasi-arithmetic mixtures in information geometry (2023)
Nielsen, F., Nock, R., Amari, S.i.: On clustering histograms with \(k\)-means by using mixed \(\alpha \)-divergences. Entropy 16(6), 3273–3301 (2014)
Nock, R., Nielsen, F.: Fitting the smallest enclosing bregman ball. In: Gama, J., Camacho, R., Brazdil, P.B., Jorge, A.M., Torgo, L. (eds.) ECML 2005. LNCS (LNAI), vol. 3720, pp. 649–656. Springer, Heidelberg (2005). https://doi.org/10.1007/11564096_65
Ohara, A.: Geodesics for dual connections and means on symmetric cones. Integr. Eqn. Oper. Theory 50, 537–548 (2004)
Pálfia, M.: Classification of affine matrix means. arXiv preprint arXiv:1208.5603 (2012)
Rockafellar, R.T.: Conjugates and Legendre transforms of convex functions. Can. J. Math. 19, 200–205 (1967)
Rockafellar, R.T.: Convex analysis, vol. 11. Princeton University Press (1997)
Shima, H., Yagi, K.: Geometry of Hessian manifolds. Differential Geom. Appl. 7(3), 277–290 (1997)
Zhang, J.: Nonparametric information geometry: from divergence function to referential-representational biduality on statistical manifolds. Entropy 15(12), 5384–5418 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Nielsen, F. (2023). Quasi-arithmetic Centers, Quasi-arithmetic Mixtures, and the Jensen-Shannon \(\nabla \)-Divergences. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2023. Lecture Notes in Computer Science, vol 14071. Springer, Cham. https://doi.org/10.1007/978-3-031-38271-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-38271-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-38270-3
Online ISBN: 978-3-031-38271-0
eBook Packages: Computer ScienceComputer Science (R0)