Abstract
A Jensen-Bregman divergence is a distortion measure defined by a Jensen convexity gap induced by a strictly convex functional generator. Jensen-Bregman divergences unify the squared Euclidean and Mahalanobis distances with the celebrated information-theoretic Jensen-Shannon divergence, and can further be skewed to include Bregman divergences in limit cases. We study the geometric properties and combinatorial complexities of both the Voronoi diagrams and the centroidal Voronoi diagrams induced by such as class of divergences. We show that Jensen-Bregman divergences occur in two contexts: (1) when symmetrizing Bregman divergences, and (2) when computing the Bhattacharyya distances of statistical distributions. Since the Bhattacharyya distance of popular parametric exponential family distributions in statistics can be computed equivalently as Jensen-Bregman divergences, these skew Jensen-Bregman Voronoi diagrams allow one to define a novel family of statistical Voronoi diagrams.
This journal article revises and extends the conference paper [1] presented at the International Symposium on Voronoi Diagrams (ISVD) 2010. This paper includes novel extensions to matrix-based Jensen-Bregman divergences, and present the general framework of skew Jensen-Bregman Voronoi diagrams that include Bregman Voronoi diagrams as particular cases. Supporting materials available at http://www.informationgeometry.org/JensenBregman/
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Nielsen, F., Nock, R.: Jensen-Bregman Voronoi diagrams and centroidal tessellations. In: Proceedings of the 2010 International Symposium on Voronoi Diagrams in Science and Engineering (ISVD), pp. 56–65. IEEE Computer Society, Washington, DC (2010)
Okabe, A., Boots, B., Sugihara, K., Chiu, S.N.: Spatial tessellations: Concepts and applications of Voronoi diagrams. In: Probability and Statistics, 2nd edn., 671 pages. Wiley, NYC (2000)
de Berg, M., Cheong, O., van Kreveld, M., Overmars, M.: Computational Geometry: Algorithms and Applications, 3rd edn. Springer, Heidelberg (2008)
Lee, D.T.: Two-dimensional Voronoi diagrams in the L p -metric. Journal of the ACM 27, 604–618 (1980)
Chew, L.P., Dyrsdale III, R.L.S.: Voronoi diagrams based on convex distance functions. In: Proceedings of the First Annual Symposium on Computational Geometry, SCG 1985, pp. 235–244. ACM, New York (1985)
Boissonnat, J.D., Nielsen, F., Nock, R.: Bregman Voronoi diagrams. Discrete and Computational Geometry 44(2), 281–307 (2010)
Lin, J.: Divergence measures based on the Shannon entropy. IEEE Transactions on Information Theory 37, 145–151 (1991)
Cover, T.M., Thomas, J.A.: Elements of information theory. Wiley-Interscience, New York (1991)
Du, Q., Faber, V., Gunzburger, M.: Centroidal voronoi tessellations: Applications and algorithms. SIAM Rev. 41, 637–676 (1999)
Jeffreys, H.: An invariant form for the prior probability in estimation problems. Proceedings of the Royal Society of London 186, 453–461 (1946)
Reid, M.D., Williamson, R.C.: Generalised Pinsker inequalities. CoRR abs/0906.1244 (2009); published at COLT 2009
Chen, P., Chen, Y., Rao, M.: Metrics defined by Bregman divergences: Part I. Commun. Math. Sci. 6, 9915–9926 (2008)
Chen, P., Chen, Y., Rao, M.: Metrics defined by Bregman divergences: Part II. Commun. Math. Sci. 6, 927–948 (2008)
Burbea, J., Rao, C.R.: On the convexity of some divergence measures based on entropy functions. IEEE Transactions on Information Theory 28, 489–495 (1982)
Chazelle, B.: An optimal convex hull algorithm in any fixed dimension. Discrete & Computational Geometry 10, 377–409 (1993)
Aurenhammer, F.: Voronoi diagrams—a survey of a fundamental geometric data structure. ACM Comput. Surv. 23, 345–405 (1991)
Sharir, M., Agarwal, P.K.: Davenport-Schinzel Sequences and their Geometric Applications. Cambridge University Press, New York (2010)
Icking, C., Ha, L.: A tight bound for the complexity of Voronoi diagrams under polyhedral convex distance functions in 3d. In: STOC 2001: Proceedings of the Thirty-Third Annual ACM Symposium on Theory of Computing, pp. 316–321. ACM, New York (2001)
Ma, L.: Bisectors and Voronoi diagrams for convex distance functions, PhD thesis (2000)
Dickerson, M., Eppstein, D., Wortman, K.A.: Dilation, smoothed distance, and minimization diagrams of convex functions, arXiv 0812.0607
Balzer, M., Schlömer, T., Deussen, O.: Capacity-constrained point distributions: a variant of Lloyd’s method. ACM Trans. Graph. 28 (2009)
Yuille, A., Rangarajan, A.: The concave-convex procedure. Neural Computation 15, 915–936 (2003)
Arshia Cont, S.D., Assayag, G.: On the information geometry of audio streams with applications to similarity computing. IEEE Transactions on Audio, Speech and Language Processing 19 (2011) (to appear)
Cowin, S.C., Yang, G.: Averaging anisotropic elastic constant data. Journal of Elasticity 46, 151–180 (1997), doi:10.1023/A:1007335407097
Wang, Y.H., Han, C.Z.: Polsar image segmentation by mean shift clustering in the tensor space. Acta Automatica Sinica 36, 798–806 (2010)
Xie, Y., Vemuri, B.C., Ho, J.: Statistical Analysis of Tensor Fields. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6361, pp. 682–689. Springer, Heidelberg (2010)
Tsuda, K., Rätsch, G., Warmuth, M.K.: Matrix exponentiated gradient updates for on-line learning and bregman projection. Journal of Machine Learning Research 6, 995–1018 (2005)
Bhatia, R., Holbrook, J.: Riemannian geometry and matrix geometric means. Linear Algebra and its Applications 413, 594–618 (2006); Special Issue on the 11th Conference of the International Linear Algebra Society, Coimbra (2004)
Nielsen, F., Boltz, S.: The Burbea-Rao and Bhattacharyya centroids. IEEE Transactions on Information Theory (2010)
Nielsen, M.A., Chuang, I.L.: Quantum computation and quantum information. Cambridge University Press, New York (2000)
Burbea, J., Rao, C.R.: On the convexity of higher order Jensen differences based on entropy functions. IEEE Transactions on Information Theory 28, 961–963 (1982)
Csiszár, I.: Information theoretic methods in probability and statistics
Vos, P.: Geometry of f-divergence. Annals of the Institute of Statistical Mathematics 43, 515–537 (1991)
Hastie, T., Tibshirani, R., Friedman, R.: Elements of Statistical Learning Theory. Springer, Heidelberg (2002)
Nielsen, F., Garcia, V.: Statistical exponential families: A digest with flash cards (2009) arXiv.org:0911.4863
Bhattacharyya, A.: On a measure of divergence between two statistical populations defined by their probability distributions. Bulletin of Calcutta Mathematical Society 35, 99–110 (1943)
Matusita, K.: Decision rules based on the distance, for problems of fit, two samples, and estimation. Annal of Mathematics and Statistics 26, 631–640 (1955)
Huzurbazar, V.S.: Exact forms of some invariants for distributions admitting sufficient statistics. Biometrika 42, 533–573 (1955)
Kailath, T.: The divergence and Bhattacharyya distance measures in signal selection. IEEE Transactions on Communications [legacy, pre - 1988] 15, 52–60 (1967)
Jebara, T., Kondor, R.: Bhattacharyya and expected likelihood kernels. In: 16th Annual Conference on Learning Theory and 7th Kernel Workshop, COLT/Kernel, p. 57 (2003)
Sahoo, P.K., Wong, A.K.C.: Generalized Jensen difference based on entropy functions. Kybernetika, 241–250 (1988)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Nielsen, F., Nock, R. (2011). Skew Jensen-Bregman Voronoi Diagrams. In: Gavrilova, M.L., Tan, C.J.K., Mostafavi, M.A. (eds) Transactions on Computational Science XIV. Lecture Notes in Computer Science, vol 6970. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25249-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-25249-5_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25248-8
Online ISBN: 978-3-642-25249-5
eBook Packages: Computer ScienceComputer Science (R0)