On Voronoi Diagrams on the Information-Geometric Cauchy Manifolds

We study the Voronoi diagrams of a finite set of Cauchy distributions and their dual complexes from the viewpoint of information geometry by considering the Fisher-Rao distance, the Kullback-Leibler divergence, the chi square divergence, and a flat divergence derived from Tsallis entropy related to the conformal flattening of the Fisher-Rao geometry. We prove that the Voronoi diagrams of the Fisher-Rao distance, the chi square divergence, and the Kullback-Leibler divergences all coincide with a hyperbolic Voronoi diagram on the corresponding Cauchy location-scale parameters, and that the dual Cauchy hyperbolic Delaunay complexes are Fisher orthogonal to the Cauchy hyperbolic Voronoi diagrams. The dual Voronoi diagrams with respect to the dual flat divergences amount to dual Bregman Voronoi diagrams, and their dual complexes are regular triangulations. The primal Bregman Voronoi diagram is the Euclidean Voronoi diagram and the dual Bregman Voronoi diagram coincides with the Cauchy hyperbolic Voronoi diagram. In addition, we prove that the square root of the Kullback-Leibler divergence between Cauchy distributions yields a metric distance which is Hilbertian for the Cauchy scale families.

[1]  Hiroshi Matsuzoe,et al.  Notes on geometry of q-normal distributions , 2011 .

[2]  C. Tsallis.  Introduction to Nonextensive Statistical Mechanics: Approaching a Complex World , 2009 .

[3]  Tamal K. Dey,et al.  Delaunay Mesh Generation , 2012, Chapman and Hall / CRC computer and information science series.

[4]  C. R. Rao,et al.  Information and the Accuracy Attainable in the Estimation of Statistical Parameters , 1992 .

[5]  Peter N. Yianilos,et al.  Data structures and algorithms for nearest neighbor search in general metric spaces , 1993, SODA '93.

[6]  Patricia Giménez,et al.  Geodesic Hypothesis Testing for Comparing Location Parameters in Elliptical Populations , 2015, Sankhya A.

[7]  Frank Nielsen,et al.  Non-flat clustering with alpha-divergences , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[8]  Shun-ichi Amari,et al.  Geometry of deformed exponential families: Invariant, dually-flat and conformal geometries , 2012 .

[9]  Atsumi Ohara,et al.  Conformal Flattening on the Probability Simplex and Its Applications to Voronoi Partitions and Centroids , 2018, Geometric Structures of Information.

[10]  Douwe Kiela,et al.  Poincaré Embeddings for Learning Hierarchical Representations , 2017, NIPS.

[11]  Igor Vajda,et al.  On Metric Divergences of Probability Measures , 2009, Kybernetika.

[12]  M. H. Protter,et al.  THE SOLUTION OF THE PROBLEM OF INTEGRATION IN FINITE TERMS , 1970 .

[13]  C. Tsallis.  Possible generalization of Boltzmann-Gibbs statistics , 1988 .

[14]  M. Rao,et al.  Metrics defined by Bregman Divergences , 2008 .

[15]  Daniel Boley,et al.  Bregman Divergences and Triangle Inequality , 2013, SDM.

[16]  JASON DEBLOIS,et al.  The Delaunay tessellation in hyperbolic space , 2013, Mathematical Proceedings of the Cambridge Philosophical Society.

[17]  C. Atkinson.  Rao's distance measure , 1981 .

[18]  S. Amari,et al.  Information geometry of divergence functions , 2010 .

[19]  Dong-Ming Yan,et al.  Efficient computation of clipped Voronoi diagram for mesh generation , 2013, Comput. Aided Des..

[20]  David P. Dobkin,et al.  The quickhull algorithm for convex hulls , 1996, TOMS.

[21]  Frank Nielsen.  Grouping and Querying: A Paradigm to Get Output-Sensitive Algorithms , 1998, JCDCG.

[22]  Frank Nielsen,et al.  Total Jensen divergences: Definition, Properties and k-Means++ Clustering , 2013, ArXiv.

[23]  Jean-Daniel Boissonnat,et al.  Convex Hull and Voronoi Diagram of Additively Weighted Points , 2005, ESA.

[24]  M. C. Chaki.  ON STATISTICAL MANIFOLDS , 2000 .

[25]  S. Sra.  Positive definite matrices and the S-divergence , 2011, 1110.1773.

[26]  Wuchen Li,et al.  Wasserstein information matrix , 2019, ArXiv.

[27]  Frank Nielsen,et al.  On Conformal Divergences and Their Population Minimizers , 2013, IEEE Transactions on Information Theory.

[28]  J. Boissonnat,et al.  Curved Voronoi diagrams , 2006 .

[29]  Ann F. S. Mitchell.  Statistical Manifolds of univariate elliptic distributions , 1988 .

[30]  Richard Nock,et al.  On Bregman Voronoi diagrams , 2007, SODA '07.

[31]  Frank Nielsen,et al.  Total Jensen divergences: Definition, properties and clustering , 2013, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[32]  Julianna Pinele,et al.  The Fisher–Rao Distance between Multivariate Normal Distributions: Special Cases, Bounds and Applications , 2020, Entropy.

[33]  Calyampudi R. Rao,et al.  Chapter 4: Statistical Manifolds , 1987 .

[34]  Frank Nielsen,et al.  An Elementary Introduction to Information Geometry , 2018, Entropy.

[35]  T. Matumoto.  Any statistical manifold has a contrast function---on the $C\sp 3$-functions taking the minimum at the diagonal of the product manifold , 1993 .

[36]  Frank Nielsen,et al.  On the chi square and higher-order chi distances for approximating f-divergences , 2013, IEEE Signal Processing Letters.

[37]  Frank Nielsen,et al.  Combinatorial bounds on the α-divergence of univariate mixture models , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[38]  Flemming Topsøe,et al.  Jensen-Shannon divergence and Hilbert space embedding , 2004, International Symposium onInformation Theory, 2004. ISIT 2004. Proceedings..

[39]  M. Rao,et al.  Metrics defined by Bregman divergences: Part 2 , 2008 .

[40]  Olivier Devillers,et al.  Hyperbolic delaunay complexes and voronoi diagrams made practical , 2013, SoCG '13.

[41]  Jun Zhang,et al.  A note on curvature of α-connections of a statistical manifold , 2007 .

[42]  Frank Nielsen,et al.  Visualizing bregman voronoi diagrams , 2007, SCG '07.

[43]  Robert P. W. Duin,et al.  The Dissimilarity Representation for Pattern Recognition - Foundations and Applications , 2005, Series in Machine Perception and Artificial Intelligence.

[44]  Hiroshi Imai,et al.  Revisiting Hyperbolic Voronoi Diagrams in Two and Higher Dimensions from Theoretical, Applied and Generalized Viewpoints , 2011, Trans. Comput. Sci..

[45]  Rui F. Vigelis,et al.  On φ-Families of Probability Distributions , 2013 .

[46]  Frank Nielsen,et al.  An Information-Geometric Characterization of Chernoff Information , 2013, IEEE Signal Processing Letters.

[47]  Asuka Takatsu.  Wasserstein geometry of Gaussian measures , 2011 .

[48]  Frank Nielsen.  A note on Onicescu's informational energy and correlation coefficient in exponential families , 2020, ArXiv.

[49]  F. Opitz.  Information geometry and its applications , 2012, 2012 9th European Radar Conference.

[50]  M. Murray,et al.  Differential Geometry and Statistics , 1993 .

[51]  Hiroshi Matsuzoe,et al.  Hessian Structures and Divergence Functions on Deformed Exponential Families , 2014 .

[52]  Frank Nielsen,et al.  Visualizing hyperbolic Voronoi diagrams , 2014, SoCG.

[53]  Frank Nielsen,et al.  Hyperbolic Voronoi Diagrams Made Easy , 2009, 2010 International Conference on Computational Science and Its Applications.

[54]  J. Naudts.  The q-exponential family in statistical physics , 2008, 0809.4764.

[55]  Bang-Yen Chen,et al.  Differential Geometry of Warped Product Manifolds and Submanifolds , 2017 .

[56]  Fumiyasu Komaki,et al.  Bayesian prediction based on a class of shrinkage priors for location-scale models , 2007 .

[57]  H. Chernoff.  A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations , 1952 .

[58]  Mariette Yvinec,et al.  Algorithmic geometry , 1998 .

[59]  Franz Aurenhammer,et al.  Voronoi diagrams—a survey of a fundamental geometric data structure , 1991, CSUR.

[60]  Hirohiko Shima,et al.  Geometry of Hessian Structures , 2013, GSI.

[61]  Yannick Berthoumieu,et al.  Warped Riemannian Metrics for Location-Scale Models , 2018, Geometric Structures of Information.

[62]  L. Bregman.  The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming , 1967 .

[63]  C. Udriste,et al.  Geometric Modeling in Probability and Statistics , 2014 .

[64]  Hiroshi Matsuzoe,et al.  Hessian structures on deformed exponential families and their conformal structures , 2014 .

[65]  Frank Nielsen,et al.  Monte Carlo Information Geometry: The dually flat case , 2018, ArXiv.

[66]  Jun Zhang,et al.  Divergence Function, Duality, and Convex Analysis , 2004, Neural Computation.

[67]  Frank Nielsen,et al.  Bregman vantage point trees for efficient nearest Neighbor Queries , 2009, 2009 IEEE International Conference on Multimedia and Expo.

[68]  Jean-Pierre Crouzeix,et al.  A relationship between the second derivatives of a convex function and of its conjugate , 1977, Math. Program..

[69]  Frank Nielsen,et al.  On the Smallest Enclosing Information Disk , 2008, CCCG.

[70]  Franziska Hoffmann,et al.  Spatial Tessellations Concepts And Applications Of Voronoi Diagrams , 2016 .

[71]  Frank Nielsen,et al.  The Burbea-Rao and Bhattacharyya Centroids , 2010, IEEE Transactions on Information Theory.

[72]  Frank Nielsen,et al.  A closed-form formula for the Kullback-Leibler divergence between Cauchy distributions , 2019, ArXiv.

[73]  Rik Sarkar,et al.  Low Distortion Delaunay Embedding of Trees in Hyperbolic Plane , 2011, GD.

[74]  S. Eguchi.  Geometry of minimum contrast , 1992 .