On Voronoi diagrams and dual Delaunay complexes on the information-geometric Cauchy manifolds

• URL: http://arxiv.org/abs/2006.07020v2
• Date: Thu, 18 Jun 2020 10:34:42 GMT
• Title: On Voronoi diagrams and dual Delaunay complexes on the information-geometric Cauchy manifolds
• Authors: Frank Nielsen
• Abstract summary: We study the Voronoi diagrams of a finite set of Cauchy distributions and their dual complexes from the viewpoint of information 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.
• Score: 12.729120803225065
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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' quadratic entropy related to the conformal flattening of the Fisher-Rao curved 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 forward/reverse flat divergences amount to dual Bregman Voronoi diagrams, and their dual complexes are regular triangulations. The primal Bregman-Tsallis Voronoi diagram corresponds to the hyperbolic Voronoi diagram and the dual Bregman-Tsallis Voronoi diagram coincides with the ordinary Euclidean Voronoi diagram. Besides, 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.

Related papers

• Critical spin models from holographic disorder [49.1574468325115]
  We study the behavior of XXZ spin chains with a quasiperiodic disorder not present in continuum holography. Our results suggest the existence of a class of critical phases whose symmetries are derived from models of discrete holography.
  arXiv  Detail & Related papers  (2024-09-25T18:00:02Z)
• Haldane model on the Sierpiński gasket [0.0]
  We investigate the topological phases of the Haldane model on the Sierpi'nski gasket. As a consequence of the fractal geometry, multiple fractal gaps arise. A flat band appears, and due to a complex next-nearest neighbour hopping, this band splits and multiple topological flux-induced gaps emerge.
  arXiv  Detail & Related papers  (2024-07-29T15:02:22Z)
• von Mises Quasi-Processes for Bayesian Circular Regression [57.88921637944379]
  We explore a family of expressive and interpretable distributions over circle-valued random functions. The resulting probability model has connections with continuous spin models in statistical physics. For posterior inference, we introduce a new Stratonovich-like augmentation that lends itself to fast Markov Chain Monte Carlo sampling.
  arXiv  Detail & Related papers  (2024-06-19T01:57:21Z)
• A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning [68.76846801719095]
  We show that double descent appears exactly when and where it occurs, and that its location is not inherently tied to the threshold p=n. This provides a resolution to tensions between double descent and statistical intuition.
  arXiv  Detail & Related papers  (2023-10-29T12:05:39Z)
• The Fisher-Rao geometry of CES distributions [50.50897590847961]
  The Fisher-Rao information geometry allows for leveraging tools from differential geometry. We will present some practical uses of these geometric tools in the framework of elliptical distributions.
  arXiv  Detail & Related papers  (2023-10-02T09:23:32Z)
• Unsupervised Machine Learning Techniques for Exploring Tropical Coamoeba, Brane Tilings and Seiberg Duality [0.0]
  We introduce unsupervised machine learning techniques in order to identify toric phases of 4d N=1 supersymmetric gauge theories. These 4d N=1 supersymmetric gauge theories are world theories of a D3-brane probing a toric Calabi-Yau 3-fold.
  arXiv  Detail & Related papers  (2023-09-11T18:00:01Z)
• Holographic tensor networks from hyperbolic buildings [0.0]
  We introduce a unifying framework for the construction of holographic tensor networks. We give a precise construction of a large family of bulk regions that satisfy complementary recovery. Our construction recovers HaPPY--like codes in all dimensions, and generalizes the geometry of Bruhat--Tits trees.
  arXiv  Detail & Related papers  (2022-02-03T19:00:01Z)
• Phase diagram of Rydberg-dressed atoms on two-leg square ladders: Coupling supersymmetric conformal field theories on the lattice [52.77024349608834]
  We investigate the phase diagram of hard-core bosons in two-leg ladders in the presence of soft-shoulder potentials. We show how the competition between local and non-local terms gives rise to a phase diagram with liquid phases with dominant cluster, spin, and density-wave quasi-long-range ordering.
  arXiv  Detail & Related papers  (2021-12-20T09:46:08Z)
• Non-Parametric Manifold Learning [0.0]
  We introduce an estimator for distances in a compact Riemannian manifold based on graph Laplacian estimates of the Laplace-Beltrami operator. A consequence is a proof of consistency for (untruncated) manifold distances. The estimator resembles, and in fact its convergence properties are derived from, a special case of the Kontorovic dual reformulation of Wasserstein distance known as Connes' Distance Formula.
  arXiv  Detail & Related papers  (2021-07-16T19:32:34Z)
• Differentiating through the Fr\'echet Mean [51.32291896926807]
  Fr'echet mean is a generalization of the Euclidean mean. We show how to differentiate through the Fr'echet mean for arbitrary Riemannian manifold. This fully integrates the Fr'echet mean into the hyperbolic neural network pipeline.
  arXiv  Detail & Related papers  (2020-02-29T19:49:38Z)
• Cram\'er-Rao Lower Bounds Arising from Generalized Csisz\'ar Divergences [17.746238062801293]
  We study the geometry of probability distributions with respect to a generalized family of Csisz'ar $f$-divergences. We show that these formulations lead us to find unbiased and efficient estimators for the escort model.
  arXiv  Detail & Related papers  (2020-01-14T13:41:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.