English
Related papers

Related papers: Towards a Canonical Divergence within Information …

200 papers

Deep generative models learn a mapping from a low dimensional latent space to a high-dimensional data space. Under certain regularity conditions, these models parameterize nonlinear manifolds in the data space. In this paper, we investigate…

Machine Learning · Computer Science 2017-11-23 Hang Shao , Abhishek Kumar , P. Thomas Fletcher

This thesis is concerned with extending the idea of geodesic completeness from pseudo-Riemannian to complex geometry: we take, however a completely holomorphicpoint of view; that is to say, a 'metric' will be a (meromorphic) symmetric…

Complex Variables · Mathematics 2009-02-26 Claudio Meneghini

Calculus and geometry are ubiquitous in the theoretical modelling of scientific phenomena, but have historically been very challenging to apply directly to real data as statistics. Diffusion geometry is a new theory that reformulates…

Differential Geometry · Mathematics 2026-02-09 Iolo Jones , David Lanners

Geodesics become an essential element of the geometry of a semi-Riemannian manifold. In fact, their differences and similarities with the (positive definite) Riemannian case, constitute the first step to understand semi-Riemannian Geometry.…

Differential Geometry · Mathematics 2010-03-23 Anna Maria Candela , Miguel Sánchez

We introduce a framework for Riemannian diffeology. To this end, we use the tangent functor in the sense of Blohmann and one of the options of a metric on a diffeological space in the sense of Iglesias-Zemmour. As a consequence, the…

Differential Geometry · Mathematics 2026-02-05 Katsuhiko Kuribayashi , Keiichi Sakai , Yusuke Shiobara

We consider a pair of smooth manifolds, which are the counterparts in the even-dimensional and odd-dimensional cases. They are separately an almost complex manifold with Norden metric and an almost contact manifolds with B-metric,…

Differential Geometry · Mathematics 2015-05-06 Mancho Manev

We study the base distribution in chart-based generative models on Riemannian manifolds. Standard methods sample in Euclidean tangent space and then map the sample to the manifold with a chart. This is convenient, but it changes the meaning…

Machine Learning · Computer Science 2026-05-14 Marios Papamichalis , Regina Ruane

Symmetric positive-definite (SPD) matrix datasets play a central role across numerous scientific disciplines, including signal processing, statistics, finance, computer vision, information theory, and machine learning among others. The set…

Machine Learning · Statistics 2026-03-04 Jacek Karwowski , Frank Nielsen

We examine the role of information geometry in the context of classical Cram\'er-Rao (CR) type inequalities. In particular, we focus on Eguchi's theory of obtaining dualistic geometric structures from a divergence function and then applying…

Information Theory · Computer Science 2021-08-24 Kumar Vijay Mishra , M. Ashok Kumar

We introduce a new information-geometric structure associated with the dynamics on discrete objects such as graphs and hypergraphs. The presented setup consists of two dually flat structures built on the vertex and edge spaces,…

Information Theory · Computer Science 2023-08-08 Tetsuya J. Kobayashi , Dimitri Loutchko , Atsushi Kamimura , Shuhei A. Horiguchi , Yuki Sughiyama

In this paper we prove two results. The first shows that the Dirichlet-Neumann map of the operator $\Delta_g+q$ on a Riemannian surface can determine its topological, differential, and metric structure. Earlier work of this type assumes a…

Analysis of PDEs · Mathematics 2024-06-26 Cătălin I. Cârstea , Tony Liimatainen , Leo Tzou

The canonical equations of the optical cloaking proposed by Shurig, Pendry and Smith has been proved to be equivalent to the geodesic in a 3-dimensional curved space. Carrying out the argument we extend to the 4-dimensional Riemannian space…

Optics · Physics 2015-05-13 Kai Niu , Ci Song , Mo-Lin Ge

In the paper we consider Riemannian surfaces admitting a global expression of the Gauss curvature as the divergence of a vector field. It is equivalent to the existence of a metric linear connection of zero curvature. Such a linear…

Differential Geometry · Mathematics 2020-03-12 Cs. Vincze , M. Oláh , L. M. Alabdulsada

This paper introduces a new metric and mean on the set of positive semidefinite matrices of fixed-rank. The proposed metric is derived from a well-chosen Riemannian quotient geometry that generalizes the reductive geometry of the positive…

Optimization and Control · Mathematics 2009-10-21 Silvere Bonnabel , Rodolphe Sepulchre

The main goal of the paper is to prove the sandwich theorem for geodesic convex functions in a complete Riemannian manifold. Then by using this theorem we have proved an inequality in a manifold with bounded sectional curvature. Finally, we…

Differential Geometry · Mathematics 2018-06-25 Absos Ali Shaikh , Ravi P. Agarwal , Chandan Kumar Mondal

A recent canonical divergence, which is introduced on a smooth manifold $\mathrm{M}$ endowed with a general dualistic structure $(\mathrm{g},\nabla,\nabla^*)$, is considered for flat $\alpha$-connections. In the classical setting, we…

Mathematical Physics · Physics 2019-10-02 Domenico Felice , Nihat Ay

We present an intrinsic reconstruction of Riemannian geometry from a symmetric, strongly local diffusion semigroup. Starting from a diffusion operator and its associated first- and second-order diffusion calculus, we recover the full…

Differential Geometry · Mathematics 2026-01-27 Amandip Sangha

Electromagnetism in an inhomogeneous dielectric medium at rest is described using the methods of differential geometry. In contrast to a general relativistic approach the electromagnetic fields are discussed in three-dimensional space only.…

General Relativity and Quantum Cosmology · Physics 2009-11-07 Paul Piwnicki

In the field of statistics, many kind of divergence functions have been studied as an amount which measures the discrepancy between two probability distributions. In the differential geometrical approach in statistics (information…

Methodology · Statistics 2018-09-11 Tomohiro Nishiyama

The Riemannian manifold of curves with a Sobolev metric is an important and frequently studied model in the theory of shape spaces. Various numerical approaches have been proposed to compute geodesics, but so far elude a rigorous…

Numerical Analysis · Mathematics 2025-05-16 Sascha Beutler , Florine Hartwig , Martin Rumpf , Benedikt Wirth