On the geometric structure ofsome statistical manifolds

02/16/2019
by   Mingao Yuan, et al.
0

In information geometry, one of the basic problem is to study the geomet-ric properties of statistical manifold. In this paper, we study the geometricstructure of the generalized normal distribution manifold and show that it has constant α-Gaussian curvature. Then for any positive integerp, we con-struct ap-dimensional statistical manifold that is α-flat.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/08/2021

Projections with logarithmic divergences

In information geometry, generalized exponential families and statistica...
research
07/05/2023

Linear Regression on Manifold Structured Data: the Impact of Extrinsic Geometry on Solutions

In this paper, we study linear regression applied to data structured on ...
research
06/26/2021

A Graph-based approach to derive the geodesic distance on Statistical manifolds: Application to Multimedia Information Retrieval

In this paper, we leverage the properties of non-Euclidean Geometry to d...
research
08/22/2018

Statistical Neurodynamics of Deep Networks: Geometry of Signal Spaces

Statistical neurodynamics studies macroscopic behaviors of randomly conn...
research
05/29/2023

Gravity as a Statistical Manifold/ On a bi-Connection Formulation of Gravitation

We formulate a bi-Connection Theory of Gravity whose Gravitational actio...
research
09/08/2023

Gabor frames and higher dimensional boundaries in signal analysis on manifolds

We provide a construction of Gabor frames that encode local linearizatio...
research
11/15/2021

A Statistical Approach to Surface Metrology for 3D-Printed Stainless Steel

Surface metrology is the area of engineering concerned with the study of...

Please sign up or login with your details

Forgot password? Click here to reset