On information geometry methods for data analysis

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989592%3A15310%2F24%3A73626814" target="_blank" >RIV/61989592:15310/24:73626814 - isvavai.cz</a>

Result on the web

<a href="https://www.researchgate.net/publication/385837561_On_Information_Geometry_Methods_for_Data_Analysis" target="_blank" >https://www.researchgate.net/publication/385837561_On_Information_Geometry_Methods_for_Data_Analysis</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.7546/giq-29-2024-11-22" target="_blank" >10.7546/giq-29-2024-11-22</a>

Result language

angličtina

Original language name

On information geometry methods for data analysis

Original language description

The paper is devoted to exploration of statistical manifolds. In particular we consider exponential family manifolds, its metrics and connections. We proved that a statistical manifold does not admit nontrivial geodesic mapping between the Riemannian connection and any alpha-connection. Besides, a statistical manifold does not admit a Weyl connection which coincides with any alpha-connection. We obtain also that the Fisher information matrix calculated for a mixture family is a Hessian metric.

Czech name

—

Czech description

—

Type

J_SC - Article in a specialist periodical, which is included in the SCOPUS database

CEP classification

—

OECD FORD branch

10101 - Pure mathematics

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Geometry, Integrability and Quantization

ISSN

1314-3247

e-ISSN

2367-7147

Volume of the periodical

29

Issue of the periodical within the volume

SEP

Country of publishing house

US - UNITED STATES

Number of pages

12

Pages from-to

11-22

UT code for WoS article

—

EID of the result in the Scopus database

2-s2.0-85210918515