國立高雄大學圖資館 |

Language: English

Back

Information geometry

Ay, Nihat.

Information geometry

Record Type:	Electronic resources : Monograph/item
Title/Author:	Information geometryby Nihat Ay ... [et al.].
other author:	Ay, Nihat.
Published:	Cham :Springer International Publishing :2017.
Description:	xi, 407 p. :ill., digital ;24 cm.
Contained By:	Springer eBooks
Subject:	Geometrical models in statistics.
Online resource:	http://dx.doi.org/10.1007/978-3-319-56478-4
ISBN:	9783319564784$q(electronic bk.)

Information geometry
Information geometry[electronic resource] /by Nihat Ay ... [et al.]. - Cham :Springer International Publishing :2017. - xi, 407 p. :ill., digital ;24 cm. - Ergebnisse der Mathematik und ihrer Grenzgebiete. 3. Folge / A series of modern surveys in mathematics,v.640071-1136 ;. - Ergebnisse der Mathematik und ihrer Grenzgebiete. 3. Folge / A series of modern surveys in mathematics ;v.65..

1 Introduction -- 2 Finite information geometry -- 3 Parametrized measure models -- 4 The intrinsic geometry of statistical models -- 5 Information geometry and statistics -- 6 Application fields of information geometry -- 7 Appendix.

The book provides a comprehensive introduction and a novel mathematical foundation of the field of information geometry with complete proofs and detailed background material on measure theory, Riemannian geometry and Banach space theory. Parametrised measure models are defined as fundamental geometric objects, which can be both finite or infinite dimensional. Based on these models, canonical tensor fields are introduced and further studied, including the Fisher metric and the Amari-Chentsov tensor, and embeddings of statistical manifolds are investigated. This novel foundation then leads to application highlights, such as generalizations and extensions of the classical uniqueness result of Chentsov or the Cramer-Rao inequality. Additionally, several new application fields of information geometry are highlighted, for instance hierarchical and graphical models, complexity theory, population genetics, or Markov Chain Monte Carlo. The book will be of interest to mathematicians who are interested in geometry, information theory, or the foundations of statistics, to statisticians as well as to scientists interested in the mathematical foundations of complex systems.

ISBN: 9783319564784$q(electronic bk.)

Standard No.: 10.1007/978-3-319-56478-4doiSubjects--Topical Terms:

791341
Geometrical models in statistics.

LC Class. No.: QA276.23

Dewey Class. No.: 519.5

Information geometry
LDR:02458nmm a2200325 a 4500 001 521345
003 DE-He213
005 20180319150213.0
006 m d
007 cr nn 008maaau
008 180504s2017 gw s 0 eng d
020 $a 9783319564784$q(electronic bk.)
020 $a 9783319564777$q(paper)
024 7 $a 10.1007/978-3-319-56478-4 $2 doi
035 $a 978-3-319-56478-4
040 $a GP $c GP
041 0 $a eng
050 4 $a QA276.23
072 7 $a PBT $2 bicssc
072 7 $a MAT029000 $2 bisacsh
082 0 4 $a 519.5 $2 23
090 $a QA276.23 $b .I43 2017
245 0 0 $a Information geometry $h [electronic resource] / $c by Nihat Ay ... [et al.].
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2017.
300 $a xi, 407 p. : $b ill., digital ; $c 24 cm.
490 1 $a Ergebnisse der Mathematik und ihrer Grenzgebiete. 3. Folge / A series of modern surveys in mathematics, $x 0071-1136 ; $v v.64
505 0 $a 1 Introduction -- 2 Finite information geometry -- 3 Parametrized measure models -- 4 The intrinsic geometry of statistical models -- 5 Information geometry and statistics -- 6 Application fields of information geometry -- 7 Appendix.
520 $a The book provides a comprehensive introduction and a novel mathematical foundation of the field of information geometry with complete proofs and detailed background material on measure theory, Riemannian geometry and Banach space theory. Parametrised measure models are defined as fundamental geometric objects, which can be both finite or infinite dimensional. Based on these models, canonical tensor fields are introduced and further studied, including the Fisher metric and the Amari-Chentsov tensor, and embeddings of statistical manifolds are investigated. This novel foundation then leads to application highlights, such as generalizations and extensions of the classical uniqueness result of Chentsov or the Cramer-Rao inequality. Additionally, several new application fields of information geometry are highlighted, for instance hierarchical and graphical models, complexity theory, population genetics, or Markov Chain Monte Carlo. The book will be of interest to mathematicians who are interested in geometry, information theory, or the foundations of statistics, to statisticians as well as to scientists interested in the mathematical foundations of complex systems.
650 0 $a Geometrical models in statistics. $3 791341
650 1 4 $a Statistics. $3 182057
650 2 4 $a Statistical Theory and Methods. $3 274054
650 2 4 $a Data Structures. $3 273992
650 2 4 $a Differential Geometry. $3 273785
650 2 4 $a Convex and Discrete Geometry. $3 277230
650 2 4 $a Functional Analysis. $3 274845
650 2 4 $a Complex Systems. $3 558544
700 1 $a Ay, Nihat. $3 791340
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer eBooks
830 0 $a Ergebnisse der Mathematik und ihrer Grenzgebiete. 3. Folge / A series of modern surveys in mathematics ; $v v.65. $3 776013
856 4 0 $u http://dx.doi.org/10.1007/978-3-319-56478-4
950 $a Mathematics and Statistics (Springer-11649)