Methods of information geometry

著者

• 甘利, 俊一 アマリ, シュンイチ
• 長岡, 浩司 ナガオカ, ヒロシ

書誌事項

Methods of information geometry

Shun-ichi Amari, Hiroshi Nagaoka ; [translated from the Japanese by Daishi Harada]

（Translations of mathematical monographs, v. 191）

American Mathematical Society , Oxford University Press, c2000

• : pbk

タイトル別名

情報幾何の方法 : JOHO KIKA NO HOHO

情報幾何の方法

注記

Includes bibliographical reference(p. 187-202) and index

内容説明・目次

巻冊次

ISBN 9780821805312

内容説明

There has been strong progress in the field of information geometry in recent years and yet there are few textbooks which reflect these developments, except for those which deal with statistics. Information geometry provides a new method applicable to various areas including information sciences and physical sciences. It has emerged from investigating the geometrical structures of the manifold of probability distributions, and has been applied successfully to statistical inference problems. However, it has been proved that information geometry opens a new paradigm useful for elucidation of information systems, intelligent systems, physical systems and mathematical systems. Information geometry has become one of the fundamental methods of analyzing neurocomputing and related areas. Its usefulness has also been recognized in multiterminal information theory and portfolio, in nonlinear systems and nonlinear prediction, in mathematical programming, in statistical inference and information theory of quantum mechanical systems, and so on. Its mathematical foundations have also shown a remarkable progress. The first three chapters of the book provide a comprehensive introduction to the mathematical foundation of information geometry while the remaining chapters provide an overview of the scope of its application. It is hoped that Methods of Information Geometry will become a key text in information geometry and help to inspire further developments in the field.

目次

• PREFACE TO THE ENGLISH EDITION
• ELEMENTARY DIFFERENTIAL GEOMETRY
• THE GEOMETRIC STRUCTURE OF STATISTICAL MODELS
• DUAL CONNECTIONS
• STATISTICAL INFERENCE AND DIFFERENTIAL GEOMETRY
• THE GEOMETRY OF TIME SERIES AND LINEAR SYSTEMS
• MULTITERMINAL INFORMATION THEORY AND STATISTICAL INFERENCE
• INFORMATION GEOMETRY FOR QUANTUM SYSTEMS
• MISCELLANEOUS TOPICS
• GUIDE TO THE BIBLIOGRAPHY
• BIBILOGRAPHY
• INDEX

巻冊次

: pbk ISBN 9780821843024

内容説明

Information geometry provides the mathematical sciences with a new framework of analysis. It has emerged from the investigation of the natural differential geometric structure on manifolds of probability distributions, which consists of a Riemannian metric defined by the Fisher information and a one-parameter family of affine connections called the $\alpha$-connections. The duality between the $\alpha$-connection and the $(-\alpha)$-connection together with the metric play an essential role in this geometry. This kind of duality, having emerged from manifolds of probability distributions, is ubiquitous, appearing in a variety of problems which might have no explicit relation to probability theory. Through the duality, it is possible to analyze various fundamental problems in a unified perspective. The first half of this book is devoted to a comprehensive introduction to the mathematical foundation of information geometry, including preliminaries from differential geometry, the geometry of manifolds or probability distributions, and the general theory of dual affine connections.The second half of the text provides an overview of many areas of applications, such as statistics, linear systems, information theory, quantum mechanics, convex analysis, neural networks, and affine differential geometry. The book can serve as a suitable text for a topics course for advanced undergraduates and graduate students.

目次

Preface Preface to the English edition Elementary differential geometry The geometric structure of statistical models Dual connections Statistical inference and differential geometry The geometry of time series and linear systems Multiterminal information theory and statistical inference Information geometry for quantum systems Miscellaneous topics Guide to the bibliography Bibliography Index

「Nielsen BookData」 より

詳細情報

• NII書誌ID(NCID): BA49572261
• ISBN:
  • 0821805312
  • 9780821843024
• LCCN: 00059362
• 出版国コード: us
• タイトル言語コード: eng
• 本文言語コード: eng
• 原本言語コード: jpn
• 出版地: Providence, R.I.,[Oxford]
• ページ数/冊数: x, 206 p.
• 大きさ: 26 cm
• 分類:
  • LCC : QA276
  • DC21 : 519.5
• 件名:
  • LCSH : Mathematical statistics
  • LCSH : Geometry, Differential
• 親書誌ID:
  • BA00080309