IDEAS home Printed from https://ideas.repec.org/h/spr/sprchp/978-4-431-56922-0_1.html
   My bibliography  Save this book chapter

Information Geometry

In: Minimum Divergence Methods in Statistical Machine Learning

Author

Listed:
  • Shinto Eguchi

    (Institute of Statistical Mathematic)

  • Osamu Komori

    (Seikei University)

Abstract

In the likelihood principle, the log-likelihood functionLog likelihood function on a statistical modelStatistical model defines the maximum likelihood estimatorMaximum Likelihood Estimator (MLE). Then the Kullback-Leibler (KL) divergenceKullback-Leibler (KL) divergence is introduced with a close relationship of the maximum likelihood, which is clarified in association with an empirical Pythagorean theoremEmpirical Pythagorean theorem. As familiar statistical modelsStatistical model, we consider a normal distribution model and a contingency tableContingency tables model to explore typical aspects of information geometry. The information metricInformation metric, the e-geodesicE-geodesic, and the m-geodesicM-geodesic paths are formulated in a general framework. Finally, we observe the Pythagorean theorem in the space of all probability density functions. If the e-geodesicE-geodesic and m-geodesicM-geodesic paths orthogonally intersect with respect to the information metricInformation metric, then the two paths induce a right triangle with a Pythagorean identity in the sense of the KL divergenceKullback-Leibler (KL) divergence.

Suggested Citation

  • Shinto Eguchi & Osamu Komori, 2022. "Information Geometry," Springer Books, in: Minimum Divergence Methods in Statistical Machine Learning, chapter 0, pages 3-17, Springer.
    • Handle: RePEc:spr:sprchp:978-4-431-56922-0_1
    DOI: 10.1007/978-4-431-56922-0_1
    as

    Download full text from publisher

    To our knowledge, this item is not available for download. To find whether it is available, there are three options:
    1. Check below whether another version of this item is available online.
    2. Check on the provider's web page whether it is in fact available.
    3. Perform a
    for a similarly titled item that would be available.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:spr:sprchp:978-4-431-56922-0_1. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.