Skip to main content
SpringerLink
Log in

Learning with the Minimum Description Length Principle

  • Book
  • © 2023

Overview

Authors:
  1. Kenji Yamanishi

    1. Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Bunkyo-ku, Japan

    View author publications

    You can also search for this author in PubMed   Google Scholar

  • Introduces readers to a modern theory of the minimum description length (MDL) principle
  • Includes rich examples of MDL applications to machine learning and data science
  • Written by a pioneer of information-theoretic learning theory

This is a preview of subscription content, log in via an institution to check access.

Access this book

Log in via an institution
eBook USD 109.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book USD 139.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

Licence this eBook for your library

Institutional subscriptions

Table of contents (9 chapters)

  1. Front Matter

    Pages i-xx
    Download chapter PDF

  2. Information and Coding

    • Kenji Yamanishi
    Pages 1-46

  3. Parameter Estimation

    • Kenji Yamanishi
    Pages 47-90

  4. Model Selection

    • Kenji Yamanishi
    Pages 91-135

  5. Latent Variable Model Selection

    • Kenji Yamanishi
    Pages 137-183

  6. Sequential Prediction

    • Kenji Yamanishi
    Pages 185-208

  7. MDL Change Detection

    • Kenji Yamanishi
    Pages 209-263

  8. Continuous Model Selection

    • Kenji Yamanishi
    Pages 265-285

  9. Extension of Stochastic Complexity

    • Kenji Yamanishi
    Pages 287-316

  10. Mathematical Preliminaries

    • Kenji Yamanishi
    Pages 317-334

  11. Back Matter

    Pages 335-339
    Download chapter PDF
Back to top

Keywords

About this book

This book introduces readers to the minimum description length (MDL) principle and its applications in learning. The MDL is a fundamental principle for inductive inference, which is used in many applications including statistical modeling, pattern recognition and machine learning. At its core, the MDL is based on the premise that “the shortest code length leads to the best strategy for learning anything from data.” The MDL provides a broad and unifying view of statistical inferences such as estimation, prediction and testing and, of course, machine learning.

The content covers the theoretical foundations of the MDL and broad practical areas such as detecting changes and anomalies, problems involving latent variable models, and high dimensional statistical inference, among others. The book offers an easy-to-follow guide to the MDL principle, together with other information criteria, explaining the differences between their standpoints. 

Written in a systematic, concise and comprehensive style, this book is suitable for researchers and graduate students of machine learning, statistics, information theory and computer science.

Authors and Affiliations

  • Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Bunkyo-ku, Japan

    Kenji Yamanishi

About the author

Kenji Yamanishi is a Professor at the Graduate School of Information Science and Technology, University of Tokyo, Japan. After completing the master course at the Graduate School of University of Tokyo, he joined NEC Corporation in 1987. He received his doctorate (in Engineering) from the University of Tokyo in 1992 and joined the University faculty in 2009. His research interests and contributions are in the theory of the minimum description length principle, information-theoretic learning theory, and data science applications such as anomaly detection and text mining.

Bibliographic Information

  • Book Title: Learning with the Minimum Description Length Principle

  • Authors: Kenji Yamanishi

  • DOI: https://doi.org/10.1007/978-981-99-1790-7

  • Publisher: Springer Singapore

  • eBook Packages: Computer Science, Computer Science (R0)

  • Copyright Information: Springer Nature Singapore Pte Ltd. 2023

  • Hardcover ISBN: 978-981-99-1789-1Published: 15 September 2023

  • Softcover ISBN: 978-981-99-1792-1Due: 16 October 2023

  • eBook ISBN: 978-981-99-1790-7Published: 14 September 2023

  • Edition Number: 1

  • Number of Pages: XX, 339

  • Number of Illustrations: 3 b/w illustrations, 48 illustrations in colour

  • Topics: Data Structures and Information Theory, Machine Learning

Publish with us

Policies and ethics

Back to top

Search

Navigation