Description

Book Synopsis
Sure to be influential, this book lays the foundations for the use of algebraic geometry in statistical learning theory. Many widely used statistical models and learning machines applied to information science have a parameter space that is singular: mixture models, neural networks, HMMs, Bayesian networks, and stochastic context-free grammars are major examples. Algebraic geometry and singularity theory provide the necessary tools for studying such non-smooth models. Four main formulas are established: 1. the log likelihood function can be given a common standard form using resolution of singularities, even applied to more complex models; 2. the asymptotic behaviour of the marginal likelihood or 'the evidence' is derived based on zeta function theory; 3. new methods are derived to estimate the generalization errors in Bayes and Gibbs estimations from training errors; 4. the generalization errors of maximum likelihood and a posteriori methods are clarified by empirical process theory o

Trade Review
"Overall, the many insightful remarks and simple direct language make the book a pleasure to read." Shaowei Lin, Mathematical Reviews

Table of Contents
Preface; 1. Introduction; 2. Singularity theory; 3. Algebraic geometry; 4. Zeta functions and singular integral; 5. Empirical processes; 6. Singular learning theory; 7. Singular learning machines; 8. Singular information science; Bibliography; Index.

Algebraic Geometry and Statistical Learning Theory 25 Cambridge Monographs on Applied and Computational Mathematics Series Number 25

    Product form

    A Hardback by Sumio Watanabe

    £76.99

    Includes FREE delivery

    Order before 4pm today for delivery by Tue 15 Sep 2026.

    15 in stock

      Trusted by thousands of customers. See 2,385+ Customer Reviews

      View other formats and editions of Algebraic Geometry and Statistical Learning Theory 25 Cambridge Monographs on Applied and Computational Mathematics Series Number 25 by Sumio Watanabe

      Book details

      Publisher Cambridge University Press
      Published 8/13/2009 12:00:00 AM
      ISBN-13 9780521864671
      978-0521864671
      ISBN-10 0521864674
      Also in:
      Machine learning Algebraic geometry

      Description

      Book Synopsis
      Sure to be influential, this book lays the foundations for the use of algebraic geometry in statistical learning theory. Many widely used statistical models and learning machines applied to information science have a parameter space that is singular: mixture models, neural networks, HMMs, Bayesian networks, and stochastic context-free grammars are major examples. Algebraic geometry and singularity theory provide the necessary tools for studying such non-smooth models. Four main formulas are established: 1. the log likelihood function can be given a common standard form using resolution of singularities, even applied to more complex models; 2. the asymptotic behaviour of the marginal likelihood or 'the evidence' is derived based on zeta function theory; 3. new methods are derived to estimate the generalization errors in Bayes and Gibbs estimations from training errors; 4. the generalization errors of maximum likelihood and a posteriori methods are clarified by empirical process theory o

      Trade Review
      "Overall, the many insightful remarks and simple direct language make the book a pleasure to read." Shaowei Lin, Mathematical Reviews

      Table of Contents
      Preface; 1. Introduction; 2. Singularity theory; 3. Algebraic geometry; 4. Zeta functions and singular integral; 5. Empirical processes; 6. Singular learning theory; 7. Singular learning machines; 8. Singular information science; Bibliography; Index.

      Recently viewed products

      © 2026 Book Curl

        • American Express
        • Apple Pay
        • Diners Club
        • Discover
        • Google Pay
        • Maestro
        • Mastercard
        • PayPal
        • Shop Pay
        • Union Pay
        • Visa

        Login

        Forgot your password?

        Don't have an account yet?
        Create account