Skip to content
Register Sign in Wishlist
Stochastic Approximation

Stochastic Approximation
A Dynamical Systems Viewpoint

£49.99

  • Author: Vivek S. Borkar, Tata Institute of Fundamental Research, Mumbai, India
  • Date Published: September 2008
  • availability: Temporarily unavailable - available from TBC
  • format: Hardback
  • isbn: 9780521515924

£ 49.99
Hardback

Temporarily unavailable - available from TBC
Notify me when available Add to wishlist

Looking for an inspection copy?

This title is not currently available on inspection

Description
Product filter button
Description
Contents
Resources
Courses
About the Authors
  • This simple, compact toolkit for designing and analyzing stochastic approximation algorithms requires only basic literacy in probability and differential equations. Yet these algorithms have powerful applications in control and communications engineering, artificial intelligence and economic modelling. The dynamical systems viewpoint treats an algorithm as a noisy discretization of a limiting differential equation and argues that, under reasonable hypotheses, it tracks the asymptotic behaviour of the differential equation with probability one. The differential equation, which can usually be obtained by inspection, is easier to analyze. Novel topics include finite-time behaviour, multiple timescales and asynchronous implementation. There is a useful taxonomy of applications, with concrete examples from engineering and economics. Notably it covers variants of stochastic gradient-based optimization schemes, fixed-point solvers, which are commonplace in learning algorithms for approximate dynamic programming, and some models of collective behaviour. Three appendices give background on differential equations and probability.

    • Simple, compact, cohesive
    • Motivated by modern applications and implementation
    • Discussion of current topics: finite-time behaviour, multiple timescales, asynchronous implementation
    Read more

    Reviews & endorsements

    'I highly recommend [this book] to all readers interested in the theory of recursive algorithms and its applications in practice.' Mathematical Reviews

    'This simple compact toolkit for designing and analyzing stochastic approximation algorithms requires only basic literacy in probability and differential equations … Ideal for graduate students, researchers and practitioners in electrical engineering and computer science, especially those working in control, communications, signal processing and machine learning, this book is also relevant to economics, probability and statistics.' L'Enseignement Mathématique

    See more reviews

    Customer reviews

    Not yet reviewed

    Be the first to review

    Review was not posted due to profanity

    ×

    , create a review

    (If you're not , sign out)

    Please enter the right captcha value
    Please enter a star rating.
    Your review must be a minimum of 12 words.

    How do you rate this item?

    ×

    Product details

    • Date Published: September 2008
    • format: Hardback
    • isbn: 9780521515924
    • length: 176 pages
    • copublisher: Hindustan Book Agency
    • dimensions: 233 x 157 x 17 mm
    • weight: 0.38kg
    • availability: Temporarily unavailable - available from TBC
  • Table of Contents

    Preface
    1. Introduction
    2. Basic convergence analysis
    3. Stability criteria
    4. Lock-in probability
    5. Stochastic recursive inclusions
    6. Multiple timescales
    7. Asynchronous schemes
    8. A limit theorem for fluctuations
    9. Constant stepsize algorithms
    10. Applications
    11. Appendices
    References
    Index.

  • Author

    Vivek S. Borkar, Tata Institute of Fundamental Research, Mumbai, India
    Vivek S. Borkar is dean of the School of Technology and Computer Science at the Tata Institute of Fundamental Research. A distinguished researcher in stochastic and adaptive control, he distils his deep knowledge and broad experience in this motivating book.

Sign In

Please sign in to access your account

Cancel

Not already registered? Create an account now. ×

Sorry, this resource is locked

Please register or sign in to request access. If you are having problems accessing these resources please email lecturers@cambridge.org

Register Sign in
Please note that this file is password protected. You will be asked to input your password on the next screen.

» Proceed

You are now leaving the Cambridge University Press website. Your eBook purchase and download will be completed by our partner www.ebooks.com. Please see the permission section of the www.ebooks.com catalogue page for details of the print & copy limits on our eBooks.

Continue ×

Continue ×

Continue ×

Find content that relates to you

Join us online

This site uses cookies to improve your experience. Read more Close

Are you sure you want to delete your account?

This cannot be undone.

Cancel

Thank you for your feedback which will help us improve our service.

If you requested a response, we will make sure to get back to you shortly.

×
Please fill in the required fields in your feedback submission.
×