Advanced Mean Field Methods: Theory and Practice (Neural Information Processing)

Opper, Manfred; Saad, David (Edited by)

ISBN 10: 0262150549 / ISBN 13: 9780262150545

Published by MIT Press, 2001

About this Item

Condition : Fair/usable study copy. Ex university library with associated markings. Hard cover, no jacket. 273pp. No highlighting or annotations. Cover sunned and worn. Photo on request.

Seller Inventory # 944014

Bibliographic Details

• Title: Advanced Mean Field Methods: Theory and Practice (Neural Information Processing)
• Publisher: MIT Press
• Publication Date: 2001
• Language: English
• ISBN 10: 0262150549
• ISBN 13: 9780262150545
• Binding: Hardcover
• Condition: Fair
• Dust Jacket Condition: No Jacket

About this title

Synopsis

A major problem in modern probabilistic modeling is the huge computational complexity involved in typical calculations with multivariate probability distributions when the number of random variables is large. Because exact computations are infeasible in such cases and Monte Carlo sampling techniques may reach their limits, there is a need for methods that allow for efficient approximate computations. One of the simplest approximations is based on the mean field method, which has a long history in statistical physics. The method is widely used, particularly in the growing field of graphical models.

Researchers from disciplines such as statistical physics, computer science, and mathematical statistics are studying ways to improve this and related methods and are exploring novel application areas. Leading approaches include the variational approach, which goes beyond factorizable distributions to achieve systematic improvements; the TAP (Thouless-Anderson-Palmer) approach, which incorporates correlations by including effective reaction terms in the mean field theory; and the more general methods of graphical models.

Bringing together ideas and techniques from these diverse disciplines, this book covers the theoretical foundations of advanced mean field methods, explores the relation between the different approaches, examines the quality of the approximation obtained, and demonstrates their application to various areas of probabilistic modeling.

About the Authors

Manfred Opper is a Reader at the Neural Computing Research Group, School of Engineering and Applied Science, Aston University, UK.

David Saad is Professor, the Neural Computing Research Group, School of Engineering and Applied Science, Aston University, UK