Stochastic Approximation (Cambridge Tracts in Mathematics) - Softcover

Wasan

Softcover

ISBN 10: 0521604850 ISBN 13: 9780521604857

Publisher: Cambridge University Press, 2008

Synopsis

Stochastic approximation is a relatively new technique for studying the properties of an experimental situation; it has important applications in fields such as medicine and engineering. The subject can be treated either largely as a branch of pure mathematics, or else from an empirical and practical angle. In this book, Dr Wasan gives a rigorous mathematical treatment of the subject, drawing together the scattered results of a number of authors. He discusses the conditions under which the method gives a valid approximation to the required solution; methods for optimal choice of parameters to hasten convergence; the comparison of the method with other techniques. The discussion and proofs of theorems are given in enough detail to make them easy to follow, while a number of interesting examples show how the techniques may be applied in many fields.

About this title

Review

"This book organizes, develops and presents both the classical expected utility and newer non-expected utility models of decision making in a way that only Peter Wakker could do. Readers interested in understanding how individuals do, and how they should, make decisions under conditions of risk or uncertainty could do no better than to consult this volume." - Mark Machina, University of California, San Diego

"Given this background, it is not a surprise that his book is a very thoughtful and in-depth overview of prospect theory."
-- Marc Oliver Rieger, Mathematical Reviews

"Peter Wakker's new book provides a brilliant account of what has happened in the field of decision theory during the last twenty years. Decision analysts will find here many tools and assessment techniques that will enlarge their usual bag of tricks. One of the virtues of the remarkable text is that it will help to reduce the gap between the models developed by decision theorists and the ones used in practice by most decision analysts. Every serious decision analyst should have a copy of this book at hand." - Denis Bouyssou, CNRS and Université Paris-Dauphine

"This is a long-overdue book, from one of the leading authorities in the field. Wakker is a leader both on the theoretical underpinnings of decision theory and in applying decision theory to practice; he also has an encyclopaedic knowledge of the field. The book is structured in a way that should make it easily accessible to a broad audience, from more mathematically-oriented readers interested in the foundations to practitioners interested in applying the ideas." - Joseph Y. Halpern, Cornell University

"This masterful survey of major theories of choice and of their implications for measurement represents two decades of research and teaching by a flawless perfectionist. Wakker's view of the field is scholarly, coherent and deeply personal." - Daniel Kahneman, Princeton University, Nobel Laureate in Economic Sciences, 2002

"Peter Wakker's book conveys the beauty and practical value of formal thinking about decisions with uncertainty, with minimal mathematical fuss. Scholars who have lived with this material for years will still find much that is new." - Drazen Prelec, Massachusetts Institute of Technology

"The need for realistic models of economic decisions involving risk and uncertainty, with plausible behavioral foundations, has never been more acute. Peter Wakker provides an intuitive and accessible, but rigorous, treatment of prospect theory, widely accepted as the main alternative to the hyper-rational expected utility model. This is the only book-length treatment of this important topic, and seems certain to dominate the field for years to come." - John Quiggin, University of Queensland

Book Description

Stochastic approximation is a technique for studying the properties of an experimental situation; it has important applications in fields such as medicine and engineering. Dr Wasan gives a rigorous mathematical treatment of the subject. The discussion and proofs of theorems are easy to follow, while a number of interesting examples show how the techniques may be applied in many fields.

Edition details

• Publisher: Cambridge University Press
• Publication date: 2008
• Language: English
• ISBN 10: 0521604850
• ISBN 13: 9780521604857
• Binding: Paperback
• Edition number: 1
• Number of pages: 216