<div class="buying"><font size="3"><b class="sans"><span id="btAsinTitle">Stochastic Approximation and Its Application (Nonconvex Optimization and Its Applications) (Hardcover)</span><!--Element not supported - Type: 8 Name: #comment--></b><br/></font></div><div class="buying">by <a href="http://www.amazon.com/exec/obidos/search-handle-url?%5Fencoding=UTF8&search-type=ss&index=books&field-author=Han-Fu%20Chen"><font color="#003399">Han-Fu Chen</font></a> (Author) <span class="tiny"><font size="1"> </font></span><br/> </div><div class="buying"><b></b></div><div class="buying"><b>Hardcover:</b> 376 pages </div><p><b>Publisher:</b> Springer; 1 edition </p><p><b>Language:</b> English </p><p><b>ISBN-10:</b> 1402008066 </p><p><strong>Amazon Prce：<font color="#990000">$229.00</font></strong><br/> </p><p><strong>Amazon Link：</strong><a href="http://www.amazon.com/Stochastic-Approximation-Application-Optimization-Applications/dp/1402008066/ref=sr_1_1?ie=UTF8&s=books&qid=1205046200&sr=8-1">http://www.amazon.com/Stochastic-Approximation-Application-Optimization-Applications/dp/1402008066/ref=sr_1_1?ie=UTF8&s=books&qid=1205046200&sr=8-1</a></p><p> </p><div class="content"><b>Book Description</b><br/>This book presents the recent development of stochastic approximation algorithms with expanding truncations based on the TS (trajectory-subsequence) method, a newly developed method for convergence analysis. This approach is so powerful that conditions used for guaranteeing convergence have been considerably weakened in comparison with those applied in the classical probability and ODE methods. The general convergence theorem is presented for sample paths and is proved in a purely deterministic way. The sample-path description of theorems is particularly convenient for applications. Convergence theory takes both observation noise and structural error of the regression function into consideration. Convergence rates, asymptotic normality and other asymptotic properties are presented as well. Applications of the developed theory to global optimization, blind channel identification, adaptive filtering, system parameter identification, adaptive stabilization and other problems arising from engineering fields are demonstrated.<br/>Audience: Researchers and students of both graduate and undergraduate levels in systems and control, optimization, signal processing, communication and statistics. <br/><br/><b>Book Info</b><br/>Presents the recent development of stochastic approximation algorithms with expanding truncations based on the TS (trajectory-subsequence) method, a newly developed method for convergence analysis. </div><p></p><p> <br/><br/></p>

[此贴子已经被作者于2008-3-10 11:54:51编辑过]