City University of Hong Kong
DSpace
 

CityU Institutional Repository >
3_CityU Electronic Theses and Dissertations >
ETD - Dept. of Mathematics  >
MA - Master of Philosophy  >

Please use this identifier to cite or link to this item: http://hdl.handle.net/2031/5481

Title: Learning gradients via gradient descent method
Other Titles: Ji yu ti du xia jiang suan fa de ti du xue xi
基於梯度下降算法的梯度學習
Authors: Guo, Xin (郭昕)
Department: Department of Mathematics
Degree: Master of Philosophy
Issue Date: 2008
Publisher: City University of Hong Kong
Subjects: Sobolev gradients.
Notes: CityU Call Number: QA218 .G86 2008
iv, 55 leaves 30 cm.
Thesis (M.Phil.)--City University of Hong Kong, 2008.
Includes bibliographical references (leaves 52-55)
Type: thesis
Abstract: We discuss the early stopping algorithm for gradient descent schemes on learning the gradient of the regression function. The motivation is to choose \useful" or \relevant" variables by a ranking method for the \large dimension, small sample" problem, where we do the ranking according to the norms of partial derivatives in some function spaces. Satisfactory learning rates are derived. In the algorithm, we used the early stopping technique, instead of the classical Tikhonov regularization method, to avoid over-¯tting. The advantage is that we need no longer consider the choice of the regular- ization coe±cient, for which no e±cient methodology is available. Many practical problems we confront have the character of high- dimension and small-sample, data points are well separated with con¯- dence. We formulate this observation precisely. Then the character is carefully and completely exploited in the analysis of the sample error. As a result, the learning rate has been improved to O(m¡c) (where m denotes the sample size) with c free of the dimension n of the sample space, when n > 23. We also give some analysis of the low-dimensional cases with 2 · n · 23.
Online Catalog Link: http://lib.cityu.edu.hk/record=b2340679
Appears in Collections:MA - Master of Philosophy

Files in This Item:

File Description SizeFormat
abstract.html134 BHTMLView/Open
fulltext.html134 BHTMLView/Open

Items in CityU IR are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0!
DSpace Software © 2013 CityU Library - Send feedback to Library Systems
Privacy Policy · Copyright · Disclaimer