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/2031/3966

Title: Learning from approximate data
Other Titles: Cong jin si zi liao xue xi
從近似資料學習
Authors: Cheung, Hung Ching (張紅靖)
Department: Dept. of Mathematics
Degree: Master of Philosophy
Issue Date: 2000
Publisher: Dept. of Mathematics, City University of Hong Kong
Subjects: Approximation theory
Polynomials
Notes: 37 leaves ; 30 cm.
CityU Call Number: QA221.C48 2000
Includes bibliographical references (leaves 36-37)
Thesis (M.Phil.)--City University of Hong Kong, 2000
Type: Thesis
Abstract: We give an algorithm to PAC learn the coefficients of a multivariate polynomial from the signs of its values, over a sample of real points which are only known approximately. While there are several papers dealing with PAC learning polynomials (e.g. [3, II]), they mainly only consider variables over finite fields or real variables with no round-off error. In particular, to the best of our knowledge, the only other work considering rounded-off real data is that of Dennis Cheung [6]. There, multivariate polynomials are learned under the assumption that the coefficients are independent, eventually leading to a linear programming problem. In this thesis we consider the other extreme: namely, we consider the case where the coefficients of the polynomial are (polynomial) functions of a single parameter. As we shall see, this leads to solving a non-linear system of polynomial inequalities in one variable. Our algorithm does so in a number of operations which is polynomial in the data size and the logarithm of the condition of the sample.
Online Catalog Link: http://lib.cityu.edu.hk/record=b1696585
Appears in Collections:MA - Master of Philosophy

Files in This Item:

File Description SizeFormat
fulltext.html159 BHTMLView/Open
abstract.html159 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