LFD Book Forum

LFD Book Forum (http://book.caltech.edu/bookforum/index.php)
-   General Discussion of Machine Learning (http://book.caltech.edu/bookforum/forumdisplay.php?f=105)
-   -   expected value for the SVM generalization error (http://book.caltech.edu/bookforum/showthread.php?t=1888)

Andrs 10-02-2012 04:47 AM
expected value for the SVM generalization error
 
In lecture 14 slide 20 there is the following statement:
Expected value(E_out) = < Expected val(#of support vectors/N-1)
That is, the exp val for the upper bound for the E_out is limited by the expected value of the #number of support vectors divided by the number of data points minus 1.

I am trying to find some reference to a book or article that presents this upper bound for the E_out for SVM but I am having a really hard time to find anything. Unfortunatly the course book does not cover SVM at all. Any suggestion about articles that discuss this upper bound for SVM more or less clearly?

yaser 10-03-2012 10:42 AM
Re: expected value for the SVM generalization error
 
Quote:
Originally Posted by Andrs (Post 5991)
In lecture 14 slide 20 there is the following statement:
Expected value(E_out) = < Expected val(#of support vectors/N-1)
That is, the exp val for the upper bound for the E_out is limited by the expected value of the #number of support vectors divided by the number of data points minus 1.

I am trying to find some reference to a book or article that presents this upper bound for the E_out for SVM but I am having a really hard time to find anything. Unfortunatly the course book does not cover SVM at all. Any suggestion about articles that discuss this upper bound for SVM more or less clearly?
The result is in Vapnik's short book "The Nature of Statistical Learning Theory" and his more technical book on the subject.


All times are GMT -7. The time now is 05:36 PM.

Powered by vBulletin® Version 3.8.3
Copyright ©2000 - 2021, Jelsoft Enterprises Ltd.
The contents of this forum are to be used ONLY by readers of the Learning From Data book by Yaser S. Abu-Mostafa, Malik Magdon-Ismail, and Hsuan-Tien Lin, and participants in the Learning From Data MOOC by Yaser S. Abu-Mostafa. No part of these contents is to be communicated or made accessible to ANY other person or entity.