LFD Book Forum

LFD Book Forum (http://book.caltech.edu/bookforum/index.php)
-   Chapter 2 - Training versus Testing (http://book.caltech.edu/bookforum/forumdisplay.php?f=109)
-   -   Proof of Growth Function when Points are not binary (http://book.caltech.edu/bookforum/showthread.php?t=4132)

udaykamath 03-27-2013 03:12 PM

Proof of Growth Function when Points are not binary
 
Prof Dr Yaser
I understand the step by step process in bounding the growth function B(N,k) in terms of recursion using x1,x2...xN data points using structural arrangements. I however started thinking, in a numerical data where x1,x2...xN is real numbers we cannot use this alpha + 2* Beta trick and use the polynomial bound by combination? What is the bounds when data is not binary ? Is it still Polynomial in N, and how?
Thanks

Uday Kamath
PhD candidate
GMU

yaser 04-08-2013 01:43 PM

Re: Proof of Growth Function when Points are not binary
 
Quote:

Originally Posted by udaykamath (Post 10084)
I understand the step by step process in bounding the growth function B(N,k) in terms of recursion using x1,x2...xN data points using structural arrangements. I however started thinking, in a numerical data where x1,x2...xN is real numbers we cannot use this alpha + 2* Beta trick and use the polynomial bound by combination? What is the bounds when data is not binary ? Is it still Polynomial in N, and how?

You are correct. For non-binary functions, the argument is more elaborate. This is addressed in Vapnik's book "Statistical Learning Theory" in much detail, and also appears in other books and papers.


All times are GMT -7. The time now is 01:25 AM.

Powered by vBulletin® Version 3.8.3
Copyright ©2000 - 2019, 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.