LFD Book Forum  

Go Back   LFD Book Forum > Book Feedback - Learning From Data > Chapter 2 - Training versus Testing

Reply
 
Thread Tools Display Modes
  #1  
Old 09-25-2017, 01:37 PM
mauriciogruppi mauriciogruppi is offline
Junior Member
 
Join Date: Sep 2017
Posts: 2
Default Exercise 2.2 (b)

The question is asking if there is a hypothesis set for which m_H(N) = N + 2^floor(N/2).

Theorem 2.4 states that m_H(N) <= sum{0 to k-1} (N choose i) if k is a breakpoint.

My understanding is that m_H(N) = 2^k or it is bounded by a polynomial.

However, the given growth function m_H(N) = N + 2^floor(N/2) seems exponential because of 2^(N/2). Therefore my answer is NO, it does not make sense to look for such hypothesis set.

Can someone clarify if this is correct?

Edit: Indeed, it is possible to show that m_H(N) is not bounded by a polynomial.
Reply With Quote
  #2  
Old 09-27-2017, 07:29 AM
htlin's Avatar
htlin htlin is offline
NTU
 
Join Date: Aug 2009
Location: Taipei, Taiwan
Posts: 562
Default Re: Exercise 2.2 (b)

Your understanding seems very reasonable!
__________________
When one teaches, two learn.
Reply With Quote
Reply

Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT -7. The time now is 12:22 AM.


Powered by vBulletin® Version 3.8.3
Copyright ©2000 - 2017, 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.