LFD Book Forum  

Go Back   LFD Book Forum > Course Discussions > Online LFD course > Homework 4

Reply
 
Thread Tools Display Modes
  #1  
Old 02-03-2013, 07:33 AM
melipone melipone is offline
Senior Member
 
Join Date: Jan 2013
Posts: 72
Default General question on VC bounds in Q9-10

Is ensemble learning with voting, an intersection or union of VC dimensions?
Reply With Quote
  #2  
Old 02-03-2013, 10:45 AM
yaser's Avatar
yaser yaser is offline
Caltech
 
Join Date: Aug 2009
Location: Pasadena, California, USA
Posts: 1,474
Default Re: General question on VC bounds in Q9-10

Quote:
Originally Posted by melipone View Post
Is ensemble learning with voting, an intersection or union of VC dimensions?
Ensemble learning (covered briefly in Lecture 18) reuses the same hypothesis set by combining the hypotheses in it, so in general it is neither an intersection nor a union. Since the combination can involve only one hypothesis (replicating the original hypothesis set) or multiple hypotheses (resulting possibly in new hypotheses), the VC dimension of the resulting hypothesis set is bigger (at least not smaller) than the original VC dimension.
__________________
Where everyone thinks alike, no one thinks very much
Reply With Quote
  #3  
Old 01-04-2018, 02:20 PM
hhprogram hhprogram is offline
Junior Member
 
Join Date: Oct 2017
Posts: 7
Default Re: General question on VC bounds in Q9-10

follow up on this question. So, if the final ensemble learned hypothesis set has weights on all the original individual hypothesis sets - does that mean the VC dimension is the union of all the individual hypothesis sets?

It seems in general that ensemble learning might run into the VC dimension / generalization problem (ie similar to 'snooping' when you try a model and then see it doesn't perform well, and then try another model etc..) but since it is used a lot in practice - I'm curious to learn why it doesn't suffer from generalization problems. After doing a little research - is it because generally when using the ensemble learning the individual hypothesis are relatively simple and thus have a low VC dimension (and also perform ok but not great by themselves) therefore, when combining simple models together the VC dimension doesn't get too ridiculous? Thanks
Reply With Quote
  #4  
Old 01-06-2018, 03:13 PM
htlin's Avatar
htlin htlin is offline
NTU
 
Join Date: Aug 2009
Location: Taipei, Taiwan
Posts: 570
Default Re: General question on VC bounds in Q9-10

Quote:
Originally Posted by hhprogram View Post
follow up on this question. So, if the final ensemble learned hypothesis set has weights on all the original individual hypothesis sets - does that mean the VC dimension is the union of all the individual hypothesis sets?

It seems in general that ensemble learning might run into the VC dimension / generalization problem (ie similar to 'snooping' when you try a model and then see it doesn't perform well, and then try another model etc..) but since it is used a lot in practice - I'm curious to learn why it doesn't suffer from generalization problems. After doing a little research - is it because generally when using the ensemble learning the individual hypothesis are relatively simple and thus have a low VC dimension (and also perform ok but not great by themselves) therefore, when combining simple models together the VC dimension doesn't get too ridiculous? Thanks
In general it might be bigger than the union. For instance, a linear ensemble hypothesis set includes each individual hypothesis as special cases. So its VC dimension is bigger. Hope this helps.
__________________
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 09:06 PM.


Powered by vBulletin® Version 3.8.3
Copyright ©2000 - 2018, 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.