LFD Book Forum

LFD Book Forum (http://book.caltech.edu/bookforum/index.php)
-   Homework 4 (http://book.caltech.edu/bookforum/forumdisplay.php?f=133)
-   -   General question on VC bounds in Q9-10 (http://book.caltech.edu/bookforum/showthread.php?t=3946)

melipone 02-03-2013 08:33 AM

General question on VC bounds in Q9-10
 
Is ensemble learning with voting, an intersection or union of VC dimensions?

yaser 02-03-2013 11:45 AM

Re: General question on VC bounds in Q9-10
 
Quote:

Originally Posted by melipone (Post 9154)
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.

hhprogram 01-04-2018 03:20 PM

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

htlin 01-06-2018 04:13 PM

Re: General question on VC bounds in Q9-10
 
Quote:

Originally Posted by hhprogram (Post 12896)
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.


All times are GMT -7. The time now is 02:50 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.