LFD Book Forum Shattering by dichotomies
 User Name Remember Me? Password
 FAQ Calendar Mark Forums Read

 Thread Tools Display Modes
#1
04-18-2012, 06:46 PM
 timhndrxn Junior Member Join Date: Apr 2012 Posts: 9
Shattering by dichotomies

OK, Definition 2.2 talks about shattering dichotomies based on H. So H shatters dichotomies. So all was OK until Definition 2.4, which talks about shattering dichotomies by other dichotomies.
#2
04-19-2012, 02:46 PM
 magdon RPI Join Date: Aug 2009 Location: Troy, NY, USA. Posts: 595
Re: Shattering by dichotomies

Def 2.2 defines m(n) using which is the restriction of to a data set, i.e the number of different hypotheses that can implement on this particular data set. A hypothesis when restricted to a finite data set results in a dichotomy, a collection of on the data points; A dichotomy is similar to a hypothesis. does not shatter a dichotomy. It shatters a data set. So shatters a data set if when restricted to that data set, can implement all the dichotomies.

Def 2.4 is introducing a more subtle concept. Fix a break point and consider the worst possible hypothesis set with the condition that it must have a break point . Worst means having the largest . The growth function of this worst hypothesis set is called . The indicates that the hypothesis set must have a break point there; otherwise is very much like except it is not for a particular hypothesis set, but rather for the worst possible hypothesis set with the break-point property.

We can analyze (even though it looks harder to analyze since we don't know what this worst hypothesis set is). However, for a particular hypothesis with break point , we cannot really analyze without more information on they hypothesis set. But since is for the worst possible hypothesis set, the particular hypothesis set cannot be worse than this and so must have a smaller growth function. That is we indirectly bound by

for any hypothesis set that has a break point at .

Quote:
 Originally Posted by timhndrxn OK, Definition 2.2 talks about shattering dichotomies based on H. So H shatters dichotomies. So all was OK until Definition 2.4, which talks about shattering dichotomies by other dichotomies.
__________________
Have faith in probability
#3
04-19-2012, 03:51 PM
 jcatanz Member Join Date: Apr 2012 Posts: 41
Re: Shattering by dichotomies

Thanks for this helpful explanation!
#4
04-19-2012, 05:45 PM
 timhndrxn Junior Member Join Date: Apr 2012 Posts: 9
Re: Shattering by dichotomies

Magdon, the explanation helps. Thank you. --Tim

 Thread Tools Display Modes Linear Mode

 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 Rules
 Forum Jump User Control Panel Private Messages Subscriptions Who's Online Search Forums Forums Home General     General Discussion of Machine Learning     Free Additional Material         Dynamic e-Chapters         Dynamic e-Appendices Course Discussions     Online LFD course         General comments on the course         Homework 1         Homework 2         Homework 3         Homework 4         Homework 5         Homework 6         Homework 7         Homework 8         The Final         Create New Homework Problems Book Feedback - Learning From Data     General comments on the book     Chapter 1 - The Learning Problem     Chapter 2 - Training versus Testing     Chapter 3 - The Linear Model     Chapter 4 - Overfitting     Chapter 5 - Three Learning Principles     e-Chapter 6 - Similarity Based Methods     e-Chapter 7 - Neural Networks     e-Chapter 8 - Support Vector Machines     e-Chapter 9 - Learning Aides     Appendix and Notation     e-Appendices

All times are GMT -7. The time now is 08:15 AM.

 Contact Us - LFD Book - Top