LFD Book Forum  

Go Back   LFD Book Forum > Course Discussions > Online LFD course > Homework 3

Reply
 
Thread Tools Display Modes
  #1  
Old 04-18-2013, 06:25 AM
Elroch Elroch is offline
Invited Guest
 
Join Date: Mar 2013
Posts: 143
Default A little puzzle

Pondering the loose relationship between parametrisation of a hypothesis set and VC dimension d_{VC} (or the minimum break point, d_{VC} + 1) led me to the following example and puzzle.

Let the set of points be the natural numbers \{1, 2, 3, ...\}

Let elements of the hypothesis set be made up of alternating intervals of the same size, like a 1-dimensional checkerboard with varying scale

H_n = \{1, 2, ... n\} \cup \{2n+1, 2n+2, ..., 3n\} \cup \{4n+1, 4n+2, ... 5n\} \cup ...

What is the VC dimension of this hypothesis set?

[there is also a continuous version on the real line, but all the structure is in this simplified version]
Reply With Quote
  #2  
Old 04-18-2013, 04:15 PM
Michael Reach Michael Reach is offline
Senior Member
 
Join Date: Apr 2013
Location: Baltimore, Maryland, USA
Posts: 71
Default Re: A little puzzle

Don't have the rules too clear. Can your alternating segments contain the +1s, _or_ all the -1s? If not, I imagine the VC dimension is 0.

If you allow both, I guess the first pattern you can't achieve is +1, -1, -1
so the VC dimension would be 2.

Or do you allow them shifted as well, then you'd get that one by starting at 2. But I don't think you could do +1, -1, +1, +1.
Reply With Quote
  #3  
Old 04-18-2013, 04:44 PM
Elroch Elroch is offline
Invited Guest
 
Join Date: Mar 2013
Posts: 143
Default Re: A little puzzle

Forgive me if it wasn't clear. There is exactly one hypothesis for each positive integer n, as described in the first post.

Intuitively, each hypothesis (i.e. permitted subset of \{1, 2, 3, ...\} )is an alternating sequence of "black" and "white" intervals of equal size starting at 1, and continuing indefinitely. "Black" = +1 = inclusion in the set, and "white" = -1 = exclusion from the set.

ok?

Do remember you have great freedom as to how to choose a set of N points. Use it well.

A good attack might be to try to shatter sets for increasing N from N=1 upward.
Reply With Quote
  #4  
Old 04-18-2013, 06:41 PM
Michael Reach Michael Reach is offline
Senior Member
 
Join Date: Apr 2013
Location: Baltimore, Maryland, USA
Posts: 71
Default Re: A little puzzle

Ah - not the first time today I was tripped up by the rule that we only need to find a single set of xns with the maximum shattering. I keep forgetting and looking for some set of xns which doesn't.

So here's a method that will work for any N, and I don't even need all of your hypotheses; it's enough just to use the set of H's where n=2^k.
H0=+1 for 1,3,5,7,...
H1=+1 for 1,2,5,6,9,10,...
H2=+1 for 1,2,3,4,9,10,11,12,17,18,19,20,...
H3=+1 for 1,2,3,4,5,6,7,8,17,18,19,...

The easy way to see it is to use binary notation.
H0=+1 for any n with the last digit=1
H1=+1 for any n with the second-to-last digit=1
H2=+1 for any n with the third-to-last digit=1 etc.

Now gH(N)=2^N. Here's how we build our set of x1,...,xN that we can shatter.

For N, take the set Z of every combination of N 1s and 0s and use them to build our x1,...,xN. They will be very big numbers indeed, with 2^N digits or so.
The first digit of xi, call it xi1, is the ith digit of the first element of Z. If that is 000000...0 (N 0s), the first digits of all the xis will all be zero as well, so all of the numbers x1,...,xN will start with 0.
If the second element of Z is 000000..01 - might as well keep them in order - the second digit of x1,...,xN will be 0, 0, ..., 0, and 1 respectively. And so forth, for all 2^N digits.

These N very special binary numbers are shattered by H0 through H(2^N-1), as H(i) picks out the ith digit of each of our numbers, and the digits cover every possibility in Z.

Way to go - this is a neat problem.
Reply With Quote
  #5  
Old 04-18-2013, 06:43 PM
Elroch Elroch is offline
Invited Guest
 
Join Date: Mar 2013
Posts: 143
Default Re: A little puzzle

Thank you and well done!

Exactly the solution I found.
Reply With Quote
  #6  
Old 04-18-2013, 09:07 PM
yaser's Avatar
yaser yaser is offline
Caltech
 
Join Date: Aug 2009
Location: Pasadena, California, USA
Posts: 1,477
Default Re: A little puzzle

Cool. I'll copy the thread into the Create New Homework Problems forum.
__________________
Where everyone thinks alike, no one thinks very much
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 06:40 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.