LFD Book Forum M=|H|? (Lecture 2 slide 16-17)
 User Name Remember Me? Password
 FAQ Calendar Mark Forums Read

 Thread Tools Display Modes
#1
01-14-2013, 06:33 PM
 Haowen Member Join Date: Jan 2013 Posts: 24
M=|H|? (Lecture 2 slide 16-17)

I have a question regarding the value of M in the multiple-bins Hoeffding bound slides.

M is supposed to be the number of different alternate hypotheses considered by the learning algorithm.

At the same time, H is the space of possible hypotheses that can be considered by the algorithm (e.g., all linear functions, etc).

I keep going back and forth in my mind about whether M=|H|.

Specifically, suppose that for a SPECIFIC training set X, after looking at the data points in X, the algorithm only explored some subset of H, say G with |G| < |H|.

Would it then be correct to set M = |G| and say that for the specific training set X, the probability of the hypothesis being bad is at most 2|G|*the hoeffding bound ? Or would this be incorrect since the theorem only deals with the behavior of the system over all possible X with the distribution P.

Thanks!
#2
01-14-2013, 06:55 PM
 yaser Caltech Join Date: Aug 2009 Location: Pasadena, California, USA Posts: 1,477
Re: M=|H|? (Lecture 2 slide 16-17)

Quote:
 Originally Posted by Haowen I have a question regarding the value of M in the multiple-bins Hoeffding bound slides. M is supposed to be the number of different alternate hypotheses considered by the learning algorithm. At the same time, H is the space of possible hypotheses that can be considered by the algorithm (e.g., all linear functions, etc). I keep going back and forth in my mind about whether M=|H|. Specifically, suppose that for a SPECIFIC training set X, after looking at the data points in X, the algorithm only explored some subset of H, say G with |G| < |H|. Would it then be correct to set M = |G| and say that for the specific training set X, the probability of the hypothesis being bad is at most 2|G|*the hoeffding bound ? Or would this be incorrect since the theorem only deals with the behavior of the system over all possible X with the distribution P. Thanks!
You raise interesting points. First, indeed . Second, if the algorithm does not fully explore the hypothesis set , then is still a working upper bound as far as generalization from in-sample to out-of-sample is concerned. Third, the analysis fixes before the data set is presented, and is done independently of the probability distribution , i.e., the same bound applies regardless of which is the true distribution.

In some cases, we can find a better (read: smaller) upper bound, such as in regularization which will be studied later in the course.
__________________
Where everyone thinks alike, no one thinks very much
#3
01-15-2013, 08:59 AM
 Haowen Member Join Date: Jan 2013 Posts: 24
Re: M=|H|? (Lecture 2 slide 16-17)

Thank you Professor for your reply. It makes sense now. I think trying to consider the space of hypothesis "actually explored" is not that useful, as you said, the space of possible hypothesis is independent of and and the resultant bound is a much more general and useful characterization of the learning model.

 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 01:04 PM.

 Contact Us - LFD Book - Top

Powered by vBulletin® Version 3.8.3
Copyright ©2000 - 2020, 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.