LFD Book Forum  

Go Back   LFD Book Forum > Book Feedback - Learning From Data > Chapter 1 - The Learning Problem

Reply
 
Thread Tools Display Modes
  #1  
Old 05-29-2016, 02:23 AM
henry2015 henry2015 is offline
Member
 
Join Date: Aug 2015
Posts: 29
Default Exercise 1.12

Hi,

I thought I could only provide what Hoeffding Inequality's guarantee to my friend.

Ein(g) could be very bad (says 0.5) as my hypothesis set could be bad and so I can only pick g which has smallest Ein(h). And so I can only promise that P[|Eout(g)-Ein(g)| < e] has an upper bound by Hoeffding Inequality...

No?
Reply With Quote
  #2  
Old 07-26-2016, 11:02 AM
jeffjackson jeffjackson is offline
Junior Member
 
Join Date: Jun 2016
Posts: 5
Default Re: Exercise 1.12

This is related to my Chapter 1 post about Section 1.3 being fundamentally flawed. You're correct, henry2015: You cannot promise any of the given answers (a) through (c) to Exercise 1.12.

What you can promise is this:

(d) With high probability, you will either produce a hypothesis g that approximates f well out of sample, or you will declare that you have failed.

You can promise this because Hoeffding guarantees that Ein will be close to Eout with high probability. So, with high probability, you will either produce a good-approximating g (Ein is small) or you will declare that you have failed (Ein is large).

Although (d) is similar to the textbook's answer (c), there is an important distinction: (c) promises that almost every time you output a hypothesis g, g is a good approximator to f. (d) does not make any such promise. In fact, (d) allows that it might be the case the every time you output a hypothesis, it is a poor approximator. What (d) does promise is that, if you are in such a learning scenario, you will normally declare that you have failed rather than outputting a poor hypothesis.
Reply With Quote
  #3  
Old 08-01-2016, 10:08 AM
magdon's Avatar
magdon magdon is offline
RPI
 
Join Date: Aug 2009
Location: Troy, NY, USA.
Posts: 592
Default Re: Exercise 1.12

You are right. Part (c) should be reworded to say:

With high probability: you will either say you failed or you will produce a good g.
__________________
Have faith in probability
Reply With Quote
  #4  
Old 08-02-2016, 01:33 PM
jeffjackson jeffjackson is offline
Junior Member
 
Join Date: Jun 2016
Posts: 5
Default Re: Exercise 1.12

Following up on my earlier reply: In my thread regarding Section 1.3 I have presented an argument for the feasibility of learning that, if accepted, allows us to promise something a good bit stronger than what I offered earlier, which was based only on Hoeffding. The stronger promise is this:
(e) Assuming that you are given sufficient data and/or allowed a sufficiently large error so that the Hoeffding probability \delta is ultra low, such as 10^{-15}, you will either produce a hypothesis g that approximates f well out of sample, or you will declare that you have failed.
Put another way, given my argument for feasible learning and given the \delta assumption above, I can in good conscience promise that whenever I produce a hypothesis, it is a good approximation to the target. That is, it is reasonable for me to promise that I will never output a poor-approximating hypothesis.
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 07:42 AM.


Powered by vBulletin® Version 3.8.3
Copyright ©2000 - 2017, 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.