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 01-26-2015, 11:20 AM
kostya3312 kostya3312 is offline
Junior Member
 
Join Date: Jan 2015
Posts: 2
Default Hoeffding inequality for multiple hypothesis

It's clear for me how inequality works for each hypothesis separately. But I don't understand why we need Hoeffding inequality for multiple hypothesis. If i have training data set of size 'N' then (for fixed tolerance 'e') Hoeffding upper bound is determined for each hypoyhesis. The only thing that remains is to find hypothesis with minimal in-sample rate. Why do we need to consider all hypothesis simultaneously? What information gives us Hoeffding inequality with factor 'M' in it? I undetstand example with coins but I can not relate it to learning problem.

Sorry for my english and thanks.
Reply With Quote
  #2  
Old 01-27-2015, 02:46 PM
magdon's Avatar
magdon magdon is offline
RPI
 
Join Date: Aug 2009
Location: Troy, NY, USA.
Posts: 595
Default Re: Hoeffding inequality for multiple hypothesis

Hoeffding for a single hypothesis h_1 tells you that, with high probability,

|E_{in}(h_1)-E_{out}(h_1)|<\epsilon.

As you point out, "The only thing that remains is to find hypothesis with minimal in-sample rate." Why would one do this? Because one is confident that Ein is close to Eout for every hypothesis, and so if we find the the hypothesis with minimum Ein, it will likely have minimum Eout. So, to be justified in picking the hypothesis with minimum Ein, we require that

\forall h_i, |E_{in}(h_i)-E_{out}(h_i)|\le\epsilon.

Equivalently,

for no h_i, |E_{in}(h_i)-E_{out}(h_i)|>\epsilon.

The factor of M comes from using the union bound

P[for\ no\ h_i, |E_{in}(h_i)-E_{out}(h_i)|>\epsilon]\le P[|E_{in}(h_1)-E_{out}(h_1)|>\epsilon]+P[|E_{in}(h_2)-E_{out}(h_2)|>\epsilon]+\cdots.


Quote:
Originally Posted by kostya3312 View Post
It's clear for me how inequality works for each hypothesis separately. But I don't understand why we need Hoeffding inequality for multiple hypothesis. If i have training data set of size 'N' then (for fixed tolerance 'e') Hoeffding upper bound is determined for each hypoyhesis. The only thing that remains is to find hypothesis with minimal in-sample rate. Why do we need to consider all hypothesis simultaneously? What information gives us Hoeffding inequality with factor 'M' in it? I undetstand example with coins but I can not relate it to learning problem.

Sorry for my english and thanks.
__________________
Have faith in probability
Reply With Quote
  #3  
Old 01-29-2015, 06:18 AM
kostya3312 kostya3312 is offline
Junior Member
 
Join Date: Jan 2015
Posts: 2
Default Re: Hoeffding inequality for multiple hypothesis

Thank you, Professor!

I do not quite understand the following:
Quote:
Originally Posted by magdon View Post
The factor of M comes from using the union bound

P[for\ no\ h_i, |E_{in}(h_i)-E_{out}(h_i)|>\epsilon]\le P[|E_{in}(h_1)-E_{out}(h_1)|>\epsilon]+P[|E_{in}(h_2)-E_{out}(h_2)|>\epsilon]+\cdots.
I thought that the goal is to get the upper bound for probability of event A = [for\ AT\ LEAST\ one\ hypothesis\ |E_{in}-E_{out}|>\epsilon]. That is, for feasibility of learning the probability of this event should be small. In my opinion two events A (mine) and B = [for\ no\ h_i, |E_{in}-E_{out}|>\epsilon] (yours) are different events. Am I right?

My last question is as follows. The LHS of Hoeffding inequality for M hypothesis is P[|E_{in}(g)-E_{out}(g)|>\epsilon]. It implies that event C = |E_{in}(g)-E_{out}(g)|>\epsilon and event A (event B if you are right) are equal. Though I understand the meaning of event A the meaning of event C isn't so clear for me. What it literally means? I think it means [absolute\ difference\ between\ E_{in}\ and\ E_{out}\ for\ final\ hypothesis\ g\ is\ greater\ than\ \epsilon]. Am I right?
Reply With Quote
  #4  
Old 02-19-2015, 10:38 AM
magdon's Avatar
magdon magdon is offline
RPI
 
Join Date: Aug 2009
Location: Troy, NY, USA.
Posts: 595
Default Re: Hoeffding inequality for multiple hypothesis

Sorry, there was a typo in my previous message. Yes they are different events. But they are very related events.



A = [at\ least\ one\ h_i, |E_{in}-E_{out}|>\epsilon]

B = [for\ no\ h_i, |E_{in}-E_{out}|>\epsilon]

P[B]=1-P[A]>=1-M*...

Quote:
Originally Posted by kostya3312 View Post
Thank you, Professor!

I do not quite understand the following:


I thought that the goal is to get the upper bound for probability of event A = [for\ AT\ LEAST\ one\ hypothesis\ |E_{in}-E_{out}|>\epsilon]. That is, for feasibility of learning the probability of this event should be small. In my opinion two events A (mine) and B = [for\ no\ h_i, |E_{in}-E_{out}|>\epsilon] (yours) are different events. Am I right?

My last question is as follows. The LHS of Hoeffding inequality for M hypothesis is P[|E_{in}(g)-E_{out}(g)|>\epsilon]. It implies that event C = |E_{in}(g)-E_{out}(g)|>\epsilon and event A (event B if you are right) are equal. Though I understand the meaning of event A the meaning of event C isn't so clear for me. What it literally means? I think it means [absolute\ difference\ between\ E_{in}\ and\ E_{out}\ for\ final\ hypothesis\ g\ is\ greater\ than\ \epsilon]. Am I right?
__________________
Have faith in probability
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 03:54 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.