LFD Book Forum (http://book.caltech.edu/bookforum/index.php)
-   Chapter 1 - The Learning Problem (http://book.caltech.edu/bookforum/forumdisplay.php?f=108)
-   -   Hoeffding inequality for multiple hypothesis (http://book.caltech.edu/bookforum/showthread.php?t=4582)

 kostya3312 01-26-2015 11:20 AM

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.

 magdon 01-27-2015 02:46 PM

Re: Hoeffding inequality for multiple hypothesis

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

for no The factor of M comes from using the union bound  Quote:
 Originally Posted by kostya3312 (Post 11910) 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.

 kostya3312 01-29-2015 06:18 AM

Re: Hoeffding inequality for multiple hypothesis

Thank you, Professor!

I do not quite understand the following:
Quote:
 Originally Posted by magdon (Post 11911) The factor of M comes from using the union bound  I thought that the goal is to get the upper bound for probability of event . That is, for feasibility of learning the probability of this event should be small. In my opinion two events (mine) and (yours) are different events. Am I right?

My last question is as follows. The LHS of Hoeffding inequality for M hypothesis is . It implies that event and event (event if you are right) are equal. Though I understand the meaning of event the meaning of event isn't so clear for me. What it literally means? I think it means . Am I right?

 magdon 02-19-2015 10:38 AM

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

Quote:
 Originally Posted by kostya3312 (Post 11916) 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 . That is, for feasibility of learning the probability of this event should be small. In my opinion two events (mine) and (yours) are different events. Am I right? My last question is as follows. The LHS of Hoeffding inequality for M hypothesis is . It implies that event and event (event if you are right) are equal. Though I understand the meaning of event the meaning of event isn't so clear for me. What it literally means? I think it means . Am I right?

 All times are GMT -7. The time now is 11:20 PM.