Thread: Question 2
View Single Post
Old 04-13-2013, 01:12 AM
Ziad Hatahet Ziad Hatahet is offline
Join Date: Apr 2013
Location: San Francisco, CA
Posts: 23
Default Re: Question 2

Originally Posted by yaser View Post
What makes a hypothesis 'not fixed' is that we have a bunch of bins and we select a bin according to the sample it produced (e.g., an all green sample). The reason we call the hypothesis not fixed in this case is because which bin we pick (hence which colors are inside, hence which hypothesis we are talking about) depends on the samples that have already been produced.
That is what we do when we sift through the bins (hypotheses) looking for an h whose sample we got minimizes E_{in}. But given the quote in my first post, doesn't it mean that the bin chosen by this procedure is not bound by 2e^{-2\epsilon^2N}?
Reply With Quote