View Single Post
  #4  
Old 04-04-2013, 01:08 PM
yaser's Avatar
yaser yaser is offline
Caltech
 
Join Date: Aug 2009
Location: Pasadena, California, USA
Posts: 1,477
Default Re: Relation between feasibility of learning and Hoeffding's Inequality.

Quote:
Originally Posted by jlaurentum View Post
Thank you very much for your quick response, Professor Yaser. Your course sets the bar for quality in MOOCs very high. You have my respect and gratitude.

At the beginning of minute 32 in the Lecture 2 video, you say "P can be any probability, but the choice of P can affect the value of ...". Is it \mu or \nu? My intuition tells me it should be \nu, because it is a random variable that varies with the sample, whereas \mu is a fixed but unknown parameter. However, I think I'm hearing "mu" mentioned several times in this context. Can you please clarify this point?
Thank you.

P affects the value of \mu (the probability) since it gives different weights to different input points {\bf x} where there is agreement/disagreement with the target. Consequently, it also affects the value of \nu (the random variable) through its impact on \mu.
__________________
Where everyone thinks alike, no one thinks very much
Reply With Quote