LFD Book Forum  

Go Back   LFD Book Forum > Course Discussions > Online LFD course > The Final

Reply
 
Thread Tools Display Modes
  #1  
Old 06-07-2012, 11:24 AM
sakumar sakumar is offline
Member
 
Join Date: Apr 2012
Posts: 40
Default Questions on the Bayesian Prior

I asked the TA this during the lecture but I am not sure I understood his answer.

Say in gradient descent (or perceptron) we start with an initial guess for w. Then we proceed to modify w as we process the training data till we get a satisfactory w.

I believe our initial w is not the same as the "Bayesian prior". Why is that? Is it because we are guessing an actual number instead of imposing a probability distribution on the values for w? How would gradient descent change if we modeled w as a Bayesian? In perceptron, when we change w based on a data point that contradicts w's predictions, that is not the same as "conditioning on data"? Why?

Also, somewhat related, I think: Prof Abu-Mostafa explained in the last lecture the second condition where it would be ok to assume a Bayesian Prior. The way I understood it was that if we had enough data points that successive updates would eventually dilute our (perhaps poor estimate of the) original prior, then we're OK? Is my understanding correct? So is that similar to saying our Eout will be low if M is large enough?
Reply With Quote
  #2  
Old 06-07-2012, 11:48 AM
yaser's Avatar
yaser yaser is offline
Caltech
 
Join Date: Aug 2009
Location: Pasadena, California, USA
Posts: 1,477
Default Re: Questions on the Bayesian Prior

Quote:
Originally Posted by sakumar View Post
Say in gradient descent (or perceptron) we start with an initial guess for w. Then we proceed to modify w as we process the training data till we get a satisfactory w.

I believe our initial w is not the same as the "Bayesian prior". Why is that? Is it because we are guessing an actual number instead of imposing a probability distribution on the values for w? How would gradient descent change if we modeled w as a Bayesian? In perceptron, when we change w based on a data point that contradicts w's predictions, that is not the same as "conditioning on data"? Why?
You are correct. The initial {\bf w}(0) is not the same as a prior. It does affect the outcome by preferring one local minimum over another, but that is often mitigated by picking the best of several runs.

If we had a prior, and we used gradient descent to pick the hypothesis with the maximum posterior, it would be working on an augmented error of sorts, part of which comes from the prior and plays the role of a regularizer.

Quote:
Also, somewhat related, I think: Prof Abu-Mostafa explained in the last lecture the second condition where it would be ok to assume a Bayesian Prior. The way I understood it was that if we had enough data points that successive updates would eventually dilute our (perhaps poor estimate of the) original prior, then we're OK? Is my understanding correct? So is that similar to saying our Eout will be low if M is large enough?
Indeed, dilution of the role of the prior is the effect we get when we have sufficient data, but it is not the same as saying that E_{\rm out} is low, as the latter depends on other factors such as noise.
__________________
Where everyone thinks alike, no one thinks very much
Reply With Quote
  #3  
Old 06-07-2012, 01:09 PM
sakumar sakumar is offline
Member
 
Join Date: Apr 2012
Posts: 40
Default Re: Questions on the Bayesian Prior

Thanks for the clarifications, Professor!
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 10:18 PM.


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.