LFD Book Forum  

Go Back   LFD Book Forum > Course Discussions > Online LFD course > Homework 3

Thread Tools Display Modes
Old 07-30-2012, 10:03 PM
Husnain Husnain is offline
Junior Member
Join Date: Apr 2012
Posts: 3
Default Clarification Needed Q1-3

When we say that the probability of something bad happening (E_{in} deviating from E_{out}) is at most delta, what do we mean?

a) n \leq \frac{1}{2\epsilon^{2}} ln\frac{2M}{\delta}
b) n \geq \frac{1}{2\epsilon^{2}} ln\frac{2M}{\delta}

The derivation from Hoeffding leads to case a) whereby for M = 1 I get [edited out by admin] or something like that as the value of n. Does this mean I have to select the value less than this one i.e. [edited out by admin] or the one above it that is greater than [edited out by admin] ...
Reply With Quote
Old 07-30-2012, 11:08 PM
yaser's Avatar
yaser yaser is offline
Join Date: Aug 2009
Location: Pasadena, California, USA
Posts: 1,478
Default Re: Clarification Needed Q1-3

If N is sufficient, then any number bigger than N is also sufficient.

The question asks what is the least number of examples needed, so among other things, that number would be itself sufficient.

BTW, when you post answers, please have *ANSWER* in the title per the instructions in the top announcement. Thank you.
Where everyone thinks alike, no one thinks very much
Reply With Quote
Old 07-31-2012, 04:47 AM
Husnain Husnain is offline
Junior Member
Join Date: Apr 2012
Posts: 3
Default Re: Clarification Needed Q1-3

Thanks a lot for your reply and I'll definitely take care of the answer issue.
Reply With Quote

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 04:38 PM.

Powered by vBulletin® Version 3.8.3
Copyright ©2000 - 2021, 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.