#21




Re: Discussion of the VC proof
I have also another question on the same page (190):
At the end of the page there is the formula: I don't understand why the RHS is greater or equal to the LHS. The only legitimation I see for this is, that the distribution of P[S] is uniform, but this has not been stated in the text. Or do I oversee here anything and this is also valid for all kinds of distribution? 
#22




Re: Discussion of the VC proof
Quote:
thanks for the answer. I understand this argument, however this holds also for or for Thus the value 1/4 is somehow magic for me. Edit: I think you choose 1/4 because it is so easy to see, that the RHS of Theorem A.1 gets 1. Nevertheless with a different value you would get a different outcome of the final formula. 
#23




Re: Discussion of the VC proof
Quote:
When we have a uniform distribution of P[S] the outcome of the productsum is simply the average of all P[AS], since And an average is of course less than or equal to the maximum of P[AS]. If P[S] is not distributed uniformly we still have an average, but a weighted average. But also here the result is always less than or equal to the maximum. Because you cannot find weighting factors that are in sum 1 but will lead to a higher result as the maximum P[AS]. 
#24




Re: Discussion of the VC proof
Correct.
Quote:
__________________
Have faith in probability 
#25




Re: Discussion of the VC proof
You are correct. We could have made other assumptions.
But there is a special reason why we DO want 1. Because we are bounding the probability, and so there is nothing to prove if we claim that a probability is less equal to 1. So, whenever the RHS (i.e. the bound) evaluates to 1 or bigger, there is nothing to prove. So we only need to consider the case when the bound evaluates to less than 1. Quote:
__________________
Have faith in probability 
#26




Re: Discussion of the VC proof
Thank you very much for your answers. This helps me a lot to understand the intention of the single steps of this prove.

#27




Re: Discussion of the VC proof
i had same question but thanks to your website my question just solved. thanks
__________________
https://seofox.ir 
#28




Re: Discussion of the VC proof
thank you for your answer. i like it.
__________________
[B][CENTER][URL="http://www.sitranet.com/storedesignpackage"]طراحی فروشگاه اینترنتی[/URL] [URL="http://www.sitranet.com/seopack"]سئو فروشگاه اینترنتی[/URL] [url=https://giftus.ir/productcategory/jewelry]زیورآلات[/url][/CENTER][/B] 
#29




Re: Discussion of the VC proof
at the beginning everything was complicated, so at first, I gave it a thought, but I could take in nothing. by the way that was pretty easy. thank you so much.
__________________
delinglish.com 
#30




Re: Discussion of the VC proof
First of all, I just joined this forum recently. The sign up process and asking question for signup was interesting. I am really excited about being in this forum.
I am Sallar Rabiei, (I use ZhaZho for my nickname). I am really interested in smart cities and after graduation urban planning I will follow it. You may read my notes about smart cities, urban sketch, programming, and data in the following URL: Smart Cities Urban Design Sketch for urban designer My Note in Learn WordPress Buy Online in Canada Spanish cheese in Netherlands Second, Thank you very much for the answers. Last edited by zhazho; 01042022 at 05:31 PM. Reason: introduce myself and add references as first post in forum. 
Thread Tools  
Display Modes  

