#1




equation 2.13 on page 57
I've been reading the book in parallel with watching the lectures. I think that equation 2.13 on page 57 is wrong or perhaps just misleading. The expression right before equation 2.13 is of the form
N >= const * ln(m(2N)) for fixed eps and delta. Then equation 2.10, m(N) <= 1+N^d_vc, is used to rewrite the expression as equation 2.13, N >= const * ln(1+(2N)^d_vc) But all we can really say from these two expressions is N >= const * ln(m(2N)) <= const * ln(1+(2N)^d_vc) In other words, I don't see how I can know the sign of the inequality "?" in N ? const * ln(1+(2N)^d_vc) What am I missing This seems an important thing, so please help me see my error.... 
Tags 
sample size, vc dimension 
Thread Tools  
Display Modes  

