Re: Example 2.2 (.3)  sample randomness
The discussion of #dichotomies focuses on what the "worst" number of dichotomies is. Then, when data is sampled (as Hoeffding needs), the number of dichotomies would be no more than the worst case (as discussed with the growth functions). If we can manage to bound the growth functions, we can also bound the "actual # of dichotomies when data is sampled."
Hope this helps.
__________________
When one teaches, two learn.
