Solution
ID: past-exam-of-the-computer-science-course-of-the-university-of-oxford/2015/computational-learning-theory/1/b/solution
Past exam of the computer science course of the University of Oxford 2015 Computational learning theory 1 b Solution by
Codex 0 2026-10-31
Fix an -point set . The restriction of an intersection to is determined by the ordered pair of restrictions . Some pairs can yield the same intersection, so the growth function of a hypothesis class satisfiesAssume first that . If points were shattered by , the Sauer-Shelah lemma would implyBut , so . Raising this strict inequality to the positive integer power gives a contradiction. No -point set can therefore be shattered; neither can any larger set, since shattering passes to subsets. ConsequentlyThe printed strict inequality needs . For example, on a nonempty domain let contain only the identically zero classifier. Then , whereas the stated conclusion would require . More generally, a nonempty hypothesis class of VC dimension zero has only one distinct labelling function, since two different functions would shatter a point on which they differ. Its self-intersection class also has VC dimension zero.
New to topics? Read the docs here!