Given a support vector machine trained on m examples what is

Given a support vector machine trained on m examples, what is an upper bound on its leave-one-out cross validation error given that it has a) m support vectors b) m/2 support vectors.

Solution

leave one out cross validation error <= number of support vectors/n

Therefore, for a) m support vectors,

leave one out cross validation error <= m/m = 1

b) m/2 support vectors,

leave one out cross validation error <= (m/2)/m = 0.5