1. In this exercise, we show that the (, 6) requirement on the convergence of errors in our definitions of PAC learning, is, in fact, quite close to a sim- pler looking requirement about averages (or expectations). Prove that the following two statements are equivalent (for any learning algorithm A, any probability distribution D, and any loss function whose range is [0, 1]): 1. For every e, 6 > 0, there exists m(c, 6) such that Vm 2 m(6, 6) SAD P LD(A(S)) >