2. [12 marks] Suppose we want to fit a constant model, y = 0, to a dataset 71, 12, . .. , yn- Part I: We choose to use the following loss function: L(yi, 0) - - In(- exp(-13:)) (a). (3 marks) What is the derivative of the average loss R (i.e. empirical risk) for this choice of model and loss function with respect to O? (Hints: exp(x) = ez, In(x) = log.(x), and In(a exp(b)) = In(a) + b). (b). (3 marks) Determine the value of 0 that minimizes average loss for the above choice of model and loss function.LA(m, 0) = 2(m - 0); Lo(m, 0) = 3m-0. Let ox and og be the values of & that minimize average LA loss and average Lg loss, respectively, for the constant model and a given data set. (c). (2 marks) What is the relationship between 84 and dg for the dataset y = [1, 2,3, 4, 5]? (Hint: the answer can be A > On, or A co