[leezard87]

For (a), if you set the break point to k*=dvc+1 for each hypothesis, it's obvious that dvc<k*. Then the upper bound of dvc for the union hypothesis set H is Kk*, meaning dvc < Kk*=K(dvc+1). This is my solution. I'm not 100% sure though.

For (c), I have the same confusion as you. I tried to simplify that inequality for a couple of hours and got nothing closer to the result. Hope someone could shed some light...