I'm not sure about this. I've been through something like that during the PhD, when I had to do some advanced stuff in Mechanics (finite element analysis), without the proper background. It worked and I learned a lot, but it is different from following the proper undergraduate courses.
My problem with graduate studies is that your mentor always has an agenda (a paper, a prototype, etc) which may compromise his advice (e.g. skipping really important courses/books to save time). Therefore, I'd much rather focus on technical/undergraduate courses, if following any at all.