Radim, Don't know if you have your answer yet, but you just need some basis, not the best basis. Thus, you can do block-wise decomposition of Y and you nearly have it. You still have to divide by the number of blocks so that Q' Q = I, but other than that, I think you are set.
2010/9/7 RadimRehurek <[email protected]> > But I don't understand the step where you orthonormalize Q: it looks like > you want to do it in blocks of Y, but orth(Y1 ; Y2 ; Y3 ...) != orth(Y1) ; > orth(Y2) ; orth(Y3) ... (the first two equations of sd.pdf). What is the > trick behind that?
