← Questions
Matrix product scan with autograd and a hand-written backward
0
I was asked this
No reports yet. Sign in to say where you were asked it.
Given a sequence of square matrices, return every prefix product. A first version that updates a buffer in place breaks autograd: say why, and replace it with one that allocates new tensors. Then derive the gradient by hand and code it, and finish with a parallel prefix-scan version of both passes.
No official answer yet. Write yours on the right and run it.
Nothing published yet.
Sign in to submit your code; every attempt is kept here.
Write and test your solution herePython in your browser, the question's tests level by level, every submission kept for you.Sign in to start coding