Backpropagating Steady State Solvers

[jpfairbanks]

@lukem12345 pointed out that we can solve steady state problems with a backpropagation algorithm. One wrinkle is that we need to handle spans in the compute graph as below.

if the decapode has this pattern

a <-A- x -B->y

but

A\a != B\y

how do you set x during backward pass?

you can formulate

[a] = [A][x]
[b] = [B]

and solve it with:

[A;B][a;b]