Panos Patrinos
Results
3
comments of
Panos Patrinos
Even better, although you wouldn't be able to use a QP solver for the prox of f(Ax), only dual PANOC (NAMA). But if it is a QP, then we should...
Guys, instead of reinventing the wheel what about letting JuliaDif compute the gradients using AD?
Another thing that is worth checking out: https://github.com/malmaud/TensorFlow.jl