(Nonlinear) Optimisation as a Network Layer

Small example showing how to use a regression as a layer inside a network.

Might contain some bugs, please also see https://github.com/fzimmermann89/PINQI (after release).

References:

See for example

• Brandon Amos and J Zico Kolter. Optnet: Differentiable optimization as a layer in neural networks.
• Akshay Agrawal, Brandon Amos, Shane Barratt, Stephen Boyd, Steven Diamond, and J Zico Kolter. Differentiable convex optimization layers