Computing the Jacobian of the solution of an optimization problem is a central problem in machine learning, with applications in hyperparameter optimization, meta-learning, optimization as a layer, and dataset distillation, to name a few.

MPC has the closest discrepancy to the given non-optimal demonstrations (e.g., when the task loss is

Given this perspective, we consider the more flexible class of iterative amortized optimizers.

We propose a fully differentiable architecture for simultaneous semantic and instance segmentation (a.k.a.