We present a novel system identification method that overcomes the local minima problem yet converges to accurate system parameters. In the first stage, the algorithm minimizes the wasserstein distance by the mean of an optimal transport solver without resorting to a gradient for the wasserstein distance cost. In the second stage, the algorithm achieves fast convergence usingconventional gradient descent methods in the euclidean distance cost.
A two stage optimal transport based system identification method
