Despite being non-convex, deep neural networks are surprisingly amenable to optimization by gradient descent. In this note, we use a deep neural network with parameters to parametrize the input space of a generic -dimensional non-convex optimization problem. Our experiments show that minimizing the over-parametrized variables provided by the deep neural network eases and accelerates the optimization of various non-convex test functions.
Live content is unavailable. Log in and register to view live content