Reviews: Learning Stable Deep Dynamics Models

The paper presents a method for constructing neural network architectures that have build-in theoretical guarantees of Lyapunov stability - meaning that the equilibrium will be in the origin and for any initial condition, the network will produce trajectories that converge to the equilibrium. The method is evaluated on the N-link pendulum and video generation problems. The method's significance comes from two different reasons. First, Lyapunov stability for the system is very difficult to prove with classical methods. Second, deep learning methods are largely empirical, without theoretical guarantees, limiting their applicability for life-critical system.