A Lyapunov Condition for Training ODEs

Anonymous

Keywords: Control, Machine Learning, Dynamical Systems, Ordinary Differential Equations, ODE, Lyapunov, Stability

Abstract: Control theory is widely used in the study of differential equations to obtain desired behavior from underlying dynamics. We propose a novel method for training ordinary differential equations by using a control-theoretic Lyapunov Condition for stability. This method avoids rolling-out ODE's during training and thus saves the cost of back propagating through a solver or using the adjoint method. We validate our approach experimentally and verify that it has similar performance to ODEs trained by backpropagating through rollouts.

Publication Status: This work is unpublished.