Gradient-free training of neural ODEs for system identification and control using ensemble Kalman inversion
This provides a gradient-free alternative for training neural ODEs in control applications, though it appears incremental as it adapts an existing method to a specific domain.
The authors tackled the problem of training neural ODEs for system identification and control by using gradient-free ensemble Kalman inversion (EKI) instead of backpropagation, demonstrating that EKI achieves competitive runtime and solution quality compared to gradient-based optimizers.
Ensemble Kalman inversion (EKI) is a sequential Monte Carlo method used to solve inverse problems within a Bayesian framework. Unlike backpropagation, EKI is a gradient-free optimization method that only necessitates the evaluation of artificial neural networks in forward passes. In this study, we examine the effectiveness of EKI in training neural ordinary differential equations (neural ODEs) for system identification and control tasks. To apply EKI to optimal control problems, we formulate inverse problems that incorporate a Tikhonov-type regularization term. Our numerical results demonstrate that EKI is an efficient method for training neural ODEs in system identification and optimal control problems, with runtime and quality of solutions that are competitive with commonly used gradient-based optimizers.