Control Disturbance Rejection in Neural ODEs
This work addresses robustness issues in Neural ODEs for applications involving control systems, but it is incremental as it builds on prior work with a key modification.
The paper tackles the problem of making Neural ODEs resilient to control disturbances by proposing an iterative training algorithm that solves a minimax problem over an infinite-dimensional control space, resulting in models that effectively learn new data and gain robustness.
In this paper, we propose an iterative training algorithm for Neural ODEs that provides models resilient to control (parameter) disturbances. The method builds on our earlier work Tuning without Forgetting-and similarly introduces training points sequentially, and updates the parameters on new data within the space of parameters that do not decrease performance on the previously learned training points-with the key difference that, inspired by the concept of flat minima, we solve a minimax problem for a non-convex non-concave functional over an infinite-dimensional control space. We develop a projected gradient descent algorithm on the space of parameters that admits the structure of an infinite-dimensional Banach subspace. We show through simulations that this formulation enables the model to effectively learn new data points and gain robustness against control disturbance.