Faster Training of Neural ODEs Using Gauß-Legendre Quadrature
This addresses a bottleneck in training neural ODEs for generative and time-series modeling, offering an incremental improvement over existing methods.
The paper tackles the slow training of neural ODEs by proposing the use of Gauß-Legendre quadrature to speed up the adjoint method, resulting in faster training, especially for large models, and extends this to SDE-based models via the Wong-Zakai theorem.
Neural ODEs demonstrate strong performance in generative and time-series modelling. However, training them via the adjoint method is slow compared to discrete models due to the requirement of numerically solving ODEs. To speed neural ODEs up, a common approach is to regularise the solutions. However, this approach may affect the expressivity of the model; when the trajectory itself matters, this is particularly important. In this paper, we propose an alternative way to speed up the training of neural ODEs. The key idea is to speed up the adjoint method by using Gauß-Legendre quadrature to solve integrals faster than ODE-based methods while remaining memory efficient. We also extend the idea to training SDEs using the Wong-Zakai theorem, by training a corresponding ODE and transferring the parameters. Our approach leads to faster training of neural ODEs, especially for large models. It also presents a new way to train SDE-based models.