Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE

Juntang Zhuang, Nicha C. Dvornek, Xiaoxiao Li, Sekhar Tatikonda, Xenophon Papademetris, James S. Duncan

Abstract: The empirical performance of neural ordinary differential equations (NODEs) is significantly inferior to discrete-layer models on benchmark tasks (e.g. image classification). We demonstrate an expl...