Adaptive Feedforward Gradient Estimation in Neural ODEs
This addresses a bottleneck in Neural ODEs for researchers and practitioners by offering a more efficient alternative, though it appears incremental relative to existing methods.
The paper tackled the computational inefficiency of Neural ODEs by introducing an adaptive feedforward gradient estimation method, which eliminates backpropagation and reduces overhead while maintaining accuracy.
Neural Ordinary Differential Equations (Neural ODEs) represent a significant breakthrough in deep learning, promising to bridge the gap between machine learning and the rich theoretical frameworks developed in various mathematical fields over centuries. In this work, we propose a novel approach that leverages adaptive feedforward gradient estimation to improve the efficiency, consistency, and interpretability of Neural ODEs. Our method eliminates the need for backpropagation and the adjoint method, reducing computational overhead and memory usage while maintaining accuracy. The proposed approach has been validated through practical applications, and showed good performance relative to Neural ODEs state of the art methods.