不用反向传播，用自适应前馈梯度提升神经ODE效率与可解释性。
Adaptive Feedforward Gradient Estimation in Neural ODEs
- 用自适应前馈方式估算梯度，避开传统反向传播和伴随方法。
- 计算开销和内存占用显著降低，精度与现有最优方法相当。
- 适合追求高效训练与模型可解释性的深度学习研究者。
神经常微分方程（Neural ODEs）是深度学习的重要进展，有望连接机器学习与数学领域数百年积累的理论框架。本文提出一种新方法，利用自适应前馈梯度估计，提升 Neural ODE 的效率、一致性与可解释性。该方法无需反向传播和伴随法，显著降低计算开销与内存占用，同时保持高精度。在实际应用中验证了其有效性，性能优于当前 Neural ODE 的主流方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。