# Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs

arXiv: https://arxiv.org/abs/2003.05271 · HTML: https://mlsanity.com/paper/2003.05271/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2020.

## Built on by (most cited first, 6 of 6)

- [Temporal Knowledge Graph Forecasting with Neural ODE](https://mlsanity.com/paper/2101.05151/) (2021)
- [MALI: A memory efficient and reverse accurate integrator for Neural ODEs](https://mlsanity.com/paper/2102.04668/) (2021)
- [OCT-GAN: Neural ODE-based Conditional Tabular GANs](https://mlsanity.com/paper/2105.14969/) (2021)
- [Meta-Solver for Neural Ordinary Differential Equations](https://mlsanity.com/paper/2103.08561/) (2021)
- [Attention-based Spatial-Temporal Graph Neural ODE for Traffic Prediction](https://mlsanity.com/paper/2305.00985/) (2023)
- [Hierarchical Network Fusion for Multi-Modal Electron Micrograph Representation Learning with Foundational Large Language Models](https://mlsanity.com/paper/2408.13661/) (2024)

## Abstract (arXiv)

We propose a simple interpolation-based method for the efficient approximation of gradients in neural ODE models. We compare it with the reverse dynamic method (known in the literature as "adjoint method") to train neural ODEs on classification, density estimation, and inference approximation tasks. We also propose a theoretical justification of our approach using logarithmic norm formalism. As a result, our method allows faster model training than the reverse dynamic method that was confirmed and validated by extensive numerical experiments for several standard benchmarks.