English

Efficient, Accurate and Stable Gradients for Neural ODEs

Machine Learning 2025-01-30 v2 Machine Learning

Abstract

Training Neural ODEs requires backpropagating through an ODE solve. The state-of-the-art backpropagation method is recursive checkpointing that balances recomputation with memory cost. Here, we introduce a class of algebraically reversible ODE solvers that significantly improve upon both the time and memory cost of recursive checkpointing. The reversible solvers presented calculate exact gradients, are high-order and numerically stable -- strictly improving on previous reversible architectures.

Keywords

Cite

@article{arxiv.2410.11648,
  title  = {Efficient, Accurate and Stable Gradients for Neural ODEs},
  author = {Sam McCallum and James Foster},
  journal= {arXiv preprint arXiv:2410.11648},
  year   = {2025}
}

Comments

Preprint

R2 v1 2026-06-28T19:22:41.062Z