Interpolation technique to speed up gradients propagation in neural ODEs

Talgat Daulbaev, Alexandr Katrutsa, Larisa Markeeva, Julia Gusak, Andrzej Cichocki, Ivan Oseledets

Research output: Contribution to journalConference articlepeer-review

4 Citations (Scopus)


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.

Original languageEnglish
JournalAdvances in Neural Information Processing Systems
Publication statusPublished - 2020
Event34th Conference on Neural Information Processing Systems, NeurIPS 2020 - Virtual, Online
Duration: 6 Dec 202012 Dec 2020


Dive into the research topics of 'Interpolation technique to speed up gradients propagation in neural ODEs'. Together they form a unique fingerprint.

Cite this