Pith. sign in

REVIEW 1 cited by

Augmented Neural ODEs

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1904.01681 v3 pith:ONHACXNG submitted 2019-04-02 stat.ML cs.LG

Emilien Dupont , Arnaud Doucet , Yee Whye Teh This is my paper · ORCID
classification stat.MLcs.LG
keywords neuralodesaugmentedadditionaddressbettercannotcomputational
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We show that Neural Ordinary Differential Equations (ODEs) learn representations that preserve the topology of the input space and prove that this implies the existence of functions Neural ODEs cannot represent. To address these limitations, we introduce Augmented Neural ODEs which, in addition to being more expressive models, are empirically more stable, generalize better and have a lower computational cost than Neural ODEs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Adjoint sharding for very long context training of state space models

    cs.LG 2025-01 reject novelty 5.0 of 10

    The paper derives an adjoint-based gradient sharding algorithm for SSMs and claims up to 3X memory reduction, but provides no experimental evidence for the central empirical claims.

Pith tools