Papers › How to train your neural ODE: the world of Jacobian and kinetic regularization

How to train your neural ODE: the world of Jacobian and kinetic regularization

7 Feb 2020ICML 2020 1arXiv:2002.02798archive 2025-07-28

Chris Finlay, Jörn-Henrik Jacobsen, Levon Nurbekyan, Adam M. Oberman

Training neural ODEs on large datasets has not been tractable due to the necessity of allowing the adaptive numerical ODE solver to refine its step size to very small values. In practice this leads to dynamics equivalent to many hundreds or even thousands of layers. In this paper, we overcome this apparent difficulty by introducing a theoretically-grounded combination of both optimal transport and stability regularizations which encourage neural ODEs to prefer simpler dynamics out of all the dynamics that solve a problem well. Simpler dynamics lead to faster convergence and to fewer discretizations of the solver, considerably decreasing wall-clock time without loss in performance. Our approach allows us to train neural ODE-based generative models to the same performance as the unregularized dynamics, with significant reductions in training time. This brings neural ODEs closer to practical relevance in large-scale applications.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2002.02798")

Code

Syntology Ran 4 of 15 code samples harvested from 2 repositories linked to this paper; 11 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong; 1 ran with no contract checked.

By repository: community (archive-listed): 15 samples from 2 repositories, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

D-hash-code/ffjord-rnode-finalweek-mnist mentioned on GitHubpytorchMIT report
cfinlay/ffjord-rnode mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested; 4 ran; 1 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
2ran · our draft was wrong
1ran
11unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

RegularizedODEfunc cfinlay/ffjord-rnode/lib/layers/wrappers/cnf_regularization.py community (archive-listed) ran fingerprinted MIT (permissive) · 2a06912ee47c2847 · report
count_parameters D-hash-code/ffjord-rnode-finalweek-mnist/train_misc.py community (archive-listed) ran · honoured contract MIT (permissive) · f6b944f50d3f15ae · report
get_logger D-hash-code/ffjord-rnode-finalweek-mnist/lib/utils.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 416b44e8cb9fc048 · report
standard_normal_logprob D-hash-code/ffjord-rnode-finalweek-mnist/train_misc.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 2dc23e3f121c6a38 · report
add_noise D-hash-code/ffjord-rnode-finalweek-mnist/trainCNFGAN.py community (archive-listed) unverified MIT (permissive) · 13a2192e17a601cb · report
add_noise D-hash-code/ffjord-rnode-finalweek-mnist/validate.py community (archive-listed) unverified MIT (permissive) · 6e49bcc681db6ead · report
build_net D-hash-code/ffjord-rnode-finalweek-mnist/lib/layers/coupling.py community (archive-listed) unverified MIT (permissive) · 1bfb103fe91e335d · report
get_data_loader D-hash-code/ffjord-rnode-finalweek-mnist/lib/utils2.py community (archive-listed) unverified MIT (permissive) · 58bb14039809fdf3 · report
isnan D-hash-code/ffjord-rnode-finalweek-mnist/lib/utils.py community (archive-listed) unverified MIT (permissive) · 005ab5343cd3459c · report
logsumexp D-hash-code/ffjord-rnode-finalweek-mnist/lib/utils.py community (archive-listed) unverified MIT (permissive) · bc02f37ed2da5d95 · report
reduce_tensor D-hash-code/ffjord-rnode-finalweek-mnist/dist_utils.py community (archive-listed) unverified MIT (permissive) · be51985b302891b6 · report
sample_mask D-hash-code/ffjord-rnode-finalweek-mnist/lib/layers/coupling.py community (archive-listed) unverified MIT (permissive) · 3a7bef4c55086f50 · report
shift D-hash-code/ffjord-rnode-finalweek-mnist/trainCNFGAN.py community (archive-listed) unverified MIT (permissive) · eff72070f790a5fe · report
sum_tensor D-hash-code/ffjord-rnode-finalweek-mnist/dist_utils.py community (archive-listed) unverified MIT (permissive) · 0009ce40d4f5ff19 · report
unshift D-hash-code/ffjord-rnode-finalweek-mnist/trainCNFGAN.py community (archive-listed) unverified MIT (permissive) · 4df0e0f1164421a1 · report

Tasks

Density EstimationImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Density Estimation CIFAR-10 RNODE NLL (bits/dim) 3.38 #11 of 15 Archive leaderboard report
Density Estimation CelebA-HQ 256x256 RNODE Log-likelihood 1.04 #1 of 1 Archive leaderboard report
Density Estimation ImageNet 64x64 RNODE Log-likelihood 3.83 #1 of 1 Archive leaderboard report
Density Estimation MNIST RNODE NLL (bits/dim) 0.97 #2 of 6 Archive leaderboard report
Image Generation CelebA-HQ 256x256 RNODE bits/dimension 1.04 #18 of 19 Archive leaderboard report
Image Generation MNIST RNODE bits/dimension 0.97 #3 of 15 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections