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 ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

Syntology holds a reference implementation of optimal transport and stability regularizations, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='optimal transport and stability regularizations') (how to connect); the free check have('2002.02798') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 15 samples from 2 repositories, 12 ran (10 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 12 samples that ran have no recorded date.

D-hash-code/ffjord-rnode-finalweek-mnist mentioned on GitHubpytorchMITSyntology: 14 samples, 11 ran (2 instrument-failed) · 3 unverified report
cfinlay/ffjord-rnode mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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: 12 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
2ran · our draft was wrong
9ran
3unverified

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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

D-hash-code/ffjord-rnode-finalweek-mnist community (archive-listed) 14 samples, 11 ran (2 instrument-failed) · 3 unverified
build_net in 13 papers lib/layers/coupling.py ran MIT (permissive) · 1bfb103fe91e335d · report fixture: signature input_dim:int/0/int, hidden_dims:list/1/int, activation:str/0/str · returned Sequential · level recorded 2026-09-24
count_parameters in 278 papers train_misc.py ran · honoured contract MIT (permissive) · f6b944f50d3f15ae · report fixture: signature model:callable/0/? · returned int · level recorded, date not recorded
get_logger in 383 papers lib/utils.py ran · our draft was wrong MIT (permissive) · 416b44e8cb9fc048 · report fixture: signature logpath:str/0/str, filepath:str/0/str, package_files:list/1/str, displaying:bool/0/bool, saving:bool/0/bool, debug:bool/0/bool · returned RootLogger · level recorded 2026-09-22
isnan in 24 papers
census: 3 implementations from 8 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
lib/utils.py ran MIT (permissive) · 005ab5343cd3459c · report fixture: signature tensor:Tensor/1/float · returned Tensor · level recorded 2026-09-25
logsumexp in 55 papers
census: 8 implementations from 12 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
lib/utils.py ran MIT (permissive) · bc02f37ed2da5d95 · report fixture: signature value:Tensor/2/float, dim:int/0/int, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-24
reduce_tensor in 32 papers
census: 5 implementations from 6 papers, 3 distinct outputs on one shared input
dist_utils.py ran MIT (permissive) · be51985b302891b6 · report fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-24
sample_mask in 39 papers
census: 4 implementations from 5 papers, 4 distinct outputs on one shared input
lib/layers/coupling.py ran MIT (permissive) · 3a7bef4c55086f50 · report fixture: signature dim:int/0/int, mask_type:str/0/str, swap:bool/0/bool · returned Tensor · level recorded 2026-09-24
shift in 22 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
trainCNFGAN.py ran fingerprinted MIT (permissive) · eff72070f790a5fe · report fixture: signature x:Tensor/2/float, nbits:int/0/int · returned Tensor · level recorded 2026-09-24
standard_normal_logprob in 14 papers train_misc.py ran · our draft was wrong fingerprinted MIT (permissive) · 2dc23e3f121c6a38 · report fixture: signature z:Tensor/2/float · returned Tensor · level recorded, date not recorded
sum_tensor in 8 papers dist_utils.py ran MIT (permissive) · 0009ce40d4f5ff19 · report fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-24
unshift trainCNFGAN.py ran fingerprinted MIT (permissive) · 4df0e0f1164421a1 · report fixture: signature x:Tensor/2/float, nbits:int/0/int · returned Tensor · level recorded 2026-09-24
get_data_loader in 44 papers lib/utils2.py unverified MIT (permissive) · 58bb14039809fdf3 · report
cfinlay/ffjord-rnode community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
RegularizedODEfunc lib/layers/wrappers/cnf_regularization.py ran fingerprinted MIT (permissive) · 2a06912ee47c2847 · report fixture: returned RegularizedODEfunc · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for optimal transport and stability regularizations (graph method: optimal transport and stability regularizations), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. rnode_loss_contribution entry · level 3 · ran · honoured contract · 156ac4189c74a96f7aa78e48d0f002bc064b41d8c8f5f8cffb79025581692b86

harvested Assembly for optimal transport and stability regularizations (graph method: optimal transport and stability regularizations). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. RegularizedODEfunc entry · level 1 · ran · 2a06912ee47c2847

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2002.02798") returns these assemblies with each brick's role and wiring (how to connect).

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