Papers › Neural Controlled Differential Equations for Irregular Time Series

Neural Controlled Differential Equations for Irregular Time Series

18 May 2020NeurIPS 2020 12arXiv:2005.08926archive 2025-07-28

Patrick Kidger, James Morrill, James Foster, Terry Lyons

Neural ordinary differential equations are an attractive option for modelling temporal dynamics. However, a fundamental issue is that the solution to an ordinary differential equation is determined by its initial condition, and there is no mechanism for adjusting the trajectory based on subsequent observations. Here, we demonstrate how this may be resolved through the well-understood mathematics of controlled differential equations. The resulting neural controlled differential equation model is directly applicable to the general setting of partially-observed irregularly-sampled multivariate time series, and (unlike previous work on this problem) it may utilise memory-efficient adjoint-based backpropagation even across observations. We demonstrate that our model achieves state-of-the-art performance against similar (ODE or RNN based) models in empirical studies on a range of datasets. Finally we provide theoretical results demonstrating universal approximation, and that our model subsumes alternative ODE models.

PaperPDFConference PDFCodeCode Syntology ran

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.

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

Code

Syntology 20 code samples harvested from 5 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 13 samples from 3 repositories, 5 ran (4 with no instrument failure; 1 where Syntology's instrument failed); found in paper text by Syntology: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 9 samples that ran have no recorded date.

patrick-kidger/NeuralCDE officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 3 ran (0 instrument-failed) · 3 unverified report
dungxibo123/NeuralCDE mentioned on GitHubpytorchApache-2.0Syntology: 5 samples, 2 ran (0 instrument-failed) · 3 unverified report
google-research/torchsde mentioned on GitHubpytorchSyntology: 4 samples, 2 ran (1 instrument-failed) · 2 unverified report
patrick-kidger/FasterNeuralDiffEq mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to "Hey, that's not an ODE": Faster ODE Adjoints via Seminorms (arXiv:2009.09457; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
philipdarke/torchtime mentioned on GitHubpytorchMITSyntology: 4 samples, 1 ran (0 instrument-failed) · 3 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

20 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 11 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 · violated contract
1ran · our draft was wrong
1ran; the contract check could not run
6ran
11unverified

Licence: 2 of the 20 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 5 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. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another 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”. “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.

patrick-kidger/NeuralCDE official repository 6 samples, 3 ran (0 instrument-failed) · 3 unverified
cheap_stack controldiffeq/misc.py ran Apache-2.0 (permissive) · f3fd7f081ad2b0ac · report fixture: signature tensors:list/1/Tensor, dim:int/0/int · returned Tensor · level recorded 2026-09-25
dataloader in 23 papers experiments/datasets/common.py ran Apache-2.0 (permissive) · 3d00ef924475de36 · report fixture: signature dataset:SimpleDataset/0/? · returned DataLoader · level recorded 2026-09-25
tridiagonal_solve controldiffeq/misc.py ran Apache-2.0 (permissive) · bd529c79265ef41b · report fixture: signature b:Tensor/2/float, A_upper:Tensor/2/float, A_diagonal:Tensor/2/float, A_lower:Tensor/2/float · returned Tensor · level recorded 2026-09-25
natural_cubic_spline_coeffs controldiffeq/interpolate.py unverified Apache-2.0 (permissive) · 9ecdee7c3249e7c8 · report
normalise_data experiments/datasets/common.py unverified Apache-2.0 (permissive) · b9dfe82fa3003be5 · report
split_data in 68 papers experiments/datasets/common.py unverified Apache-2.0 (permissive) · 39ae76dc29320765 · report
dungxibo123/NeuralCDE community (archive-listed) 5 samples, 2 ran (0 instrument-failed) · 3 unverified
cdeint controldiffeq/cdeint_module.py ran Apache-2.0 (permissive) · a4dafc84cbeb2bb5 · report fixture: signature dX_dt:callable/0/?, z0:Tensor/2/float, func:callable/0/?, t:Tensor/1/float, adjoint:bool/0/bool · returned Tensor · level recorded 2026-09-24
dataloader in 23 papers experiments/datasets/common.py ran Apache-2.0 (permissive) · 3588c9b656c72587 · report fixture: signature dataset:SimpleDataset/0/? · returned DataLoader · level recorded 2026-09-24
GRU_ODE experiments/models/vector_fields.py unverified Apache-2.0 (permissive) · 95c5d0ccacb5efc4 · report
normalise_data experiments/datasets/common.py unverified Apache-2.0 (permissive) · aceed8741052218d · report
split_data in 68 papers experiments/datasets/common.py unverified Apache-2.0 (permissive) · a5ee2b2e1aa03e18 · report
google-research/torchsde community (archive-listed) 4 samples, 2 ran (1 instrument-failed) · 2 unverified
parse_return torchsde/_core/sdeint.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic Apache-2.0 (permissive) · bd70944e548b69cd · report fixture: signature y0:Tensor/2/float, ys:Tensor/3/float, extra_solver_state:dict/0/?, extra:bool/0/bool, logqp:bool/0/bool · returned tuple · level recorded, date not recorded
str2bool in 533 papers examples/latent_sde.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · violated contract licence of this copy not recorded · 6a904c09f82ab220 · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
check_contract torchsde/_core/sdeint.py unverified Apache-2.0 (permissive) · e6f3ab1566910024 · report
evaluate_loss in 8 papers examples/sde_gan.py unverified Apache-2.0 (permissive) · ff96c7be4662524f · report
philipdarke/torchtime community (archive-listed) 4 samples, 1 ran (0 instrument-failed) · 3 unverified
forward_impute src/torchtime/impute.py ran MIT (permissive) · 13f770aeadd69af7 · report fixture: signature input:Tensor/3/float, fill:Tensor/1/float, select:Tensor/1/int · returned Tensor · level recorded 2026-09-24
packed_sequence src/torchtime/collate.py unverified MIT (permissive) · d01650eee408e749 · report
replace_missing src/torchtime/impute.py unverified MIT (permissive) · a1971b5815c2fc7a · report
sort_by_length src/torchtime/collate.py unverified MIT (permissive) · 9828f771a54b575c · report
patrick-kidger/torchcde found in paper text by Syntology 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_data in 223 papers example/time_series_classification.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · 582d465aad5dd543 · report fixture: signature num_timepoints:int/0/int · returned tuple · level recorded, date not recorded

Tasks

Irregular Time SeriesTime SeriesTime Series Analysis

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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