Papers › Soft-DTW: a Differentiable Loss Function for Time-Series

Soft-DTW: a Differentiable Loss Function for Time-Series

5 Mar 2017ICML 2017 8arXiv:1703.01541archive 2025-07-28

Marco Cuturi, Mathieu Blondel

We propose in this paper a differentiable learning loss between time series, building upon the celebrated dynamic time warping (DTW) discrepancy. Unlike the Euclidean distance, DTW can compare time series of variable size and is robust to shifts or dilatations across the time dimension. To compute DTW, one typically solves a minimal-cost alignment problem between two time series using dynamic programming. Our work takes advantage of a smoothed formulation of DTW, called soft-DTW, that computes the soft-minimum of all alignment costs. We show in this paper that soft-DTW is a differentiable loss function, and that both its value and gradient can be computed with quadratic time/space complexity (DTW has quadratic time but linear space complexity). We show that this regularization is particularly well suited to average and cluster time series under the DTW geometry, a task for which our proposal significantly outperforms existing baselines. Next, we propose to tune the parameters of a machine that outputs time series by minimizing its fit with ground-truth labels in a soft-DTW sense.

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 11 code samples harvested from 5 repositories linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 9 samples from 4 repositories, 3 ran (2 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 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mblondel/soft-dtw officialmentioned in papermentioned on GitHubBSD-2-ClauseSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
Maghoumi/DeepNAG mentioned on GitHubpytorchMITSyntology: 3 samples, 0 ran · 3 unverified report
PeteWe/ts_similarity_tensorflow mentioned on GitHubtfSyntology: not harvested report
baggepinnen/DynamicAxisWarping.jl mentioned on GitHubNOASSERTIONSyntology: not harvested report
jihyeonseong/SoM-TP mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learnable Dynamic Temporal Pooling for Time Series Classification (arXiv:2104.02577; that paper's own run record: 9 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
keonlee9420/Soft-DTW-Loss mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
khdlr/softdtw_jax mentioned on GitHubjaxMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
lyprince/sdtw_pytorch mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
yueyaog/TSGEM_Clustering mentioned on GitHubGPL-3.0Syntology: not harvested 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

11 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 7 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; the contract check could not run
3ran
7unverified

Licence: 3 of the 11 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. “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. 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.

mblondel/soft-dtw official repository 2 samples, 1 ran (0 instrument-failed) · 1 unverified
delannoy_num sdtw/path.py ran fingerprinted BSD-2-Clause (permissive) · 4f2a86831e92d61e · report fixture: signature m:int/0/int, n:int/0/int · returned float64 · level recorded 2026-09-25
load_ucr sdtw/dataset.py unverified BSD-2-Clause (permissive) · 57a33bcae3c2374a · report
Maghoumi/DeepNAG community (archive-listed) 3 samples, 0 ran · 3 unverified
dist_func_cos models/hausdorff_distance.py unverified MIT (permissive) · c542e2fb148a11f8 · report
masked_max models/hausdorff_distance.py unverified MIT (permissive) · 8f1d21b59b848f46 · report
keonlee9420/Soft-DTW-Loss community (archive-listed) 1 sample, 0 ran · 1 unverified
jacobean_product_squared_euclidean sdtw_cuda_loss.py unverified MIT (permissive) · 2331123dca3def2c · report
khdlr/softdtw_jax community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
distance_matrix softdtw_jax/softdtw_jax.py ran MIT (permissive) · f6de6e2b30a06bf5 · report fixture: returned ArrayImpl · level recorded 2026-09-26
pad_inf softdtw_jax/softdtw_jax.py ran MIT (permissive) · 05bf33cfc4c9c7cf · report fixture: signature inp:ArrayImpl/2/float, before:int/0/int, after:int/0/int · returned ArrayImpl · level recorded 2026-09-26
lyprince/sdtw_pytorch community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
sakoe_chiba_band sdtw.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted no licence file found · pointer only · e1ffef61f9ff62a7 · report fixture: signature i_list:list/1/int, j_list:list/1/int, m:int/0/int, n:int/0/int, bandwidth:int/0/int · returned tuple · level recorded 2026-09-22
jacobean_product_squared_euclidean sdtw.py unverified no licence file found · pointer only · 1d66eaff37129b6a · report
softmin sdtw.py unverified no licence file found · pointer only · 3f0b3faa4c343689 · report

Tasks

Dynamic Time WarpingTime SeriesTime Series Analysis

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DTW

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