Papers › Distance-Based Tree-Sliced Wasserstein Distance

Distance-Based Tree-Sliced Wasserstein Distance

14 Mar 2025arXiv:2503.11050archive 2025-07-28

Hoang V. Tran, Khoi N. M. Nguyen, Trang Pham, Thanh T. Chu, Tam Le, Tan M. Nguyen

To overcome computational challenges of Optimal Transport (OT), several variants of Sliced Wasserstein (SW) has been developed in the literature. These approaches exploit the closed-form expression of the univariate OT by projecting measures onto (one-dimensional) lines. However, projecting measures onto low-dimensional spaces can lead to a loss of topological information. Tree-Sliced Wasserstein distance on Systems of Lines (TSW-SL) has emerged as a promising alternative that replaces these lines with a more advanced structure called tree systems. The tree structures enhance the ability to capture topological information of the metric while preserving computational efficiency. However, at the core of TSW-SL, the splitting maps, which serve as the mechanism for pushing forward measures onto tree systems, focus solely on the position of the measure supports while disregarding the projecting domains. Moreover, the specific splitting map used in TSW-SL leads to a metric that is not invariant under Euclidean transformations, a typically expected property for OT on Euclidean space. In this work, we propose a novel class of splitting maps that generalizes the existing one studied in TSW-SL enabling the use of all positional information from input measures, resulting in a novel Distance-based Tree-Sliced Wasserstein (Db-TSW) distance. In addition, we introduce a simple tree sampling process better suited for Db-TSW, leading to an efficient GPU-friendly implementation for tree systems, similar to the original SW. We also provide a comprehensive theoretical analysis of proposed class of splitting maps to verify the injectivity of the corresponding Radon Transform, and demonstrate that Db-TSW is an Euclidean invariant metric. We empirically show that Db-TSW significantly improves accuracy compared to recent SW variants while maintaining low computational cost via a wide range of experiments.

PaperPDFCodeCode 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 19 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 2 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 15 ran (14 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.

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. 2 of the 15 samples that ran have no recorded date.

Fsoft-AIC/DbTSW officialpytorchApache-2.0Syntology: 19 samples, 15 ran (1 instrument-failed) · 4 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

19 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 2 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 4 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.

2ran · violated contract
1ran · our draft was wrong
12ran
4unverified

Licence: 4 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Fsoft-AIC/DbTSW. “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.

Fsoft-AIC/DbTSW official repository 19 samples, 15 ran (1 instrument-failed) · 4 unverified
W2_1d experiments/gradient-flow/core/SWGG.py ran fingerprinted Apache-2.0 (permissive) · 10853de1303723dd · report fixture: signature X_line_sort:Tensor/2/float, Y_line_sort:Tensor/2/float · returned Tensor · level recorded 2026-09-26
calculate_frechet_distance in 119 papers experiments/denoising-diffusion-gan/pytorch_fid/fid_score.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · fcdc92d3d2e8edc1 · report fixture: signature mu1:ndarray/1/float, sigma1:ndarray/2/float, mu2:ndarray/1/float, sigma2:ndarray/2/float, eps:float/0/float · returned float64 · level recorded 2026-09-25
compute_Wasserstein experiments/gradient-flow/core/gradient_flow.py ran Apache-2.0 (permissive) · df383ed042cd440b · report fixture: signature M:Tensor/2/float, device:str/0/str, e:int/0/int · returned Tensor · level recorded 2026-09-24
compute_true_Wasserstein experiments/gradient-flow/core/gradient_flow.py ran fingerprinted Apache-2.0 (permissive) · 56c0afd58960e460 · report fixture: signature X:Tensor/2/float, Y:Tensor/2/float, p:int/0/int · returned float · level recorded 2026-09-24
extract in 149 papers
census: 9 implementations from 12 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
experiments/denoising-diffusion-gan/train_ddgan.py ran Apache-2.0 (permissive) · dbaf06f6ab72167f · report fixture: signature input:Tensor/2/float, t:Tensor/2/int, shape:tuple/1/int · returned Tensor · level recorded 2026-09-24
generate_trees_frames db_tsw/utils.py ran Apache-2.0 (permissive) · 44a9a491a88a84ec · report fixture: signature ntrees:int/0/int, nlines:int/0/int, d:int/0/int, mean:int/0/int, std:float/0/float, device:str/0/str, gen_mode:str/0/str · returned tuple · level recorded 2026-09-24
make_blobs_random experiments/gradient-flow/core/generate_data.py ran Apache-2.0 (permissive) · 0c49eeb3efa10d5b · report fixture: signature n_samples:int/0/int, n_blobs:int/0/int, scale:float/0/float, offset:int/0/int · returned ndarray · level recorded 2026-09-26
make_blobs_reg experiments/gradient-flow/core/generate_data.py ran Apache-2.0 (permissive) · 281c672a91d898db · report fixture: signature n_samples:int/0/int, n_blobs:int/0/int, scale:float/0/float · returned ndarray · level recorded 2026-09-26
make_spiral experiments/gradient-flow/core/generate_data.py ran fingerprinted Apache-2.0 (permissive) · e6859576298167fd · report fixture: signature n_samples:int/0/int, noise:float/0/float · returned ndarray · level recorded 2026-09-26
preds2score in 5 papers experiments/denoising-diffusion-gan/pytorch_fid/inception_score.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · a32f853e4b62793c · report fixture: signature preds:ndarray/2/float, splits:int/0/int · returned tuple · level recorded 2026-09-22
str2bool in 533 papers experiments/gradient-flow/cfg.py ran · violated contract Apache-2.0 (permissive) · f017532fc389cbfe · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
svd_orthogonalize db_tsw/utils.py ran fingerprinted Apache-2.0 (permissive) · a23adc90085cc7b7 · report fixture: signature matrix:Tensor/2/float · returned Tensor · level recorded 2026-09-24
temperature experiments/gradient-flow/core/Simulated_Annealing.py ran Apache-2.0 (permissive) · 56963d39c9de6af6 · report fixture: signature n_iter:int/0/int, T_0:float/0/float · returned list · level recorded 2026-09-26
var_func_geometric in 8 papers experiments/denoising-diffusion-gan/train_ddgan.py ran · violated contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 65846ba5525a01b5 · report fixture: signature t:float/0/float, beta_min:float/0/float, beta_max:float/0/float · returned float · level recorded, date not recorded
var_func_vp in 8 papers experiments/denoising-diffusion-gan/train_ddgan.py ran Apache-2.0 (permissive) · 37f4a211c7f3b70a · report fixture: signature t:Tensor/1/float, beta_min:Tensor/0/float, beta_max:Tensor/0/float · returned Tensor · level recorded 2026-09-24
W2_proj experiments/gradient-flow/core/SWGG.py unverified Apache-2.0 (permissive) · 805b00de71cd788c · report
calculate_activation_statistics in 75 papers experiments/denoising-diffusion-gan/pytorch_fid/fid_score.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · bd88683e6bd4454d · report
compute_bary_line experiments/gradient-flow/core/SWGG.py unverified Apache-2.0 (permissive) · 5803c476aaa8df6b · report
get_activations in 100 papers experiments/denoising-diffusion-gan/pytorch_fid/fid_score.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 26edbd4467e04bec · report

Tasks

Computational Efficiency

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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