Papers › Mirror and Preconditioned Gradient Descent in Wasserstein Space

Mirror and Preconditioned Gradient Descent in Wasserstein Space

13 Jun 2024arXiv:2406.08938archive 2025-07-28

Clément Bonet, Théo Uscidda, Adam David, Pierre-Cyril Aubin-Frankowski, Anna Korba

As the problem of minimizing functionals on the Wasserstein space encompasses many applications in machine learning, different optimization algorithms on ℝᵈ have received their counterpart analog on the Wasserstein space. We focus here on lifting two explicit algorithms: mirror descent and preconditioned gradient descent. These algorithms have been introduced to better capture the geometry of the function to minimize and are provably convergent under appropriate (namely relative) smoothness and convexity conditions. Adapting these notions to the Wasserstein space, we prove guarantees of convergence of some Wasserstein-gradient-based discrete-time schemes for new pairings of objective functionals and regularizers. The difficulty here is to carefully select along which curves the functionals should be smooth and convex. We illustrate the advantages of adapting the geometry induced by the regularizer on ill-conditioned optimization tasks, and showcase the improvement of choosing different discrepancies and geometries in a computational biology task of aligning single-cells.

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 15 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 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: 15 samples from 1 repository, 13 ran (12 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

clbonet/Mirror_and_Preconditioned_Gradient_Descent_in_Wasserstein_Space officialmentioned on GitHubjaxSyntology: 15 samples, 13 ran (1 instrument-failed) · 2 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: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

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

Licence: 15 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 clbonet/Mirror_and_Preconditioned_Gradient_Descent_in_Wasserstein_Space. “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.

clbonet/Mirror_and_Preconditioned_Gradient_Descent_in_Wasserstein_Space official repository 15 samples, 13 ran (1 instrument-failed) · 2 unverified
ent lib_jax/estimator_entropy.py ran · honoured contract no licence file found · pointer only · 4ca1c4e3be0976ac · report fixture: signature X:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-24
fill_diagonal lib_jax/estimator_entropy.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 061339e08118d70f · report fixture: signature arr:ArrayImpl/2/float, val:float/0/float · returned ArrayImpl · level recorded 2026-09-24
fwd_solver lib_jax/gd.py ran no licence file found · pointer only · c5cb4bbca6ccc429 · report fixture: signature f:callable/0/?, z_init:ArrayImpl/1/float · returned ArrayImpl · level recorded 2026-09-24
gaussian_kernel in 51 papers
census: 9 implementations from 9 papers, 9 distinct outputs across 6 buckets, one shared input per bucket
lib_jax/mmdf.py ran no licence file found · pointer only · de0ddc485474c498 · report fixture: signature x:ArrayImpl/2/float, y:ArrayImpl/2/float, h:float/0/float · returned ArrayImpl · level recorded 2026-09-24
gen_matrix_with_eigs xps_Gaussians/xp_gaussian.py ran · violated contract fingerprinted no licence file found · pointer only · 08da1440ea25282e · report fixture: signature eigs:list/1/float · returned ndarray · level recorded 2026-09-24
get_potential lib_jax/swf.py ran · honoured contract fingerprinted no licence file found · pointer only · 4bb4069f124b6f5f · report fixture: signature x_proj:ArrayImpl/2/float, target_proj:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-24
gradient_descent lib_jax/gd.py ran no licence file found · pointer only · 3aa3ac0cc5796225 · report fixture: signature target_grad:callable/0/?, n_epochs:int/0/int, lr:float/0/float, n_particles:int/0/int, d:int/0/int, preconditioner:callable/0/?, x0:ndarray/2/float, scale_grad:float/0/float · returned tuple · level recorded 2026-09-24
imq_kernel lib_jax/mmdf.py ran no licence file found · pointer only · f37dfdac0d4f70ee · report fixture: signature x:ArrayImpl/2/float, y:ArrayImpl/2/float, c:float/0/float · returned ArrayImpl · level recorded 2026-09-24
kl_divergence in 86 papers
census: 18 implementations from 18 papers, 15 distinct outputs across 7 buckets, one shared input per bucket
xps_Gaussians/xp_gaussian.py ran no licence file found · pointer only · 969166020ca100c0 · report fixture: signature mu1:ndarray/1/float, mu2:ndarray/1/float, sigma_1:ndarray/2/float, sigma_2:ndarray/2/float · returned ndarray · level recorded 2026-09-24
laplace_kernel in 5 papers lib_jax/mmdf.py ran no licence file found · pointer only · 52ff60389b3a2228 · report fixture: signature x:ArrayImpl/2/float, y:ArrayImpl/2/float, h:float/0/float · returned ArrayImpl · level recorded 2026-09-24
mirror_descent_entropy lib_jax/mirror_gaussians.py ran no licence file found · pointer only · b81bc59373b998ed · report fixture: signature n_epochs:int/0/int, lr:float/0/float, d:int/0/int, Sigma_opt_inv:ndarray/2/float, Sigma0:NoneType/0/?, bar:bool/0/bool · returned list · level recorded 2026-09-24
plot_trajectory lib_jax/utils_plot.py ran no licence file found · pointer only · 6e4b6e8722e3b41d · report fixture: signature particles:ndarray/3/float, colorbar:bool/0/bool, ax:Axes/0/?, fig:Figure/0/?, log:bool/0/bool, ts:ndarray/1/float · returned LineCollection · level recorded 2026-09-24
target_grad_sw lib_jax/swf.py ran no licence file found · pointer only · 5520a0a9dbc6a754 · report fixture: signature x:ArrayImpl/2/float, sampler_src:SimpleSampler/0/?, n_projs:int/0/int · returned ArrayImpl · level recorded 2026-09-24
forward_backward in 5 papers lib_jax/mirror_gaussians.py unverified no licence file found · pointer only · becb8047c46a5257 · report
mirror_descent_kl lib_jax/mirror_gaussians.py unverified no licence file found · pointer only · fbc6d7665e4fc746 · report

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