Papers › Statistical and Geometrical properties of regularized Kernel Kullback-Leibler divergence

Statistical and Geometrical properties of regularized Kernel Kullback-Leibler divergence

29 Aug 2024arXiv:2408.16543archive 2025-07-28

Clémentine Chazal, Anna Korba, Francis Bach

In this paper, we study the statistical and geometrical properties of the Kullback-Leibler divergence with kernel covariance operators (KKL) introduced by Bach [2022]. Unlike the classical Kullback-Leibler (KL) divergence that involves density ratios, the KKL compares probability distributions through covariance operators (embeddings) in a reproducible kernel Hilbert space (RKHS), and compute the Kullback-Leibler quantum divergence. This novel divergence hence shares parallel but different aspects with both the standard Kullback-Leibler between probability distributions and kernel embeddings metrics such as the maximum mean discrepancy. A limitation faced with the original KKL divergence is its inability to be defined for distributions with disjoint supports. To solve this problem, we propose in this paper a regularised variant that guarantees that the divergence is well defined for all distributions. We derive bounds that quantify the deviation of the regularised KKL to the original one, as well as finite-sample bounds. In addition, we provide a closed-form expression for the regularised KKL, specifically applicable when the distributions consist of finite sets of points, which makes it implementable. Furthermore, we derive a Wasserstein gradient descent scheme of the KKL divergence in the case of discrete distributions, and study empirically its properties to transport a set of points to a target distribution.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2408.16543")

Code

Syntology Ran 22 of 24 code samples harvested from 2 repositories linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · our draft was wrong; 20 ran with no contract checked.

By repository: official repository: 2 samples from 1 repository, 2 ran; found in paper text by Syntology: 22 samples from 1 repository, 20 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

cclementine25/kkl-divergence-gradient-flows officialmentioned in paperpytorch 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

24 samples harvested; 22 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
1ran · our draft was wrong
20ran
2unverified

Licence: 24 of the 24 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; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

KKL cclementine25/kkl-divergence-gradient-flows/Regularized/kkl/divergences.py official repository ran · our draft was wrong no licence file found · pointer only · e1793b3bb6c0a8d0 · report
log_ou_0 cclementine25/kkl-divergence-gradient-flows/Regularized/kkl/divergences.py official repository ran · violated contract fingerprinted no licence file found · pointer only · 9f9fb7836d5b6f54 · report
WGrad_KKL clementinechazal/KKL-divergence-gradient-flows/Regularized/kkl/divergences.py found in paper text by Syntology ran no licence file found · pointer only · ef69d628412393fc · report
dk_gauss clementinechazal/KKL-divergence-gradient-flows/Regularized/kkl/kernels.py found in paper text by Syntology ran no licence file found · pointer only · d2e91a24a5daf9dd · report
dual_kale_objective clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/kale.py found in paper text by Syntology ran no licence file found · pointer only · 39b85c7a59cab838 · report
gaussian clementinechazal/KKL-divergence-gradient-flows/Regularized/kkl/generate_data.py found in paper text by Syntology ran no licence file found · pointer only · 315c972d7076c254 · report
gaussian_kernel clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/kernels.py found in paper text by Syntology ran fingerprinted no licence file found · pointer only · 6fb23c47226c3604 · report
get_logger clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/config.py found in paper text by Syntology ran no licence file found · pointer only · e0d3e1933eb6c0cc · report
get_scale clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/plotting.py found in paper text by Syntology ran no licence file found · pointer only · 36014b23f5783ac2 · report
grad_dual_kale_obj clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/kale.py found in paper text by Syntology ran no licence file found · pointer only · 66fc296b4a9fabc4 · report
gradient_descent clementinechazal/KKL-divergence-gradient-flows/Regularized/kkl/gradient_descent.py found in paper text by Syntology ran no licence file found · pointer only · 085219670cbf19c6 · report
hess_dual_kale_obj clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/kale.py found in paper text by Syntology ran no licence file found · pointer only · 3ea66eb12b5f0390 · report
k_gauss clementinechazal/KKL-divergence-gradient-flows/Regularized/kkl/kernels.py found in paper text by Syntology ran fingerprinted no licence file found · pointer only · 767c90fd9e4d01c4 · report
laplace_kernel clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/kernels.py found in paper text by Syntology ran fingerprinted no licence file found · pointer only · 12a78faf896055fe · report
make_updater clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/plotting.py found in paper text by Syntology ran no licence file found · pointer only · e49ee0157f166546 · report
mixt_gauss clementinechazal/KKL-divergence-gradient-flows/Regularized/kkl/generate_data.py found in paper text by Syntology ran no licence file found · pointer only · b5a158d415e6e554 · report
mmd clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/mmd.py found in paper text by Syntology ran no licence file found · pointer only · 8d45b931b21286e0 · report
mmd_first_variation clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/mmd.py found in paper text by Syntology ran no licence file found · pointer only · bd4ea51ac588e009 · report
mmd_k clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/mmd.py found in paper text by Syntology ran no licence file found · pointer only · 76a106f1c87c70c6 · report
negative_distance_kernel clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/kernels.py found in paper text by Syntology ran fingerprinted no licence file found · pointer only · cbc9020c26136013 · report
rings clementinechazal/KKL-divergence-gradient-flows/Regularized/kkl/generate_data.py found in paper text by Syntology ran no licence file found · pointer only · a8177ee54e95ad4a · report
unadjusted_langevin_algorithm clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/extras.py found in paper text by Syntology ran no licence file found · pointer only · aa565d53d151fdea · report
gradient_flow clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/gradient_flow.py found in paper text by Syntology unverified no licence file found · pointer only · 32b535b80fc71fd8 · report
gradient_flow clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/gradient_flow_2.py found in paper text by Syntology unverified no licence file found · pointer only · 2abe9e31184b219d · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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