SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.16543 · NeurIPS · 2024

Statistical and Geometrical Properties of Regularized Kernel Kullback-Leibler Divergence

Anna Korba, Francis Bach, Clémentine Chazal

arXiv · PDF · Open in the Atlas

Code that ran

22 of 24 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 4 violated it and 0 have no contract verdict; 15 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2408.16543.json · badge: /api/ran/2408.16543.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
clementinechazal/KKL-divergence-gradient-flows canonical (classifier label)
classifier basis: census
20 ran · 2 no recorded run
cclementine25/kkl-divergence-gradient-flows marked official in Papers with Code
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
KKL Ran
ran; our contract draft was wrong, not the code
cclementine25/kkl-divergence-gradient-flows/Regularized/kkl/divergences.py
pointer only (licence: NONE) · get_code("e1793b3bb6c0a8d0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cclementine25/kkl-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

WGrad_KKL Ran
ran; our contract draft was wrong, not the code
clementinechazal/KKL-divergence-gradient-flows/Regularized/kkl/divergences.py
pointer only (licence: NONE) · get_code("ef69d628412393fc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

dk_gauss Ran
ran, honoured the contract we drafted
clementinechazal/KKL-divergence-gradient-flows/Regularized/kkl/kernels.py
pointer only (licence: NONE) · get_code("d2e91a24a5daf9dd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

dual_kale_objective Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/kale.py
pointer only (licence: NONE) · get_code("39b85c7a59cab838")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gaussian Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
clementinechazal/KKL-divergence-gradient-flows/Regularized/kkl/generate_data.py
pointer only (licence: NONE) · get_code("315c972d7076c254")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gaussian_kernel Ran
ran, violated the contract we drafted
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/kernels.py
pointer only (licence: NONE) · get_code("6fb23c47226c3604")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_logger Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/config.py
pointer only (licence: NONE) · get_code("e0d3e1933eb6c0cc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_scale Ran
ran; our contract draft was wrong, not the code
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/plotting.py
pointer only (licence: NONE) · get_code("36014b23f5783ac2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

grad_dual_kale_obj Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/kale.py
pointer only (licence: NONE) · get_code("66fc296b4a9fabc4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gradient_descent Ran
ran; our contract draft was wrong, not the code
clementinechazal/KKL-divergence-gradient-flows/Regularized/kkl/gradient_descent.py
pointer only (licence: NONE) · get_code("085219670cbf19c6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

hess_dual_kale_obj Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/kale.py
pointer only (licence: NONE) · get_code("3ea66eb12b5f0390")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

k_gauss Ran
ran, honoured the contract we drafted
clementinechazal/KKL-divergence-gradient-flows/Regularized/kkl/kernels.py
pointer only (licence: NONE) · get_code("767c90fd9e4d01c4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

laplace_kernel Ran
ran, violated the contract we drafted
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/kernels.py
pointer only (licence: NONE) · get_code("12a78faf896055fe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

log_ou_0 Ran
ran, violated the contract we drafted
cclementine25/kkl-divergence-gradient-flows/Regularized/kkl/divergences.py
pointer only (licence: NONE) · get_code("9f9fb7836d5b6f54")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cclementine25/kkl-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_updater Ran
ran; our contract draft was wrong, not the code
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/plotting.py
pointer only (licence: NONE) · get_code("e49ee0157f166546")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mixt_gauss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
clementinechazal/KKL-divergence-gradient-flows/Regularized/kkl/generate_data.py
pointer only (licence: NONE) · get_code("b5a158d415e6e554")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mmd Ran
ran; our contract draft was wrong, not the code
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/mmd.py
pointer only (licence: NONE) · get_code("8d45b931b21286e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mmd_first_variation Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/mmd.py
pointer only (licence: NONE) · get_code("bd4ea51ac588e009")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mmd_k Ran
ran; our contract draft was wrong, not the code
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/mmd.py
pointer only (licence: NONE) · get_code("76a106f1c87c70c6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

negative_distance_kernel Ran
ran, violated the contract we drafted
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/kernels.py
pointer only (licence: NONE) · get_code("cbc9020c26136013")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rings Ran
ran, honoured the contract we drafted
clementinechazal/KKL-divergence-gradient-flows/Regularized/kkl/generate_data.py
pointer only (licence: NONE) · get_code("a8177ee54e95ad4a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

unadjusted_langevin_algorithm Ran
ran; our contract draft was wrong, not the code
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/extras.py
pointer only (licence: NONE) · get_code("aa565d53d151fdea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gradient_flow Not yet run
unverified (harvested, no recorded run)
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/gradient_flow.py
pointer only (licence: NONE) · get_code("32b535b80fc71fd8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

gradient_flow Not yet run
unverified (harvested, no recorded run)
clementinechazal/KKL-divergence-gradient-flows/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/gradient_flow_2.py
pointer only (licence: NONE) · get_code("2abe9e31184b219d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clementinechazal/KKL-divergence-gradient-flows when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 23 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 22 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
gradient_flow 1 other paper
1 dated earlier
2106.08929 (2021-06)
KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 regularized variant that guarantees that the divergence is well defined for all distributions. We derive bounds that quantify the deviation of the regularized KKL to the original one, as well as finite-sample bounds. In addition, we provide a closed-form expression for the regularized 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. Recently, Bach [2022] introduced alternative divergences based on quantum divergences evaluated through kernel covariance operators, that we call here a kernel Kullback-Leibler (KKL) divergence. The latter can be seen as second-order embeddings of probability distributions, in contrast with first-order kernel mean embeddings (as used in MMD). In Bach [2022], it was shown that the KKL enjoys nice properties such as separation of measures, and that it is framed between a standard KL divergence (from above) and a smoothed KL divergence (from below), i.e., a KL divergence between smoothed versions of the measures with respect to a specific smoothing kernel. Hence, it cannot directly be identified to a KL divergence and corresponds to a novel and distinct divergence. However, many of its properties remained unexplored, including a complete analysis of the KKL for empirical measures, a tractable closed-form expression and its optimization properties. In this paper, we tackle the previous questions. We propose a regularized version of the KKL that is well-defined for any discrete measures, in contrast with the original KKL. We establish upper bounds that quantify the deviation of the regularized KKL to its unregularized counterpart, and convergence for empirical distributions. Moreover, we derive a tractable closed-form for the regularized KKL and its derivatives that writes with respect to kernel Gram matrices, leading to a practical optimization algorithm. Finally,

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.16543")
get_code_for_paper("2408.16543")
have("2408.16543")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2408.16543.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2408.16543.svg)](https://syntology.ai/paper/2408.16543)

Connect an agent — have() is free.