SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.05833 · 2023

Bregman-Wasserstein divergence: geometry and applications

arXiv · PDF · Open in the Atlas

Code that ran

4 of 8 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; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 failures of our instrument; 4 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/2302.05833.json · badge: /api/ran/2302.05833.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
amanjitsk/bregman-wasserstein canonical (classifier label)
classifier basis not recorded on the link
4 ran · 4 no recorded run
FunctionStatusWhere it lives
custom_grad Ran
ran on a synthesized input
amanjitsk/bregman-wasserstein/math_utils.py
code served (permissive licence) · get_code("bcf8e486c0fed151")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned custom_jvp. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import jax
import jax.numpy as jnp
import numpy as np

# Define a simple potential function (e.g., quadratic)
def potential_func(x):
    """A simple potential: sum of squares"""
    return jnp.sum(x ** 2)

# Define the gradient map
def gradient_map(x):
    """Gradient of the potential: 2*x"""
    return 2 * x

# Create small test inputs
x_test = jnp.array([1.0, 2.0, 3.0, 4.0])

ARGS = {
    "f": potential_func,
    "f_grad": gradient_map,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax, jaxtyping, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type custom_jvp — a custom_jvp output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a custom_jvp output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
custom_warning Ran
ran on a synthesized input
amanjitsk/bregman-wasserstein/plot_utils.py
code served (permissive licence) · get_code("c89864abe4c054a0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import warnings

ARGS = {
    'message': 'This is a test warning message',
    'category': UserWarning,
    'filename': '/path/to/test_module.py',
    'lineno': 42,
    'file': None,
    'line': None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
format_axes Ran
ran on a synthesized input
amanjitsk/bregman-wasserstein/plot_utils.py
code served (permissive licence) · get_code("d9aff414f861e9bd")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Axes. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import matplotlib.pyplot as plt
import matplotlib as mpl

# Create a figure and axis
fig, ax = plt.subplots()

# Plot some dummy data so the axis has content
ax.plot([1, 2, 3], [1, 2, 3], label='test line')

# Define arguments for format_axes
ARGS = {
    'ax': ax,
    'title': 'Test Title',
    'xlabel': 'X Axis',
    'ylabel': 'Y Axis',
    'xticks': [1, 2, 3],
    'yticks': [1, 2, 3],
    'xlim': (0, 4),
    'ylim': (0, 4),
    'leg_loc': 'upper left',
    'leg_title': 'Legend',
    'leg_kwargs': {'frameon': True, 'fontsize': 10},
    'nbins': 5,
    'grid': True,
    'visible_spines': 'lb',
    'xlabel_kwargs': {'fontsize': 12},
    'ylabel_kwargs': {'fontsize': 12},
    'spine_placement': ('axes', 0.5),
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Axes — a Axes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Axes output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
multiple_formatter Ran
ran on a synthesized input
amanjitsk/bregman-wasserstein/plot_utils.py
code served (permissive licence) · get_code("1d1e5bce94699b59")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    'denominator': 2,
    'number': np.pi,
    'latex': '\\pi'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
make_baseline Not yet run
unverified (harvested, no recorded run)
amanjitsk/bregman-wasserstein/data.py
code served (permissive licence) · get_code("5c1dc2af2676b04f")
How it ran

no invocation recorded.

make_samplers Not yet run
unverified (harvested, no recorded run)
amanjitsk/bregman-wasserstein/data.py
code served (permissive licence) · get_code("7dcfa9c84a6f8af7")
How it ran

no invocation recorded.

make_separable Not yet run
unverified (harvested, no recorded run)
amanjitsk/bregman-wasserstein/math_utils.py
code served (permissive licence) · get_code("a15c5e27e79eec16")
How it ran

no invocation recorded.

wrap_potentials Not yet run
unverified (harvested, no recorded run)
amanjitsk/bregman-wasserstein/math_utils.py
code served (permissive licence) · get_code("e4d079f85a78691e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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.

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

The Bregman-Wasserstein divergence is the optimal transport cost when the underlying cost function is given by a Bregman divergence, and arises naturally in fields such as statistics and machine learning. We establish fundamental properties of the Bregman-Wasserstein divergence and propose a novel generalized transport geometry that promotes the Bregman geometry to the space of probability distributions. We provide a probabilistic interpretation involving exponential families and define generalized displacement interpolations compatible with the Bregman geometry. These interpolations are used to derive a generalized Pythagorean inequality, which is of independent interest. Furthermore, we construct a generalized dualistic geometry that lifts the differential geometry of the Bregman divergence to an infinite-dimensional statistical manifold. On the computational side, we demonstrate how Bregman-Wasserstein optimal transport maps can be estimated using neural approaches, establish the well-posedness of Bregman-Wasserstein barycenters, and relate them to Bayesian learning. Finally, we introduce the Bregman-Wasserstein JKO scheme for discretizing Riemannian Wasserstein gradient flows.

For agents

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

get_harvested_code_for_paper("2302.05833")
get_code_for_paper("2302.05833")
have("2302.05833")

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

curl https://syntology.ai/api/ran/2302.05833.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.05833.svg)](https://syntology.ai/paper/2302.05833)

Connect an agent — have() is free.