SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.09050 · 2019

Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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; 1 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 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/1905.09050.json · badge: /api/ran/1905.09050.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
mmahesh/cocain-bpg-matrix-completion canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
mmahesh/cocain-bpg-matrix-factorization community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
FunctionStatusWhere it lives
abs_func Ran
ran on a synthesized input
mmahesh/cocain-bpg-matrix-factorization/my_functions.py
code served (permissive licence) · get_code("91b70c2f20574c88")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

# Set random seed for reproducibility
np.random.seed(0)

# Define small matrices for the matrix factorization problem
# A is the target matrix (m x n)
m, n = 4, 3
k = 2  # latent dimension

A = np.random.randn(m, n)
U = np.random.randn(m, k)
Z = np.random.randn(k, n)
U1 = np.random.randn(m, k)
Z1 = np.random.randn(k, n)

# Regularization parameter
lam = 0.1

# Function number (determines which objective is used)
fun_num = 1

# Absolute function number (determines which variant is used)
abs_fun_num = 1

ARGS = {
    'A': A,
    'U': U,
    'Z': Z,
    'U1': U1,
    'Z1': Z1,
    'lam': lam,
    'abs_fun_num': abs_fun_num,
    'fun_num': fun_num
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
do_tight_layout_for_fig Ran
ran on a synthesized input
mmahesh/cocain-bpg-matrix-factorization/create_plots.py
code served (permissive licence) · get_code("dfebed255091bcc7")
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 Figure. 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

fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot([1, 2, 3], [1, 2, 3])

ARGS = {
    "fig": fig
}
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 Figure — a Figure output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Figure 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
grad Ran
ran on a synthesized input
mmahesh/cocain-bpg-matrix-factorization/my_functions.py
code served (permissive licence) · get_code("7de0fb631a5ab4ea")
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 tuple. 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

# Create small numpy arrays for matrix operations
# A should be a matrix that represents data (m x n)
A = np.random.randn(3, 4)

# U should be a matrix (m x k) where k is the latent dimension
U = np.random.randn(3, 2)

# Z should be a matrix (k x n)
Z = np.random.randn(2, 4)

# lam is a scalar regularization parameter
lam = 0.01

# fun_num selects which function variant (0, 1, or 2)
fun_num = 1

# option selects which output format (1, 2, or 3)
option = 1

ARGS = {
    "A": A,
    "U": U,
    "Z": Z,
    "lam": lam,
    "fun_num": fun_num,
    "option": option
}
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 tuple — a tuple output has no array shape of its own; none is 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
loss_func1 Ran
ran, honoured the contract we drafted
mmahesh/cocain-bpg-matrix-completion/matrix_completion_pytorch.py
code served (permissive licence) · get_code("cd198438e27f36b2")
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) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple model (the function doesn't actually use it, but it's a parameter)
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()

# Create small tensors for output and target
# batch_size=2, feature_dim=4
output = torch.randn(2, 4)
target = torch.randn(2, 4)

ARGS = {
    "output": output,
    "target": target,
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
main_func Ran
ran on a synthesized input
mmahesh/cocain-bpg-matrix-factorization/my_functions.py
code served (permissive licence) · get_code("200fbb5b8e7f0382")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

# Set random seed for reproducibility
np.random.seed(0)

# Create small test matrices
# A: m x n matrix (the target matrix)
m, n = 4, 3
A = np.random.randn(m, n)

# U: m x k matrix (basis matrix)
k = 2
U = np.random.randn(m, k)

# Z: k x n matrix (coefficient matrix)
Z = np.random.randn(k, n)

# Regularization parameter
lam = 0.1

# Function selector
fun_num = 1

ARGS = {
    "A": A,
    "U": U,
    "Z": Z,
    "lam": lam,
    "fun_num": fun_num
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
makeup_for_plot Not yet run
unverified (harvested, no recorded run)
mmahesh/cocain-bpg-matrix-factorization/create_plots.py
code served (permissive licence) · get_code("a4a5a170457994fe")
How it ran

no invocation recorded.

train_test_split2 Not yet run
unverified (harvested, no recorded run)
mmahesh/cocain-bpg-matrix-completion/create_datasets.py
code served (permissive licence) · get_code("d6dd9c2a3f968978")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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
do_tight_layout_for_fig 1 other paper
1 dated earlier
1904.03537 (2019-04)
Convex-Concave Backtracking for Inertial Bregman Proximal Gradient Algorithms in Non-Convex Optimization
makeup_for_plot 1 other paper
1 dated earlier
1904.03537 (2019-04)
Convex-Concave Backtracking for Inertial Bregman Proximal Gradient Algorithms in Non-Convex Optimization

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

Matrix Factorization is a popular non-convex optimization problem, for which alternating minimization schemes are mostly used. They usually suffer from the major drawback that the solution is biased towards one of the optimization variables. A remedy is non-alternating schemes. However, due to a lack of Lipschitz continuity of the gradient in matrix factorization problems, convergence cannot be guaranteed. A recently developed approach relies on the concept of Bregman distances, which generalizes the standard Euclidean distance. We exploit this theory by proposing a novel Bregman distance for matrix factorization problems, which, at the same time, allows for simple/closed form update steps. Therefore, for non-alternating schemes, such as the recently introduced Bregman Proximal Gradient (BPG) method and an inertial variant Convex--Concave Inertial BPG (CoCaIn BPG), convergence of the whole sequence to a stationary point is proved for Matrix Factorization. In several experiments, we observe a superior performance of our non-alternating schemes in terms of speed and objective value at the limit point.

For agents

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

get_harvested_code_for_paper("1905.09050")
get_code_for_paper("1905.09050")
have("1905.09050")

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

curl https://syntology.ai/api/ran/1905.09050.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.09050.svg)](https://syntology.ai/paper/1905.09050)

Connect an agent — have() is free.