SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.03537 · 2019

Convex-Concave Backtracking for Inertial Bregman Proximal Gradient Algorithms in Non-Convex Optimization

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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, 1 violated it and 3 have no contract verdict; 3 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/1904.03537.json · badge: /api/ran/1904.03537.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-escapes-spurious-stationary-points reimplementation (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
mmahesh/cocain-bpg-phase-retrieval community (classifier label)
classifier basis not recorded on the link
3 ran · 2 no recorded run
FunctionStatusWhere it lives
abs_func Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mmahesh/cocain-bpg-escapes-spurious-stationary-points/my_functions.py
code served (permissive licence) · get_code("6626088330fe48bd")
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 float64, 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 numpy as np

# Construct valid arguments for abs_func
# The function expects:
# - U: array-like with 2 elements [x, y]
# - U1: array-like with 2 elements [x_1, y_1]
# - abs_fun_num: int (default 1)
# - fun_num: int (default 1)

U = np.array([0.5, 0.3])
U1 = np.array([1.2, 0.8])
abs_fun_num = 1
fun_num = 1

ARGS = {
    "U": U,
    "U1": U1,
    "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
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, 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
abs_func Ran
ran on a synthesized input
mmahesh/cocain-bpg-phase-retrieval/my_functions.py
code served (permissive licence) · get_code("87e305c861755b51")
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 dimensions for A, b, U, U1
# A is a list of matrices, b is a vector, U and U1 are vectors
n = 4  # dimension of U
m = 3  # number of matrices in A

# Create A: list of m square matrices of size n x n
A = [np.random.randn(n, n) for _ in range(m)]

# Create b: vector of length m
b = np.random.randn(m)

# Create U: vector of length n
U = np.random.randn(n)

# Create U1: vector of length n (another point for abs_func)
U1 = np.random.randn(n)

# Create lam: regularization parameter (scalar)
lam = 0.1

# Define abs_fun_num and fun_num
abs_fun_num = 1
fun_num = 1

# Construct ARGS dictionary with all parameters
ARGS = {
    'A': A,
    'b': b,
    'U': U,
    'U1': U1,
    '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-phase-retrieval/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
f Ran
ran, violated the contract we drafted
mmahesh/cocain-bpg-escapes-spurious-stationary-points/contour_plot.py
code served (permissive licence) · get_code("075afe4d626a2df1")
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 ndarray, ndim 1, dtype family float, shape (4,) 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 numpy as np

x = np.linspace(-2, 2, 100)
y = np.linspace(-2, 2, 100)

def f(x, y):
    return 0.5 * np.log(1 + 100 * np.abs(x - 1) ** 2) + 0.5 * np.log(1 + 100 * np.abs(y - 1) ** 2) + np.log(1 + np.abs(x)) + np.log(1 + np.abs(y))

# Create small numpy arrays for x and y parameters
x_arg = np.array([0.5, 1.5, -0.5, 2.0])
y_arg = np.array([0.5, 1.5, -0.5, 2.0])

ARGS = {
    'x': x_arg,
    'y': y_arg
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (4,) 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
grad Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mmahesh/cocain-bpg-escapes-spurious-stationary-points/my_functions.py
code served (permissive licence) · get_code("64e23227316b67fc")
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 ndarray, ndim 1, dtype family float, shape (2,) 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 numpy as np

# The function takes U (a 2-element array-like) and fun_num (int)
# U[0] and U[1] are accessed and used in arithmetic operations
# They should be numeric values (scalars or arrays)

# Create a simple 2-element numpy array as U
U = np.array([0.5, 1.5])

# fun_num is an integer parameter, defaulting to 1
fun_num = 1

ARGS = {
    "U": U,
    "fun_num": fun_num
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) 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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mmahesh/cocain-bpg-escapes-spurious-stationary-points/my_functions.py
code served (permissive licence) · get_code("a698f4aa932f4fd7")
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 float64, 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 numpy as np

# Construct U as a list/array with two elements [x, y]
# The function accesses U[0] and U[1], so we need at least 2 elements
U = np.array([0.5, 1.5])

ARGS = {
    "U": U,
    "fun_num": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 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-phase-retrieval/my_functions.py
code served (permissive licence) · get_code("7825fe0e0cc46f78")
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 ndarray, ndim 2, dtype family float, shape (1, 1) 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 numpy as np

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

# Define dimensions with distinct sizes
n_features = 4  # dimension of U
n_matrices = 2  # number of matrices in A
matrix_dim = 3  # dimension of each matrix in A

# Create U: a column vector of shape (n_features, 1)
U = np.random.randn(n_features, 1)

# Create A: a list of square matrices, each of shape (matrix_dim, matrix_dim)
# We need U.T.dot(item.dot(U)) to work, so:
# U is (n_features, 1)
# item.dot(U) gives (matrix_dim, 1) - item should be (matrix_dim, n_features)
# U.T.dot(...) gives scalar - U.T is (1, n_features)
# Actually, let's reconsider: if U is (n_features, 1), then U.T is (1, n_features)
# For U.T.dot(item.dot(U)) to work:
# - item.dot(U) must give a vector of length n_features
# - So item should be (n_features, n_features)
# - Then U.T (shape 1, n_features) dot (n_features, 1) gives scalar

A = [np.random.randn(n_features, n_features) for _ in range(n_matrices)]

# Create b: a list of scalars (one for each matrix in A)
b = np.random.randn(n_matrices)

# Create lambda (regularization parameter)
lam = 0.1

ARGS = {
    'A': A,
    'b': b,
    'U': U,
    'lam': lam,
    'fun_num': 1
}
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 ndarray, ndim 2, dtype family float, shape (1, 1) — shape (1, 1) 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
grad Not yet run
unverified (harvested, no recorded run)
mmahesh/cocain-bpg-phase-retrieval/my_functions.py
code served (permissive licence) · get_code("1b20d466ab5027ec")
How it ran

no invocation recorded.

makeup_for_plot Not yet run
unverified (harvested, no recorded run)
mmahesh/cocain-bpg-phase-retrieval/create_plots.py
code served (permissive licence) · get_code("a4a5a170457994fe")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 7 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 later
1905.09050 (2019-05)
Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms
makeup_for_plot 1 other paper
1 later
1905.09050 (2019-05)
Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms

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

Backtracking line-search is an old yet powerful strategy for finding a better step sizes to be used in proximal gradient algorithms. The main principle is to locally find a simple convex upper bound of the objective function, which in turn controls the step size that is used. In case of inertial proximal gradient algorithms, the situation becomes much more difficult and usually leads to very restrictive rules on the extrapolation parameter. In this paper, we show that the extrapolation parameter can be controlled by locally finding also a simple concave lower bound of the objective function. This gives rise to a double convex-concave backtracking procedure which allows for an adaptive choice of both the step size and extrapolation parameters. We apply this procedure to the class of inertial Bregman proximal gradient methods, and prove that any sequence generated by these algorithms converges globally to a critical point of the function at hand. Numerical experiments on a number of challenging non-convex problems in image processing and machine learning were conducted and show the power of combining inertial step and double backtracking strategy in achieving improved performances.

For agents

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

get_harvested_code_for_paper("1904.03537")
get_code_for_paper("1904.03537")
have("1904.03537")

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

curl https://syntology.ai/api/ran/1904.03537.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.03537.svg)](https://syntology.ai/paper/1904.03537)

Connect an agent — have() is free.