SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1702.02505 · 2017

Inertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problems

arXiv · PDF · Open in the Atlas

Code that ran

6 of 14 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 6 have no contract verdict; 0 failures of our instrument; 8 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/1702.02505.json · badge: /api/ran/1702.02505.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
VLOGroup/mri-variationalnetwork community (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
VLOGroup/tensorflow-icg community (classifier label)
classifier basis not recorded on the link
1 ran · 7 no recorded run
FunctionStatusWhere it lives
addFEOversampling Ran
ran on a synthesized input
VLOGroup/mri-variationalnetwork/mriutils.py
code served (permissive licence) · get_code("1cadfa4859f5809f")
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 4, dtype family float, shape (2, 3, 16, 16) 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

# Create a small test array with shape that allows FE oversampling
# The function requires the second-to-last dimension to be even and >= 4
# Let's use shape (2, 3, 8, 16) - batch=2, channels=3, height=8, width=16
src = np.random.randn(2, 3, 8, 16).astype(np.float32)

ARGS = {
    "src": src
}
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 4, dtype family float, shape (2, 3, 16, 16) — shape (2, 3, 16, 16) 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
conv2d_complex Ran
ran on a synthesized input
VLOGroup/mri-variationalnetwork/icg/icg_ops.py
code served (permissive licence) · get_code("43af4c5667b5be5f")
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 EagerTensor, ndim 4, dtype family float, shape (2, 4, 3, 5) 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 tensorflow as tf
import numpy as np

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

# Create small complex-valued tensors
# u: input tensor (batch, height, width, channels) in NHWC format
# batch=2, height=4, width=3, channels=2
u_real = tf.constant(np.random.randn(2, 4, 3, 2), dtype=tf.float32)
u_imag = tf.constant(np.random.randn(2, 4, 3, 2), dtype=tf.float32)
u = tf.complex(u_real, u_imag)

# k: kernel tensor (filter_height, filter_width, in_channels, out_channels)
# filter_height=3, filter_width=3, in_channels=2, out_channels=5
k_real = tf.constant(np.random.randn(3, 3, 2, 5), dtype=tf.float32)
k_imag = tf.constant(np.random.randn(3, 3, 2, 5), dtype=tf.float32)
k = tf.complex(k_real, k_imag)

ARGS = {
    'u': u,
    'k': k,
    'strides': [1, 1, 1, 1],
    'padding': 'SAME',
    'data_format': 'NHWC'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 5) 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
ifftc2d Ran
ran on a synthesized input
VLOGroup/mri-variationalnetwork/icg/icg_ops.py
code served (permissive licence) · get_code("a5d6c4d96499d971")
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 EagerTensor, ndim 3, dtype family float, shape (2, 4, 3) 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 tensorflow as tf
import numpy as np

# Create a small complex-valued tensor
# The function operates on the last two axes, so we create a batch of 2D complex arrays
batch_size = 2
height = 4
width = 3

# Create a small complex-valued tensor with shape (batch_size, height, width)
real_part = np.random.randn(batch_size, height, width).astype(np.float32)
imag_part = np.random.randn(batch_size, height, width).astype(np.float32)
complex_array = real_part + 1j * imag_part

# Convert to TensorFlow tensor
inp = tf.constant(complex_array, dtype=tf.complex64)

ARGS = {
    "inp": inp
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) 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
print_model_analysis Ran
ran on a synthesized input
VLOGroup/tensorflow-icg/tensorflow/contrib/tfprof/model_analyzer.py
pointer only (licence: Apache-2.0) · get_code("28351708358d23f0")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, VLOGroup/tensorflow-icg, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

removeFEOversampling Ran
ran on a synthesized input
VLOGroup/mri-variationalnetwork/mriutils.py
code served (permissive licence) · get_code("4d70cea5d19f3e69")
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 (8, 12) 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

# Create a numpy array with at least 2 dimensions
# Using shape (16, 12) where nFE=16, nPE=12 (nPE != nFE, so oversampling will be removed)
src = np.random.randn(16, 12)

ARGS = {
    "src": src
}
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 (8, 12) — shape (8, 12) 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
removePEOversampling Ran
ran on a synthesized input
VLOGroup/mri-variationalnetwork/mriutils.py
code served (permissive licence) · get_code("e715f6193dc3643f")
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 3, dtype family float, shape (2, 4, 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

# Create a small test array with Phase Encoding oversampling
# Shape: (batch, FE, PE) where PE > FE to demonstrate oversampling
# Using distinct sizes: batch=2, FE=4, PE=6 to show the oversampling clearly
src = np.random.randn(2, 4, 6).astype(np.float32)

ARGS = {
    "src": src
}
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 3, dtype family float, shape (2, 4, 4) — shape (2, 4, 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
GenerateModelReport Not yet run
unverified (harvested, no recorded run)
VLOGroup/tensorflow-icg/tensorflow/python/grappler/model_analyzer.py
pointer only (licence: Apache-2.0) · get_code("f336ea79c52000df")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, VLOGroup/tensorflow-icg, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

advise Not yet run
unverified (harvested, no recorded run)
VLOGroup/tensorflow-icg/tensorflow/contrib/tfprof/model_analyzer.py
pointer only (licence: Apache-2.0) · get_code("9c576dde035e4276")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, VLOGroup/tensorflow-icg, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

conv2d_complex Not yet run
unverified (harvested, no recorded run)
VLOGroup/tensorflow-icg/tensorflow/contrib/icg/python/ops/icg_ops.py
pointer only (licence: Apache-2.0) · get_code("38ac9a0d09b9d16b")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, VLOGroup/tensorflow-icg, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

conv2d_transpose_complex Not yet run
unverified (harvested, no recorded run)
VLOGroup/mri-variationalnetwork/icg/icg_ops.py
code served (permissive licence) · get_code("b3dfb2eca32d9150")
How it ran

no invocation recorded.

conv2d_transpose_complex Not yet run
unverified (harvested, no recorded run)
VLOGroup/tensorflow-icg/tensorflow/contrib/icg/python/ops/icg_ops.py
pointer only (licence: Apache-2.0) · get_code("902181c038a90ba9")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, VLOGroup/tensorflow-icg, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

loadYaml Not yet run
unverified (harvested, no recorded run)
VLOGroup/tensorflow-icg/tensorflow/contrib/icg/python/utils.py
pointer only (licence: Apache-2.0) · get_code("6cf59a23aba16bcc")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, VLOGroup/tensorflow-icg, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

loadmat Not yet run
unverified (harvested, no recorded run)
VLOGroup/tensorflow-icg/tensorflow/contrib/icg/python/utils.py
pointer only (licence: Apache-2.0) · get_code("b9e36b98d5a93b31")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, VLOGroup/tensorflow-icg, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

log10 Not yet run
unverified (harvested, no recorded run)
VLOGroup/tensorflow-icg/tensorflow/contrib/icg/python/utils.py
pointer only (licence: Apache-2.0) · get_code("fbe392ab8ebabf38")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, VLOGroup/tensorflow-icg, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 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 14 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

In this paper we study nonconvex and nonsmooth optimization problems with semi-algebraic data, where the variables vector is split into several blocks of variables. The problem consists of one smooth function of the entire variables vector and the sum of nonsmooth functions for each block separately. We analyze an inertial version of the Proximal Alternating Linearized Minimization (PALM) algorithm and prove its global convergence to a critical point of the objective function at hand. We illustrate our theoretical findings by presenting numerical experiments on blind image deconvolution, on sparse non-negative matrix factorization and on dictionary learning, which demonstrate the viability and effectiveness of the proposed method.

For agents

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

get_harvested_code_for_paper("1702.02505")
get_code_for_paper("1702.02505")
have("1702.02505")

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

curl https://syntology.ai/api/ran/1702.02505.json

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

[![Syntology run record](https://syntology.ai/api/ran/1702.02505.svg)](https://syntology.ai/paper/1702.02505)

Connect an agent — have() is free.