SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1710.05050 · 2017

Learning Independent Features with Adversarial Nets for Non-linear ICA

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 3 have no contract verdict; 0 failures of our instrument; 1 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/1710.05050.json · badge: /api/ran/1710.05050.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
pbrakel/anica canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
get_data Ran
ran on a synthesized input
pbrakel/anica/datasets/synthetic.py
code served (permissive licence) · get_code("fdca466e9c315a50")
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

ARGS = {
    'seed': 101,
    'mix_dim': 6,
    'task_type': 'linear',
    'samples': 4000,
}
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
plot_signals Ran
ran on a synthesized input
pbrakel/anica/utils.py
code served (permissive licence) · get_code("c34b95406621e6ec")
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 module. 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
import matplotlib.pyplot as plt

# Create mock plotting object
pl = plt

# Create sample signal data
# x should be a list/array of n signals, each with some time steps
n = 5
signal_length = 100

x = [np.random.randn(signal_length) for _ in range(n)]
y = [np.random.randn(signal_length) for _ in range(n)]

ARGS = {
    'pl': pl,
    'x': x,
    'y': y,
    'n': n
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type module — a module output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a module 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
plot_signals_single Ran
ran on a synthesized input
pbrakel/anica/utils.py
code served (permissive licence) · get_code("2d1e73fba1e8806c")
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 MockPlotter. 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
import matplotlib.pyplot as plt

# Create a mock plotting object that has the methods used in plot_signals_single
class MockPlotter:
    def __init__(self):
        self.fig, self.axes_list = plt.subplots()
        self.current_ax = None
    
    def subplot(self, nrows, ncols, index):
        # Simplified subplot that just tracks state
        self.current_ax = plt.subplot(nrows, ncols, index)
        return self
    
    def plot(self, data, color='black'):
        if self.current_ax is None:
            plt.plot(data, color=color)
        else:
            self.current_ax.plot(data, color=color)
        return self
    
    def gca(self):
        return plt.gca()

# Create sample signal data: 3 signals, each with 10 time steps
x = np.array([
    [1.0, 2.0, 1.5, 3.0, 2.5, 1.8, 2.2, 3.5, 2.8, 1.9],
    [0.5, 1.2, 0.8, 1.5, 0.9, 1.1, 1.3, 0.7, 1.4, 0.6],
    [-1.0, 0.5, -0.5, 1.0, 0.0, -0.8, 0.3, 1.2, -0.2, 0.9]
], dtype=np.float32)

pl = MockPlotter()

ARGS = {
    'pl': pl,
    'x': x,
    'rescale': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MockPlotter — a MockPlotter output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockPlotter 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
lognormdens Not yet run
unverified (harvested, no recorded run)
pbrakel/anica/utils.py
code served (permissive licence) · get_code("f876a3ab920edc12")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Reliable measures of statistical dependence could be useful tools for learning independent features and performing tasks like source separation using Independent Component Analysis (ICA). Unfortunately, many of such measures, like the mutual information, are hard to estimate and optimize directly. We propose to learn independent features with adversarial objectives which optimize such measures implicitly. These objectives compare samples from the joint distribution and the product of the marginals without the need to compute any probability densities. We also propose two methods for obtaining samples from the product of the marginals using either a simple resampling trick or a separate parametric distribution. Our experiments show that this strategy can easily be applied to different types of model architectures and solve both linear and non-linear ICA problems.

For agents

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

get_harvested_code_for_paper("1710.05050")
get_code_for_paper("1710.05050")
have("1710.05050")

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

curl https://syntology.ai/api/ran/1710.05050.json

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

[![Syntology run record](https://syntology.ai/api/ran/1710.05050.svg)](https://syntology.ai/paper/1710.05050)

Connect an agent — have() is free.