SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1706.08500 · 2017

GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

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 0 have no contract verdict; 3 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/1706.08500.json · badge: /api/ran/1706.08500.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
bioinf-jku/TTUR canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
hidekifujinami6/gan_evaluation reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
SiskonEmilia/StyleGAN-PyTorch reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
yenchenlin/fid reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
calculate_frechet_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
bioinf-jku/TTUR/fid.py
code served (permissive licence) · get_code("5277c96076ea2fe5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 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

np.random.seed(42)

# Create mean vectors for two distributions
# Using different dimensions to make them distinct
feature_dim = 128

mu1 = np.random.randn(feature_dim)
mu2 = np.random.randn(feature_dim)

# Create covariance matrices (must be positive semi-definite)
# Generate random covariance matrices by A @ A.T method
A1 = np.random.randn(feature_dim, feature_dim)
sigma1 = A1 @ A1.T

A2 = np.random.randn(feature_dim, feature_dim)
sigma2 = A2 @ A2.T

eps = 1e-06

ARGS = {
    'mu1': mu1,
    'sigma1': sigma1,
    'mu2': mu2,
    'sigma2': sigma2,
    'eps': eps
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, scipy — 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
calculate_frechet_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hidekifujinami6/gan_evaluation/fid_score.py
pointer only (licence: NONE) · get_code("80628f7f07bed5a8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hidekifujinami6/gan_evaluation when it was checked. 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.

quick_scale Ran
ran; our contract draft was wrong, not the code
SiskonEmilia/StyleGAN-PyTorch/model.py
code served (permissive licence) · get_code("b919a96235b8ee68")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned SimpleModule. 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 torch
import torch.nn as nn
import math

torch.manual_seed(0)

# Create a simple linear module to test the scaling
# The function expects a module with a 'weight' parameter (or other named parameter)
# The weight needs to have at least 2 dimensions where:
# - dimension 1 is fan_in related
# - dimension 0 contains elements that have .numel()

class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        # Create a weight parameter with shape (out_features, in_features)
        # For a Linear layer-like weight: (3, 4)
        self.weight = nn.Parameter(torch.randn(3, 4))
    
    def forward(self, x):
        return x

module = SimpleModule()

ARGS = {
    'module': module,
    'name': 'weight'
}
Setup block drafted by
a language model, Claude Sonnet 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 SimpleModule — a SimpleModule output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModule 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
get_activations Not yet run
unverified (harvested, no recorded run)
yenchenlin/fid/fid_score.py
code served (permissive licence) · get_code("04254f2109518e2b")
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, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 later) and 1 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
calculate_frechet_distance 74 other papers
1 dated earlier, 73 later
1610.09585 (2016-10)
Conditional Image Synthesis With Auxiliary Classifier GANs
1807.11458 (2018-07)
To learn image super-resolution, use a GAN to learn how to do image degradation first
1812.08985 (2018-12)
Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors
and 71 more not named here
calculate_frechet_distance 15 other papers
2 dated earlier, 13 later
1406.2661 (2014-06)
Generative Adversarial Networks
1703.10593 (2017-03)
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
1802.10551 (2018-02)
A Variational Inequality Perspective on Generative Adversarial Networks
and 12 more not named here
quick_scale 3 other papers
3 later
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
1801.04406 (2018-01)
Which Training Methods for GANs do actually Converge?
1812.04948 (2018-12)
A Style-Based Generator Architecture for Generative Adversarial Networks

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

More are linked than shown here.

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved. We propose a two time-scale update rule (TTUR) for training GANs with stochastic gradient descent on arbitrary GAN loss functions. TTUR has an individual learning rate for both the discriminator and the generator. Using the theory of stochastic approximation, we prove that the TTUR converges under mild assumptions to a stationary local Nash equilibrium. The convergence carries over to the popular Adam optimization, for which we prove that it follows the dynamics of a heavy ball with friction and thus prefers flat minima in the objective landscape. For the evaluation of the performance of GANs at image generation, we introduce the "Fréchet Inception Distance" (FID) which captures the similarity of generated images to real ones better than the Inception Score. In experiments, TTUR improves learning for DCGANs and Improved Wasserstein GANs (WGAN-GP) outperforming conventional GAN training on CelebA, CIFAR-10, SVHN, LSUN Bedrooms, and the One Billion Word Benchmark.

For agents

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

get_harvested_code_for_paper("1706.08500")
get_code_for_paper("1706.08500")
have("1706.08500")

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

curl https://syntology.ai/api/ran/1706.08500.json

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

[![Syntology run record](https://syntology.ai/api/ran/1706.08500.svg)](https://syntology.ai/paper/1706.08500)

Connect an agent — have() is free.