SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.10588 · 2020

Anomalous diffusion dynamics of learning in deep neural networks

arXiv · PDF · Open in the Atlas

Code that ran

9 of 11 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 5 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/2009.10588.json · badge: /api/ran/2009.10588.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
ifgovh/Anomalous-diffusion-dynamics-of-SGD canonical (classifier label)
classifier basis: census
9 ran · 2 no recorded run
FunctionStatusWhere it lives
alpha_estimator Ran
ran on a synthesized input
ifgovh/Anomalous-diffusion-dynamics-of-SGD/get_gradient_weight/gradient_noise.py
code served (permissive licence) · get_code("a69670bf9807e661")
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 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 numpy as np
import math

torch.manual_seed(0)

# The function takes:
# - m: an integer (divisor for reshaping)
# - X: a tensor that will be reshaped and have operations applied to it

# X needs to have length N that is divisible by m
# X will be reshaped to (n, m, -1) where n = N / m
# X will also have .norm(dim=1) called on it (before reshaping)
# So X should be 2D with shape (N, feature_dim)

m = 2
N = 8  # divisible by m=2, so n=4
feature_dim = 4
X = torch.randn(N, feature_dim)

ARGS = {
    "m": m,
    "X": X,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
get_grads Ran
ran on a synthesized input
ifgovh/Anomalous-diffusion-dynamics-of-SGD/get_gradient_weight/gradient_noise.py
code served (permissive licence) · get_code("81aabb5979983838")
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 Tensor, ndim 1, dtype family float, shape (23,) 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)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

# Create some dummy data and do a forward/backward pass to populate gradients
x = torch.randn(2, 4)
y = torch.randn(2, 2)
output = model(x)
loss = torch.nn.functional.mse_loss(output, y)
loss.backward()

ARGS = {
    'model': model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 1, dtype family float, shape (23,) — shape (23,) 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
get_layerWise_norms Ran
ran on a synthesized input
ifgovh/Anomalous-diffusion-dynamics-of-SGD/get_gradient_weight/gradient_noise.py
code served (permissive licence) · get_code("1e49a19659aab31b")
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, ndim 2, 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 torch
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

# Create a simple network
net = SimpleNet()

# Create some dummy input and perform a forward pass
dummy_input = torch.randn(2, 4)
output = net(dummy_input)

# Create a dummy loss and backward pass to populate gradients
loss = output.sum()
loss.backward()

ARGS = {
    "net": net
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
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
get_random_states Ran
ran; our contract draft was wrong, not the code
ifgovh/Anomalous-diffusion-dynamics-of-SGD/get_gradient_weight/net_plotter.py
pointer only (licence: MIT); the stored copy get_code serves, from runtsang/VFPT, is pointer only (licence: NOASSERTION) · get_code("7ead1a7c9a99873f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from runtsang/VFPT, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

get_random_weights Ran
ran; our contract draft was wrong, not the code
ifgovh/Anomalous-diffusion-dynamics-of-SGD/get_gradient_weight/net_plotter.py
pointer only (licence: MIT); the stored copy get_code serves, from runtsang/VFPT, is pointer only (licence: NOASSERTION) · get_code("3e80953c5e1e0841")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from runtsang/VFPT, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

get_relative_path Ran
ran on a synthesized input
ifgovh/Anomalous-diffusion-dynamics-of-SGD/dataloader.py
code served (permissive licence) · get_code("028de37884922bbd")
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 str. 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 os

# The function get_relative_path takes a single parameter 'file' which is a string
# It uses os.path.dirname(__file__) to get the script directory
# and os.path.join to join it with the file parameter
# So 'file' should be a string representing a file path

ARGS = {
    "file": "example.txt"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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_synthetic_gaussian_data_loaders Ran
ran on a synthesized input
ifgovh/Anomalous-diffusion-dynamics-of-SGD/train_DNN_code/dataloader.py
code served (permissive licence) · get_code("3b068a8f9eb6416e")
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, ndim 1, 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 torch
import torchvision
from torchvision.transforms import functional as F

torch.manual_seed(0)

class MockArgs:
    def __init__(self, batch_size):
        self.batch_size = batch_size

ARGS = {
    "args": MockArgs(batch_size=2)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
get_weights Ran
ran; our contract draft was wrong, not the code
ifgovh/Anomalous-diffusion-dynamics-of-SGD/get_gradient_weight/net_plotter.py
pointer only (licence: MIT); the stored copy get_code serves, from runtsang/VFPT, is pointer only (licence: NOASSERTION) · get_code("5fa87577ccee9cca")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from runtsang/VFPT, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

read_list Ran
ran, honoured the contract we drafted
ifgovh/Anomalous-diffusion-dynamics-of-SGD/get_gradient_weight/h5_util.py
pointer only (licence: MIT); the stored copy get_code serves, from runtsang/VFPT, is pointer only (licence: NOASSERTION) · get_code("0d11ac9cea6805a3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from runtsang/VFPT, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

get_data_loaders Not yet run
unverified (harvested, no recorded run)
ifgovh/Anomalous-diffusion-dynamics-of-SGD/train_DNN_code/dataloader.py
code served (permissive licence) · get_code("191831befedc50f5")
How it ran

no invocation recorded.

load_dataset Not yet run
unverified (harvested, no recorded run)
ifgovh/Anomalous-diffusion-dynamics-of-SGD/dataloader.py
code served (permissive licence) · get_code("c8c8dee0fe2c623e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 5 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 later) and 6 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
get_weights 2 other papers
2 later
2407.07805 (2024-07)
SUMix: Mixup with Semantic and Uncertain Information
2411.01327 (2024-11)
Visual Fourier Prompt Tuning
read_list 2 other papers
2 later
2407.07805 (2024-07)
SUMix: Mixup with Semantic and Uncertain Information
2411.01327 (2024-11)
Visual Fourier Prompt Tuning
get_grads 1 other paper
1 dated earlier
2006.09313 (2020-06)
Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks
get_random_states 1 other paper
1 later
2411.01327 (2024-11)
Visual Fourier Prompt Tuning
get_random_weights 1 other paper
1 later
2411.01327 (2024-11)
Visual Fourier Prompt Tuning

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

Learning in deep neural networks (DNNs) is implemented through minimizing a highly non-convex loss function, typically by a stochastic gradient descent (SGD) method. This learning process can effectively find good wide minima without being trapped in poor local ones. We present a novel account of how such effective deep learning emerges through the interactions of the SGD and the geometrical structure of the loss landscape. Rather than being a normal diffusion process (i.e. Brownian motion) as often assumed, we find that the SGD exhibits rich, complex dynamics when navigating through the loss landscape; initially, the SGD exhibits anomalous superdiffusion, which attenuates gradually and changes to subdiffusion at long times when the solution is reached. Such learning dynamics happen ubiquitously in different DNNs such as ResNet and VGG-like networks and are insensitive to batch size and learning rate. The anomalous superdiffusion process during the initial learning phase indicates that the motion of SGD along the loss landscape possesses intermittent, big jumps; this non-equilibrium property enables the SGD to escape from sharp local minima. By adapting the methods developed for studying energy landscapes in complex physical systems, we find that such superdiffusive learning dynamics are due to the interactions of the SGD and the fractal-like structure of the loss landscape. We further develop a simple model to demonstrate the mechanistic role of the fractal loss landscape in enabling the SGD to effectively find global minima. Our results thus reveal the effectiveness of deep learning from a novel perspective and have implications for designing efficient deep neural networks.

For agents

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

get_harvested_code_for_paper("2009.10588")
get_code_for_paper("2009.10588")
have("2009.10588")

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

curl https://syntology.ai/api/ran/2009.10588.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.10588.svg)](https://syntology.ai/paper/2009.10588)

Connect an agent — have() is free.