SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.11942 · 2020

Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent

arXiv · PDF · Open in the Atlas

Code that ran

5 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, 0 violated it and 1 has no contract verdict; 4 failures of our instrument; 4 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/2006.11942.json · badge: /api/ran/2006.11942.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
MehdiAbbanaBennani/continual-learning-ogdplus canonical (classifier label)
classifier basis: census
5 ran · 4 no recorded run
FunctionStatusWhere it lives
LeNetC Ran
ran; our contract draft was wrong, not the code
MehdiAbbanaBennani/continual-learning-ogdplus/models/cifar10net.py
code served (permissive licence) · get_code("a5e5ad4d88cd4ae0")
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 LeNet. 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

torch.manual_seed(0)

# LeNetC takes out_dim as a parameter
ARGS = {
    'out_dim': 10
}
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 LeNet — a LeNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LeNet 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
LeNetC Ran
ran on a synthesized input
MehdiAbbanaBennani/continual-learning-ogdplus/models/lenet.py
code served (permissive licence) · get_code("9d6b02b02f8751d3")
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 LeNet. 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

torch.manual_seed(0)

ARGS = {
    'hidden_dim': 128,
    'out_dim': 10,
}
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 LeNet — a LeNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LeNet 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
ResNet20_cifar Ran
ran; our contract draft was wrong, not the code
MehdiAbbanaBennani/continual-learning-ogdplus/models/resnet.py
code served (permissive licence) · get_code("d4e39697bdc71eac")
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 PreActResNet_cifar. 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

torch.manual_seed(0)

ARGS = {
    "out_dim": 10,
}
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 PreActResNet_cifar — a PreActResNet_cifar output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PreActResNet_cifar 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
ResNet56_cifar Ran
ran; our contract draft was wrong, not the code
MehdiAbbanaBennani/continual-learning-ogdplus/models/resnet.py
code served (permissive licence) · get_code("f3dc12181020f048")
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 PreActResNet_cifar. 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

torch.manual_seed(0)

# ResNet56_cifar only takes one parameter: out_dim
ARGS = {
    "out_dim": 10
}
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 PreActResNet_cifar — a PreActResNet_cifar output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PreActResNet_cifar 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
MehdiAbbanaBennani/continual-learning-ogdplus/models/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from amerch/CIFAR100-Training, is pointer only (licence: NONE) · get_code("583f9780bdd00a45")
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 amerch/CIFAR100-Training, and GitHub detected no licence in that repository 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.

NormalNN_reset_optim Not yet run
unverified (harvested, no recorded run)
MehdiAbbanaBennani/continual-learning-ogdplus/agents/customization.py
code served (permissive licence) · get_code("a6b5321ddba4e76a")
How it ran

no invocation recorded.

ResNet110_cifar Not yet run
unverified (harvested, no recorded run)
MehdiAbbanaBennani/continual-learning-ogdplus/models/senet.py
code served (permissive licence) · get_code("38189f93ef69d6ec")
How it ran

no invocation recorded.

SE_ResNet20_cifar Not yet run
unverified (harvested, no recorded run)
MehdiAbbanaBennani/continual-learning-ogdplus/models/senet.py
code served (permissive licence) · get_code("16e2d4177214aebb")
How it ran

no invocation recorded.

SE_ResNet56_cifar Not yet run
unverified (harvested, no recorded run)
MehdiAbbanaBennani/continual-learning-ogdplus/models/senet.py
code served (permissive licence) · get_code("e1b5400489e523bc")
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, 8 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 8 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
conv3x3 686 other papers
226 dated earlier, 11 the same month, 448 later, 1 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
LeNetC 1 other paper
1 later
2204.07249 (2022-04)
Minimizing Control for Credit Assignment with Strong Feedback
NormalNN_reset_optim 1 other paper
1 later
2204.07249 (2022-04)
Minimizing Control for Credit Assignment with Strong Feedback
ResNet110_cifar 1 other paper
1 later
2204.07249 (2022-04)
Minimizing Control for Credit Assignment with Strong Feedback
ResNet20_cifar 1 other paper
1 later
2204.07249 (2022-04)
Minimizing Control for Credit Assignment with Strong Feedback
ResNet56_cifar 1 other paper
1 later
2204.07249 (2022-04)
Minimizing Control for Credit Assignment with Strong Feedback
SE_ResNet20_cifar 1 other paper
1 later
2204.07249 (2022-04)
Minimizing Control for Credit Assignment with Strong Feedback
SE_ResNet56_cifar 1 other paper
1 later
2204.07249 (2022-04)
Minimizing Control for Credit Assignment with Strong Feedback

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 Continual Learning settings, deep neural networks are prone to Catastrophic Forgetting. Orthogonal Gradient Descent was proposed to tackle the challenge. However, no theoretical guarantees have been proven yet. We present a theoretical framework to study Continual Learning algorithms in the Neural Tangent Kernel regime. This framework comprises closed form expression of the model through tasks and proxies for Transfer Learning, generalisation and tasks similarity. In this framework, we prove that OGD is robust to Catastrophic Forgetting then derive the first generalisation bound for SGD and OGD for Continual Learning. Finally, we study the limits of this framework in practice for OGD and highlight the importance of the Neural Tangent Kernel variation for Continual Learning with OGD.

For agents

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

get_harvested_code_for_paper("2006.11942")
get_code_for_paper("2006.11942")
have("2006.11942")

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

curl https://syntology.ai/api/ran/2006.11942.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.11942.svg)](https://syntology.ai/paper/2006.11942)

Connect an agent — have() is free.