SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.09343 · ICML · 2020

MTL2L: A Context Aware Neural Optimiser

Mehrtash Harandi, Nicholas I-Hsien Kuo, Nicolas Fourrier, Christian Walder, Gabriela Ferraro, Hanna Suominen

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2007.09343.json · badge: /api/ran/2007.09343.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
nic5472k/automl2020_icml_mtl2l canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
Nic5472K/AutoML2020_ICML_MTL2L marked official in Papers with Code
Papers with Code archive
3 ran · 0 no recorded run
FunctionStatusWhere it lives
MyMLP Ran
ran on a synthesized input · constructed an object; no result was computed
Nic5472K/AutoML2020_ICML_MTL2L/Z002_AutoML/B002_MTL2L/B002d_AutoML_MTL2L.py
code served (permissive licence) · get_code("e33f03bd2f81102b")
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 an instance of its own class, MyMLP: the run constructed the object and did not call it, so no result was computed. 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)

# MyMLP expects OD (output dimension) as parameter
# Looking at the forward method:
# - inputs should be a tensor with shape (batch, channels, height, width) or (batch, 28*28)
# - It reshapes to (-1, 28*28) so it expects flattened or image-like input
# - UpdateTrain is a boolean flag for dropout during training

OD = 10  # output dimension (e.g., for 10 classes)

ARGS = {
    "OD": OD
}
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 MyMLP — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a MyMLP 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
RNNOptimiser Ran
ran on a synthesized input · constructed an object; no result was computed
Nic5472K/AutoML2020_ICML_MTL2L/Z002_AutoML/B002_MTL2L/B002d_AutoML_MTL2L.py
code served (permissive licence) · get_code("54bc7ca61265e074")
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 an instance of its own class, RNNOptimiser: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
from scipy.stats import ortho_group

torch.manual_seed(0)

class SimpleModel(nn.Module):
    """Minimal model that satisfies the interface expected by RNNOptimiser"""
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.linear = nn.Linear(10, 5)
    
    def reset(self):
        pass
    
    def copy_params_from(self, model):
        pass

class DummyOptimiser(nn.Module):
    """Dummy optimiser for testing"""
    def __init__(self):
        super(DummyOptimiser, self).__init__()

model = SimpleModel()
ID = 2
HD = 4
BS = 2

ARGS = {
    'model': model,
    'ID': ID,
    'HD': HD,
    'BS': BS
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type RNNOptimiser — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a RNNOptimiser 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
preprocess_gradients Ran
ran; our contract draft was wrong, not the code
nic5472k/automl2020_icml_mtl2l/Z002_AutoML/B002_MTL2L/B002d_AutoML_MTL2L.py
code served (permissive licence) · get_code("8ee5134bc24e5adc")
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) and returned Tensor, ndim 3, dtype family float, shape (2, 2, 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 torch
import math

torch.manual_seed(0)

# Create a small tensor for x parameter
# The function expects a tensor and performs operations like .abs(), .log(), .sign(), .unsqueeze()
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 2, 4) — shape (2, 2, 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
preprocess_gradients Ran
ran; our contract draft was wrong, not the code
Nic5472K/AutoML2020_ICML_MTL2L/Z002_AutoML/B002_MTL2L/B002d_AutoML_MTL2L.py
code served (permissive licence) · get_code("467a15ca5cb9700e")
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 3, dtype family float, shape (2, 2, 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 torch
import math

torch.manual_seed(0)

# Create a small tensor with gradients
# The function operates on x which should be a 1D or multi-dimensional tensor
# It uses: x.abs(), x.sign(), unsqueeze(), and cat()
# Shape: (2, 4) - batch of 2, feature dimension of 4
x = torch.randn(2, 4, requires_grad=True)

ARGS = {
    "x": x
}
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 3, dtype family float, shape (2, 2, 4) — shape (2, 2, 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

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 3 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 3 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

Learning to learn (L2L) trains a meta-learner to assist the learning of a task-specific base learner. Previously, it was shown that a meta-learner could learn the direct rules to update learner parameters; and that the learnt neural optimiser updated learners more rapidly than handcrafted gradient-descent methods. However, we demonstrate that previous neural optimisers were limited to update learners on one designated dataset. In order to address input-domain heterogeneity, we introduce Multi-Task Learning to Learn (MTL2L), a context aware neural optimiser which self-modifies its optimisation rules based on input data. We show that MTL2L is capable of updating learners to classify on data of an unseen input-domain at the meta-testing phase. We release our codes at https://github.com/Nic5472K/AutoML2020_ICML_MTL2L.

For agents

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

get_harvested_code_for_paper("2007.09343")
get_code_for_paper("2007.09343")
have("2007.09343")

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

curl https://syntology.ai/api/ran/2007.09343.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.09343.svg)](https://syntology.ai/paper/2007.09343)

Connect an agent — have() is free.