SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.10575 · NeurIPS · 2021

EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization

Yongxin Yang, Timothy Hospedales, Ondrej Bohdal

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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; 4 failures of our instrument; 3 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/2106.10575.json · badge: /api/ran/2106.10575.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
ondrejbohdal/evograd canonical (classifier label)
classifier basis: classifier_2025
3 ran · 1 no recorded run
uber-research/EvoGrad extension (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
convert_examples_to_features Ran
ran; our contract draft was wrong, not the code
ondrejbohdal/evograd/CrossLingualLearningMetaXL/mtrain.py
code served (permissive licence) · get_code("c4806e075ebe8fb0")
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 list, 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

class Example:
    def __init__(self, text_a, label):
        self.text_a = text_a
        self.label = label

class SimpleTokenizer:
    def encode(self, text, label):
        # Returns (input_ids, input_mask, label_ids)
        input_ids = [101, 2054, 2003, 102]  # [CLS] what is [SEP]
        input_mask = [1, 1, 1, 1]
        label_ids = [0, 1, 0, 1]  # sequence labels
        return input_ids, input_mask, label_ids

examples = [
    Example(text_a="what is this", label="positive"),
    Example(text_a="hello world", label="negative"),
]

label_list = ["negative", "positive"]

max_seq_length = 8

tokenizer = SimpleTokenizer()

ARGS = {
    "examples": examples,
    "label_list": label_list,
    "max_seq_length": max_seq_length,
    "tokenizer": tokenizer,
}
Setup block drafted by
a language model, Claude Haiku 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 list, ndim 1, dtype family float — a list 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
expectation Ran
ran; our contract draft was wrong, not the code
uber-research/EvoGrad/evograd/expectation.py
pointer only (licence: NOASSERTION) · get_code("74c63bb5cff264d6")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, uber-research/EvoGrad (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.

extract_args_from_json Ran
ran; our contract draft was wrong, not the code
ondrejbohdal/evograd/LabelNoiseMetaWeightNet/meta-weight-net-label-noise.py
code served (permissive licence) · get_code("25b7c604b7346978")
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 AttributeAccessibleDict. 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 json
import tempfile
import os

# Create a temporary JSON file with test arguments
temp_dir = tempfile.mkdtemp()
json_file_path = os.path.join(temp_dir, "test_args.json")

test_json_content = {
    "learning_rate": 0.001,
    "batch_size": 32,
    "epochs": 10,
    "model_name": "test_model"
}

with open(json_file_path, 'w') as f:
    json.dump(test_json_content, f)

# Create an existing_args_dict with some values
class SimpleArgs:
    def __init__(self):
        self.optimizer = "adam"
        self.device = "cpu"
        self.seed = 42

existing_args_dict = SimpleArgs()

ARGS = {
    "json_file_path": json_file_path,
    "existing_args_dict": existing_args_dict
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 AttributeAccessibleDict — a AttributeAccessibleDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a AttributeAccessibleDict 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
readfile Ran
ran; our contract draft was wrong, not the code
ondrejbohdal/evograd/CrossLingualLearningMetaXL/mtrain.py
code served (permissive licence) · get_code("b23c45da1891b8ed")
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 list. 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 tempfile
import os

# Create a temporary file with sample data in the expected format
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt', encoding='utf8')
temp_file.write("token1\tPOS\tNER\n")
temp_file.write("token2\tVERB\tO\n")
temp_file.write("\n")
temp_file.write("token3\tNOUN\tB-PER\n")
temp_file.write("token4\tDET\tO\n")
temp_file.write("-DOCSTART- -X- -X- O\n")
temp_file.write("token5\tADJ\tB-LOC\n")
temp_file.close()

ARGS = {
    "filename": temp_file.name,
    "lang": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 list — a list 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
accuracy Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from snu-mllab/PuzzleMix
pointer only · get_code("f0c9a29156911331")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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. No invocation recorded.

pad Not yet run
unverified (harvested, no recorded run)
ondrejbohdal/evograd/LabelNoiseMetaWeightNet/meta-weight-net-label-noise.py
code served (permissive licence) · get_code("b6ff598187d9c7d8")
How it ran

no invocation recorded.

unsqueeze_as Not yet run
unverified (harvested, no recorded run)
uber-research/EvoGrad/evograd/expectation.py
pointer only (licence: NOASSERTION) · get_code("6f3c5ba1bac8315c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, uber-research/EvoGrad (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. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 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
accuracy 71 other papers
49 dated earlier, 1 the same month, 19 later, 2 same year, order not determinable · 2 only as an assembly brick
1505.05424 (2015-05)
Weight Uncertainty in Neural Networks
1705.07204 (2017-05)
Ensemble Adversarial Training: Attacks and Defenses
1802.10399 (2018-02)
Compressing Neural Networks using the Variational Information Bottleneck
and 68 more not named here

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

Gradient-based meta-learning and hyperparameter optimization have seen significant progress recently, enabling practical end-to-end training of neural networks together with many hyperparameters. Nevertheless, existing approaches are relatively expensive as they need to compute second-order derivatives and store a longer computational graph. This cost prevents scaling them to larger network architectures. We present EvoGrad, a new approach to meta-learning that draws upon evolutionary techniques to more efficiently compute hypergradients. Evo-Grad estimates hypergradient with respect to hyperparameters without calculating second-order gradients, or storing a longer computational graph, leading to significant improvements in efficiency. We evaluate EvoGrad on three substantial recent meta-learning applications, namely cross-domain few-shot learning with featurewise transformations, noisy label learning with Meta-Weight-Net and low-resource cross-lingual learning with meta representation transformation. The results show that EvoGrad significantly improves efficiency and enables scaling meta-learning to bigger architectures such as from ResNet10 to ResNet34.

For agents

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

get_harvested_code_for_paper("2106.10575")
get_code_for_paper("2106.10575")
have("2106.10575")

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

curl https://syntology.ai/api/ran/2106.10575.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.10575.svg)](https://syntology.ai/paper/2106.10575)

Connect an agent — have() is free.