SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.12878 · NeurIPS · 2020

Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures

Florent Krzakala, Julien Launay, Iacopo Poli, François Boniface

arXiv · PDF · Open in the Atlas

Code that ran

2 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 2 have no contract verdict; 0 failures of our instrument; 5 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/2006.12878.json · badge: /api/ran/2006.12878.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
lightonai/dfa-scales-to-modern-deep-learning canonical (classifier label)
classifier basis: census
2 ran · 5 no recorded run
FunctionStatusWhere it lives
get_device Ran
ran on a synthesized input
lightonai/dfa-scales-to-modern-deep-learning/paper-experiments/geometric-learning/alignment.py
code served (permissive licence) · get_code("45e3ddd9c9803f5e")
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 device. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:55:33Z. 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

torch.manual_seed(0)

# The function get_device(gpu_id) expects an integer gpu_id parameter
# It will raise OSError if CUDA is not available, which is expected in CPU-only environment
# We construct a valid gpu_id argument

ARGS = {
    'gpu_id': 0
}
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 device — a device output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a device output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
remove_indices Ran
ran on a synthesized input
lightonai/dfa-scales-to-modern-deep-learning/TinyDFA/tinydfa/utils.py
code served (permissive licence) · get_code("4beba5bae36d22cd")
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 list, ndim 1, dtype family int; 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 numpy as np

torch.manual_seed(0)

# The function remove_indices takes an array and a list of indices,
# returning a new list with elements at those indices removed.
# 
# Parameters:
# - array: a sequence (list, tuple, or iterable) of elements
# - indices: a sequence of integer indices to remove

# Create a simple array with distinct elements
array = [10, 20, 30, 40, 50]

# Create indices to remove
indices = [1, 3]

ARGS = {
    "array": array,
    "indices": indices,
}
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 list, ndim 1, dtype family int — 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
get_data Not yet run
unverified (harvested, no recorded run)
lightonai/dfa-scales-to-modern-deep-learning/paper-experiments/geometric-learning/alignment.py
code served (permissive licence) · get_code("4b36f632eb1ccc80")
How it ran

no invocation recorded.

get_data Not yet run
unverified (harvested, no recorded run)
lightonai/dfa-scales-to-modern-deep-learning/paper-experiments/geometric-learning/autoencoder.py
code served (permissive licence) · get_code("57e0043966887f1b")
How it ran

no invocation recorded.

get_data Not yet run
unverified (harvested, no recorded run)
lightonai/dfa-scales-to-modern-deep-learning/paper-experiments/geometric-learning/geometric.py
code served (permissive licence) · get_code("b3c53775e578f268")
How it ran

no invocation recorded.

get_data Not yet run
unverified (harvested, no recorded run)
lightonai/dfa-scales-to-modern-deep-learning/paper-experiments/geometric-learning/tsne.py
code served (permissive licence) · get_code("9a9bbcf0acab0876")
How it ran

no invocation recorded.

keep_indices Not yet run
unverified (harvested, no recorded run)
lightonai/dfa-scales-to-modern-deep-learning/TinyDFA/tinydfa/utils.py
code served (permissive licence) · get_code("6bb2b9249518fd2f")
How it ran

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 6 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 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.

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

Despite being the workhorse of deep learning, the backpropagation algorithm is no panacea. It enforces sequential layer updates, thus preventing efficient parallelization of the training process. Furthermore, its biological plausibility is being challenged. Alternative schemes have been devised; yet, under the constraint of synaptic asymmetry, none have scaled to modern deep learning tasks and architectures. Here, we challenge this perspective, and study the applicability of Direct Feedback Alignment (DFA) to neural view synthesis, recommender systems, geometric learning, and natural language processing. In contrast with previous studies limited to computer vision tasks, our findings show that it successfully trains a large range of state-of-the-art deep learning architectures, with performance close to fine-tuned backpropagation. When a larger gap between DFA and backpropagation exists, like in Transformers, we attribute this to a need to rethink common practices for large and complex architectures. At variance with common beliefs, our work supports that challenging tasks can be tackled in the absence of weight transport.

For agents

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

get_harvested_code_for_paper("2006.12878")
get_code_for_paper("2006.12878")
have("2006.12878")

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

curl https://syntology.ai/api/ran/2006.12878.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.12878.svg)](https://syntology.ai/paper/2006.12878)

Connect an agent — have() is free.