Papers › Optimization without Backpropagation

Optimization without Backpropagation

13 Sep 2022arXiv:2209.06302archive 2025-07-28

Gabriel Belouze

Forward gradients have been recently introduced to bypass backpropagation in autodifferentiation, while retaining unbiased estimators of true gradients. We derive an optimality condition to obtain best approximating forward gradients, which leads us to mathematical insights that suggest optimization in high dimension is challenging with forward gradients. Our extensive experiments on test functions support this claim.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2209.06302")

Code

Syntology Ran 0 of 8 code samples harvested from 1 repository linked to this paper; 8 have no recorded run.

By repository: official repository: 8 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

gbelouze/forward-gradient officialmentioned in papermentioned on GitHubBSD-2-Clause report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

8 samples harvested; 0 ran; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

8unverified

Licence: 0 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from gbelouze/forward-gradient. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

accuracy_profile gbelouze/forward-gradient/benchmark/figures.py official repository unverified BSD-2-Clause (permissive) · 04ab04ae8695b9d9 · report
circle gbelouze/forward-gradient/src/forward/samplers.py official repository unverified BSD-2-Clause (permissive) · d6321e8f96e01110 · report
df gbelouze/forward-gradient/src/forward/grad.py official repository unverified BSD-2-Clause (permissive) · fb638feb15a956da · report
gaussian gbelouze/forward-gradient/src/forward/samplers.py official repository unverified BSD-2-Clause (permissive) · f0a5202e373d9d3e · report
get_experiment_files gbelouze/forward-gradient/benchmark/figures.py official repository unverified BSD-2-Clause (permissive) · d34dd42dbb5c0649 · report
rademacher gbelouze/forward-gradient/src/forward/samplers.py official repository unverified BSD-2-Clause (permissive) · 9efbf539b61ba248 · report
read_experiment_files gbelouze/forward-gradient/benchmark/figures.py official repository unverified BSD-2-Clause (permissive) · 71265864f5120481 · report
sample_in_domain gbelouze/forward-gradient/benchmark/make.py official repository unverified BSD-2-Clause (permissive) · abaf02bbe4183369 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdabeliefAdamForward gradientSGDTest

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections