Papers › ReZero is All You Need: Fast Convergence at Large Depth

ReZero is All You Need: Fast Convergence at Large Depth

10 Mar 2020arXiv:2003.04887archive 2025-07-28

Thomas Bachlechner, Bodhisattwa Prasad Majumder, Huanru Henry Mao, Garrison W. Cottrell, Julian McAuley

Deep networks often suffer from vanishing or exploding gradients due to inefficient signal propagation, leading to long training times or convergence difficulties. Various architecture designs, sophisticated residual-style networks, and initialization schemes have been shown to improve deep signal propagation. Recently, Pennington et al. used free probability theory to show that dynamical isometry plays an integral role in efficient deep learning. We show that the simplest architecture change of gating each residual connection using a single zero-initialized parameter satisfies initial dynamical isometry and outperforms more complex approaches. Although much simpler than its predecessors, this gate enables training thousands of fully connected layers with fast convergence and better test performance for ResNets trained on CIFAR-10. We apply this technique to language modeling and find that we can easily train 120-layer Transformers. When applied to 12 layer Transformers, it converges 56% faster on enwiki8.

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="2003.04887")

Code

Syntology Ran 6 of 6 code samples harvested from 2 repositories linked to this paper; 0 have no recorded run. Of those that ran: 6 ran · our draft was wrong.

By repository: community (archive-listed): 6 samples from 2 repositories, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

13 repositories listed; official and paper-mentioned ones first.

majumderb/rezero officialmentioned in papermentioned on GitHubpytorchMIT report
JunnYu/x-transformers-paddle mentioned on GitHubjaxApache-2.0 report
coolsunxu/rezero_tf2 mentioned on GitHubtf report
davidsvy/cosformer-pytorch mentioned on GitHubpytorchMIT report
fabio-deep/ReZero-ResNet mentioned on GitHubpytorch report
fengleifan/relinear mentioned on GitHubpytorch report
lucidrains/performer-pytorch mentioned on GitHubpytorch report
lucidrains/reformer-pytorch mentioned on GitHubpytorch report
lucidrains/routing-transformer mentioned on GitHubpytorch report
sooheon/perceiver-jax mentioned on GitHubjax report
statsu1990/ReZero-Cifar100 mentioned on GitHubpytorch report
tbachlechner/ReZero-examples mentioned on GitHubpytorchMIT 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

6 samples harvested; 6 ran; 0 honoured the contract we drafted; 0 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.

6ran · our draft was wrong

Licence: 0 of the 6 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

PreActResNet18 statsu1990/ReZero-Cifar100/src/model/rezero_preact_resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 09aa6bbcdc551903 · report
PreActResNet34 statsu1990/ReZero-Cifar100/src/model/rezero_preact_resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 228f5abb7a7bf1c7 · report
PreActResNet50 statsu1990/ReZero-Cifar100/src/model/rezero_preact_resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 347af4f109be8414 · report
resnet20 fabio-deep/ReZero-ResNet/src/resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · ced375c8bbba0283 · report
resnet32 fabio-deep/ReZero-ResNet/src/resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 0062b25c7d99c79a · report
resnet44 fabio-deep/ReZero-ResNet/src/resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 7377861df3c47980 · report

Tasks

AllLanguage ModelingLanguage Modelling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: ReZero

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUReZeroResidual ConnectionSoftmaxTransformer

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