Papers › All you need is a good init

All you need is a good init

19 Nov 2015ICLR 2015 11arXiv:1511.06422archive 2025-07-28

Dmytro Mishkin, Jiri Matas

Layer-sequential unit-variance (LSUV) initialization - a simple method for weight initialization for deep net learning - is proposed. The method consists of the two steps. First, pre-initialize weights of each convolution or inner-product layer with orthonormal matrices. Second, proceed from the first to the final layer, normalizing the variance of the output of each layer to be equal to one. Experiment with different activation functions (maxout, ReLU-family, tanh) show that the proposed initialization leads to learning of very deep nets that (i) produces networks with test accuracy better or equal to standard methods and (ii) is at least as fast as the complex schemes proposed specifically for very deep nets such as FitNets (Romero et al. (2015)) and Highway (Srivastava et al. (2015)). Performance is evaluated on GoogLeNet, CaffeNet, FitNets and Residual nets and the state-of-the-art, or very close to it, is achieved on the MNIST, CIFAR-10/100 and ImageNet datasets.

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="1511.06422")

Code

Syntology Ran 0 of 19 code samples harvested from 6 repositories linked to this paper; 19 have no recorded run.

By repository: official repository: 1 sample from 1 repository, 0 ran; community (archive-listed): 18 samples from 5 repositories, 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.

ducha-aiki/LSUVinit officialmentioned in papermentioned on GitHubpytorch report
JonasWechsler/DeepLearningLab5 mentioned on GitHubtfMIT report
dmbernaal/Daedalus mentioned on GitHubpytorch report
ducha-aiki/LSUV-keras mentioned on GitHubpytorchBSD-2-Clause report
ducha-aiki/LSUV-pytorch mentioned on GitHubpytorchBSD-2-Clause report
ducha-aiki/lsuv mentioned on GitHubpytorchMIT report
shunk031/LSUV.pytorch mentioned on GitHubpytorch report
vimarshc/fastai_experiments mentioned on GitHubtf 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

19 samples harvested; 0 ran; 0 honoured the contract we drafted; 19 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.

19unverified

Licence: 2 of the 19 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 6 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.

svd_orthonormal ducha-aiki/LSUVinit/tools/extra/lsuv_init.py official repository unverified licence not identified · pointer only · 07793677326f6721 · report
LSUVinit JonasWechsler/DeepLearningLab5/lsuv_init.py community (archive-listed) unverified MIT (permissive) · a42f70aba8b0e71a · report
LSUVinit ducha-aiki/LSUV-keras/lsuv_init.py community (archive-listed) unverified BSD-2-Clause (permissive) · 522aea77ce74065c · report
LSUVinit ducha-aiki/LSUV-pytorch/LSUV.py community (archive-listed) unverified BSD-2-Clause (permissive) · 02e5a31d6c7a6b1c · report
average_gradients JonasWechsler/DeepLearningLab5/cifar10/cifar10_multi_gpu_train.py community (archive-listed) unverified MIT (permissive) · 25474dc6ec455a0d · report
distorted_inputs JonasWechsler/DeepLearningLab5/cifar10/cifar10_input.py community (archive-listed) unverified MIT (permissive) · 8919d7b64b3fd80a · report
get_activations JonasWechsler/DeepLearningLab5/lsuv_init.py community (archive-listed) unverified MIT (permissive) · f0ac7f8a003439d1 · report
get_scalable_weight ducha-aiki/lsuv/lsuv/lsuvinit.py community (archive-listed) unverified MIT (permissive) · e4da73f8a72851bb · report
inputs JonasWechsler/DeepLearningLab5/cifar10/cifar10_input.py community (archive-listed) unverified MIT (permissive) · 0f84f9e9bc13c884 · report
is_relevant_layer ducha-aiki/lsuv/lsuv/lsuvinit.py community (archive-listed) unverified MIT (permissive) · 6b3581c398b49245 · report
loss JonasWechsler/DeepLearningLab5/cifar10/cifar10.py community (archive-listed) unverified MIT (permissive) · 7b7d1b28f254c06c · report
lsuv_init shunk031/LSUV.pytorch/lsuv/lsuv.py community (archive-listed) unverified no licence file found · pointer only · 9c5badcb7115095b · report
move_to ducha-aiki/lsuv/lsuv/lsuvinit.py community (archive-listed) unverified MIT (permissive) · 1de0deb674c678ec · report
random_rotation JonasWechsler/DeepLearningLab5/image.py community (archive-listed) unverified MIT (permissive) · c03141891ec617ab · report
random_shear JonasWechsler/DeepLearningLab5/image.py community (archive-listed) unverified MIT (permissive) · 9d24359eae5d10c4 · report
random_shift JonasWechsler/DeepLearningLab5/image.py community (archive-listed) unverified MIT (permissive) · ec1c67befd8a9ab3 · report
read_cifar10 JonasWechsler/DeepLearningLab5/cifar10/cifar10_input.py community (archive-listed) unverified MIT (permissive) · 969bfd9c98f79209 · report
svd_orthonormal JonasWechsler/DeepLearningLab5/lsuv_init.py community (archive-listed) unverified MIT (permissive) · 962d5f8133e2c7ce · report
svd_orthonormal ducha-aiki/LSUV-pytorch/LSUV.py community (archive-listed) unverified BSD-2-Clause (permissive) · 69c8426f8140deac · report

Tasks

AllImage Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 Fitnet4-LSUV Percentage correct 94.2 #161 of 265 Archive leaderboard report
Image Classification CIFAR-100 Fitnet4-LSUV Percentage correct 72.3 #169 of 211 Archive leaderboard report
Image Classification MNIST Fitnet-LSUV-SVM Percentage error 0.4 #30 of 81 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAuxiliary ClassifierAverage PoolingConvolutionDense ConnectionsDropoutGoogLeNetInception ModuleLSUV InitializationLocal Response NormalizationMax PoolingReLUSoftmax

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