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 View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 19 code samples harvested from 6 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 18 samples from 5 repositories, 10 ran (10 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ducha-aiki/LSUVinit officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
JonasWechsler/DeepLearningLab5 mentioned on GitHubtfMITSyntology: 11 samples, 5 ran (0 instrument-failed) · 6 unverified report
dmbernaal/Daedalus mentioned on GitHubpytorchSyntology: not harvested report
ducha-aiki/LSUV-keras mentioned on GitHubpytorchBSD-2-ClauseSyntology: 1 sample, 0 ran · 1 unverified report
ducha-aiki/LSUV-pytorch mentioned on GitHubpytorchBSD-2-ClauseSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
ducha-aiki/lsuv mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
shunk031/LSUV.pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
vimarshc/fastai_experiments mentioned on GitHubtfSyntology: not harvested report
MindCode-4/code-12 mindsporeSyntology: not harvested report
MindCode-4/code-7 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to KPC-cF: Aspect-Based Sentiment Analysis via Implicit-Feature Alignment with Corpus Filtering (arXiv:2407.00342; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific/code-6 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training (arXiv:2203.09313; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

19 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

10ran
9unverified

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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

ducha-aiki/LSUVinit official repository 1 sample, 0 ran · 1 unverified
svd_orthonormal tools/extra/lsuv_init.py unverified licence not identified · pointer only · 07793677326f6721 · report
JonasWechsler/DeepLearningLab5 community (archive-listed) 11 samples, 5 ran (0 instrument-failed) · 6 unverified
average_gradients in 20 papers cifar10/cifar10_multi_gpu_train.py ran MIT (permissive) · 25474dc6ec455a0d · report fixture: signature tower_grads:list/1/list · returned list · level recorded 2026-09-26
random_rotation in 15 papers image.py ran MIT (permissive) · c03141891ec617ab · report fixture: signature x:ndarray/3/float, rg:float/0/float, row_axis:int/0/int, col_axis:int/0/int, channel_axis:int/0/int, fill_mode:str/0/str, cval:float/0/float · returned ndarray · level recorded 2026-09-26
random_shear image.py ran MIT (permissive) · 9d24359eae5d10c4 · report fixture: signature x:ndarray/3/float, intensity:float/0/float, row_axis:int/0/int, col_axis:int/0/int, channel_axis:int/0/int, fill_mode:str/0/str, cval:float/0/float · returned ndarray · level recorded 2026-09-26
random_shift in 5 papers image.py ran MIT (permissive) · ec1c67befd8a9ab3 · report fixture: signature x:ndarray/3/float, wrg:float/0/float, hrg:float/0/float, row_axis:int/0/int, col_axis:int/0/int, channel_axis:int/0/int, fill_mode:str/0/str, cval:float/0/float · returned ndarray · level recorded 2026-09-26
svd_orthonormal lsuv_init.py ran MIT (permissive) · 962d5f8133e2c7ce · report fixture: signature shape:tuple/1/int · returned ndarray · level recorded 2026-09-26
LSUVinit lsuv_init.py unverified MIT (permissive) · a42f70aba8b0e71a · report
distorted_inputs cifar10/cifar10_input.py unverified MIT (permissive) · 8919d7b64b3fd80a · report
get_activations in 100 papers lsuv_init.py unverified MIT (permissive) · f0ac7f8a003439d1 · report
inputs cifar10/cifar10_input.py unverified MIT (permissive) · 0f84f9e9bc13c884 · report
read_cifar10 in 5 papers cifar10/cifar10_input.py unverified MIT (permissive) · 969bfd9c98f79209 · report
ducha-aiki/LSUV-keras community (archive-listed) 1 sample, 0 ran · 1 unverified
LSUVinit lsuv_init.py unverified BSD-2-Clause (permissive) · 522aea77ce74065c · report
ducha-aiki/LSUV-pytorch community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
LSUVinit LSUV.py ran BSD-2-Clause (permissive) · 02e5a31d6c7a6b1c · report fixture: signature model:callable/0/?, data:Tensor/4/float, needed_std:float/0/float, std_tol:float/0/float, max_attempts:int/0/int, do_orthonorm:bool/0/bool, needed_mean:float/0/float, cuda:bool/0/bool, verbose:bool/0/bool · returned SimpleModel · level recorded 2026-09-26
svd_orthonormal LSUV.py ran fingerprinted BSD-2-Clause (permissive) · 69c8426f8140deac · report fixture: signature w:ndarray/3/float · returned ndarray · level recorded 2026-09-26
ducha-aiki/lsuv community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
get_scalable_weight lsuv/lsuvinit.py ran MIT (permissive) · e4da73f8a72851bb · report fixture: signature m:callable/0/? · returned Parameter · level recorded 2026-09-26
is_relevant_layer lsuv/lsuvinit.py ran MIT (permissive) · 6b3581c398b49245 · report fixture: signature m:callable/0/? · returned bool · level recorded 2026-09-26
move_to in 15 papers lsuv/lsuvinit.py ran MIT (permissive) · 1de0deb674c678ec · report fixture: signature obj:dict/0/?, device:str/0/str · returned dict · level recorded 2026-09-26
shunk031/LSUV.pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
lsuv_init lsuv/lsuv.py unverified no licence file found · pointer only · 9c5badcb7115095b · 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