Papers › The HSIC Bottleneck: Deep Learning without Back-Propagation

The HSIC Bottleneck: Deep Learning without Back-Propagation

5 Aug 2019arXiv:1908.01580archive 2025-07-28

Wan-Duo Kurt Ma, J. P. Lewis, W. Bastiaan Kleijn

We introduce the HSIC (Hilbert-Schmidt independence criterion) bottleneck for training deep neural networks. The HSIC bottleneck is an alternative to the conventional cross-entropy loss and backpropagation that has a number of distinct advantages. It mitigates exploding and vanishing gradients, resulting in the ability to learn very deep networks without skip connections. There is no requirement for symmetric feedback or update locking. We find that the HSIC bottleneck provides performance on MNIST/FashionMNIST/CIFAR10 classification comparable to backpropagation with a cross-entropy target, even when the system is not encouraged to make the output resemble the classification labels. Appending a single layer trained with SGD (without backpropagation) to reformat the information further improves performance.

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 16 code samples harvested from 3 repositories linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 2 ran (1 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 4 samples from 2 repositories, 2 ran (2 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.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

choasma/HSIC-Bottleneck officialmentioned in paperpytorchMITSyntology: 12 samples, 2 ran (1 instrument-failed) · 10 unverified report
forin-xyz/Keras-HSIC-Bottleneck mentioned on GitHubtfMITSyntology: 2 samples, 0 ran · 2 unverified report
gusye1234/Pytorch-HSIC-bottleneck mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified 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

16 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 12 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.

2ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
12unverified

Licence: 1 of the 16 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 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.

choasma/HSIC-Bottleneck official repository 12 samples, 2 ran (1 instrument-failed) · 10 unverified
distmat in 12 papers
census: 4 implementations from 6 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
source/hsicbt/math/hsic.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · ca565da6831e8ade · report fixture: signature X:Tensor/2/float · returned Tensor · level recorded 2026-09-22
sigma_estimation in 12 papers
census: 4 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
source/hsicbt/math/hsic.py ran · our draft was wrong fingerprinted MIT (permissive) · 9cb35dd6de9569b7 · report fixture: signature X:Tensor/2/float, Y:Tensor/2/float · returned float32 · level recorded 2026-09-22
activations_extraction source/hsicbt/core/train_misc.py unverified MIT (permissive) · 36113cd19ffcf229 · report
get_activation in 218 papers source/hsicbt/model/block.py unverified MIT (permissive) · 081d601ecb8131e9 · report
get_activation_functional source/hsicbt/model/block.py unverified MIT (permissive) · f673b1b67b853686 · report
hsic_objective source/hsicbt/core/train_misc.py unverified MIT (permissive) · a91fadca8b8eda82 · report
hsic_train source/hsicbt/core/train_hsic.py unverified MIT (permissive) · 3e2e5b7d40d8d635 · report
kernelmat in 10 papers source/hsicbt/math/hsic.py unverified MIT (permissive) · 24809ea920bce66a · report
model_distribution source/hsicbt/core/train_misc.py unverified MIT (permissive) · 4e359f516c8b5cde · report
training_format source/hsicbt/core/engine.py unverified MIT (permissive) · 8cf8628e457c620a · report
training_format_combined source/hsicbt/core/engine.py unverified MIT (permissive) · eb4769af96585b1e · report
training_standard source/hsicbt/core/engine.py unverified MIT (permissive) · b790ea06fc508512 · report
forin-xyz/Keras-HSIC-Bottleneck community (archive-listed) 2 samples, 0 ran · 2 unverified
hsic in 5 papers hsic_bottleneck.py unverified MIT (permissive) · fa8a5e8c525f588e · report
kernel_matrix in 6 papers hsic_bottleneck.py unverified MIT (permissive) · b8bd182708aa51a7 · report
gusye1234/Pytorch-HSIC-bottleneck community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
HSIC in 5 papers torch_hsic.py ran · violated contract fingerprinted MIT (permissive) · 76846d9d673d577b · report fixture: signature Kx:Tensor/2/float, Ky:Tensor/2/float, m:int/0/int · returned Tensor · level recorded 2026-09-22
kernel_matrix in 6 papers torch_hsic.py ran · honoured contract fingerprinted MIT (permissive) · 4043a12aa5102af0 · report fixture: signature x:Tensor/2/float, sigma:float/0/float · returned Tensor · level recorded 2026-09-22

Tasks

ClassificationDeep LearningGeneral Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SGD

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