SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.01580 · 2019

The HSIC Bottleneck: Deep Learning without Back-Propagation

arXiv · PDF · Open in the Atlas

Code that ran

4 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 12 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1908.01580.json · badge: /api/ran/1908.01580.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
choasma/HSIC-Bottleneck canonical (classifier label)
classifier basis: census
2 ran · 10 no recorded run
gusye1234/Pytorch-HSIC-bottleneck reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
forin-xyz/Keras-HSIC-Bottleneck community (classifier label)
classifier basis not recorded on the link
0 ran · 2 no recorded run
FunctionStatusWhere it lives
HSIC Ran
ran, violated the contract we drafted
gusye1234/Pytorch-HSIC-bottleneck/torch_hsic.py
code served (permissive licence) · get_code("76846d9d673d577b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Kx and Ky are kernel matrices (Gram matrices)
# They should be square matrices of size m x m
m = 2
Kx = torch.randn(m, m)
Ky = torch.randn(m, m)

ARGS = {
    "Kx": Kx,
    "Ky": Ky,
    "m": m,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
distmat Ran
ran, honoured the contract we drafted
choasma/HSIC-Bottleneck/source/hsicbt/math/hsic.py
pointer only (licence: MIT); the stored copy get_code serves, from sjyucnel/cauchy-schwarz-information-bottleneck, is pointer only (licence: NONE) · get_code("ca565da6831e8ade")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from sjyucnel/cauchy-schwarz-information-bottleneck, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

kernel_matrix Ran
ran, honoured the contract we drafted
gusye1234/Pytorch-HSIC-bottleneck/torch_hsic.py
code served (permissive licence) · get_code("4043a12aa5102af0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small tensor with shape (2, 4) - batch size 2, dimension 4
x = torch.randn(2, 4)

# sigma is a scalar parameter for the kernel
sigma = 1.0

ARGS = {
    "x": x,
    "sigma": sigma,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 2) — shape (2, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
sigma_estimation Ran
ran; our contract draft was wrong, not the code
choasma/HSIC-Bottleneck/source/hsicbt/math/hsic.py
code served (permissive licence) · get_code("9cb35dd6de9569b7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned float32, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create small sample tensors
# X: shape (2, 4) - 2 samples, 4 dimensions
X = torch.randn(2, 4)

# Y: shape (3, 4) - 3 samples, 4 dimensions (different from X to make shapes distinct)
Y = torch.randn(3, 4)

ARGS = {
    "X": X,
    "Y": Y,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float32, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
activations_extraction Not yet run
unverified (harvested, no recorded run)
choasma/HSIC-Bottleneck/source/hsicbt/core/train_misc.py
code served (permissive licence) · get_code("36113cd19ffcf229")
How it ran

no invocation recorded.

get_activation Not yet run
unverified (harvested, no recorded run)
choasma/HSIC-Bottleneck/source/hsicbt/model/block.py
code served (permissive licence) · get_code("081d601ecb8131e9")
How it ran

no invocation recorded.

get_activation_functional Not yet run
unverified (harvested, no recorded run)
choasma/HSIC-Bottleneck/source/hsicbt/model/block.py
code served (permissive licence) · get_code("f673b1b67b853686")
How it ran

no invocation recorded.

hsic Not yet run
unverified (harvested, no recorded run)
forin-xyz/Keras-HSIC-Bottleneck/hsic_bottleneck.py
code served (permissive licence) · get_code("fa8a5e8c525f588e")
How it ran

no invocation recorded.

hsic_objective Not yet run
unverified (harvested, no recorded run)
choasma/HSIC-Bottleneck/source/hsicbt/core/train_misc.py
code served (permissive licence) · get_code("a91fadca8b8eda82")
How it ran

no invocation recorded.

hsic_train Not yet run
unverified (harvested, no recorded run)
choasma/HSIC-Bottleneck/source/hsicbt/core/train_hsic.py
code served (permissive licence) · get_code("3e2e5b7d40d8d635")
How it ran

no invocation recorded.

kernel_matrix Not yet run
unverified (harvested, no recorded run)
forin-xyz/Keras-HSIC-Bottleneck/hsic_bottleneck.py
code served (permissive licence) · get_code("b8bd182708aa51a7")
How it ran

no invocation recorded.

kernelmat Not yet run
unverified (harvested, no recorded run)
choasma/HSIC-Bottleneck/source/hsicbt/math/hsic.py
code served (permissive licence) · get_code("24809ea920bce66a")
How it ran

no invocation recorded.

model_distribution Not yet run
unverified (harvested, no recorded run)
choasma/HSIC-Bottleneck/source/hsicbt/core/train_misc.py
code served (permissive licence) · get_code("4e359f516c8b5cde")
How it ran

no invocation recorded.

training_format Not yet run
unverified (harvested, no recorded run)
choasma/HSIC-Bottleneck/source/hsicbt/core/engine.py
code served (permissive licence) · get_code("8cf8628e457c620a")
How it ran

no invocation recorded.

training_format_combined Not yet run
unverified (harvested, no recorded run)
choasma/HSIC-Bottleneck/source/hsicbt/core/engine.py
code served (permissive licence) · get_code("eb4769af96585b1e")
How it ran

no invocation recorded.

training_standard Not yet run
unverified (harvested, no recorded run)
choasma/HSIC-Bottleneck/source/hsicbt/core/engine.py
code served (permissive licence) · get_code("b790ea06fc508512")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 12 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
sigma_estimation 11 other papers
11 later
2106.01939 (2021-06)
Causal Effect Inference for Structured Treatments
2106.02734 (2021-06)
Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness
2210.04311 (2022-10)
Pruning Adversarially Robust Neural Networks without Adversarial Examples
and 8 more not named here
distmat 8 other papers
8 later · 1 only as an assembly brick
2106.01939 (2021-06)
Causal Effect Inference for Structured Treatments
2106.02734 (2021-06)
Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness
2210.04311 (2022-10)
Pruning Adversarially Robust Neural Networks without Adversarial Examples
and 5 more not named here
activations_extraction 2 other papers
2 later
2106.02734 (2021-06)
Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness
2210.04311 (2022-10)
Pruning Adversarially Robust Neural Networks without Adversarial Examples
kernelmat 1 other paper
1 later
2106.01939 (2021-06)
Causal Effect Inference for Structured Treatments

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1908.01580")
get_code_for_paper("1908.01580")
have("1908.01580")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1908.01580.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1908.01580.svg)](https://syntology.ai/paper/1908.01580)

Connect an agent — have() is free.