Papers › NICE: Non-linear Independent Components Estimation

NICE: Non-linear Independent Components Estimation

30 Oct 2014arXiv:1410.8516archive 2025-07-28

Laurent Dinh, David Krueger, Yoshua Bengio

We propose a deep learning framework for modeling complex high-dimensional densities called Non-linear Independent Component Estimation (NICE). It is based on the idea that a good representation is one in which the data has a distribution that is easy to model. For this purpose, a non-linear deterministic transformation of the data is learned that maps it to a latent space so as to make the transformed data conform to a factorized distribution, i.e., resulting in independent latent variables. We parametrize this transformation so that computing the Jacobian determinant and inverse transform is trivial, yet we maintain the ability to learn complex non-linear transformations, via a composition of simple building blocks, each based on a deep neural network. The training criterion is simply the exact log-likelihood, which is tractable. Unbiased ancestral sampling is also easy. We show that this approach yields good generative models on four image datasets and can be used for inpainting.

PaperPDFCodeCode Syntology ranMethod as code

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 27 code samples harvested from 8 repositories linked to this paper: 24 ran (of which 16 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 27 samples from 8 repositories, 24 ran (19 with no instrument failure; 5 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

DakshIdnani/pytorch-nice mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
HUJI-Deep/nice mentioned on GitHubBSD-3-ClauseSyntology: not harvested report
MStypulkowski/mlinpl-generative-workshop mentioned on GitHubSyntology: not harvested report
SrinjaySarkar/NICE mentioned on GitHubpytorchSyntology: not harvested report
claCase/NormalizingFlow mentioned on GitHubtfSyntology: not harvested report
ermongroup/a-nice-mc mentioned on GitHubtfSyntology: not harvested report
fmu2/NICE mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
gmum/nice_pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jfcrenshaw/pzflow mentioned on GitHubjaxSyntology: 7 samples, 6 ran (2 instrument-failed) · 1 unverified report
jiamings/a-nice-mc mentioned on GitHubtfSyntology: not harvested report
laurent-dinh/nice mentioned on GitHubBSD-3-ClauseSyntology: not harvested report
paultsw/nice_pytorch mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (2 instrument-failed) · 0 unverified report
simonwestberg/DD2412-Glow mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Density estimation using Real NVP (arXiv:1605.08803; that paper's own run record: 48 ran (of which 26 constructed an object rather than computing a result; 38 with no instrument failure: 2 honoured, 0 violated, 36 with no contract checked; 10 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
simonwestberg/Glow mentioned on GitHubtfSyntology: not harvested report
vincentstimper/normalizing-flows mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
gitlab.com/i-flow/i-flow mentioned on GitHubtfSyntology: not harvested report
EugenHotaj/pytorch-generative pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MADE: Masked Autoencoder for Distribution Estimation (arXiv:1502.03509; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified), Neural Autoregressive Distribution Estimation (arXiv:1605.02226; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified), Conditional Image Generation with PixelCNN Decoders (arXiv:1606.05328; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
MaximeVandegar/Papers-in-100-Lines-of-Code pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
g4vrel/simple_ml pytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 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.

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

27 samples harvested: 24 ran (of which 16 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 5 where Syntology's instrument failed) · 3 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.

3ran · our draft was wrong
2ran; the contract check could not run
19ran
3unverified

Licence: 0 of the 27 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 8 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”. For 11 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

DakshIdnani/pytorch-nice community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
CouplingLayer in 11 papers nice.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · a1e6e98c3d08e03f · report fixture: returned CouplingLayer · level recorded 2026-09-22
LogisticDistribution nice.py ran MIT (permissive) · 5d1d5872e739c007 · report fixture: returned LogisticDistribution · level recorded 2026-09-22
NICE nice.py ran fingerprinted MIT (permissive) · 797c85f9a30a07bd · report fixture: returned NICE · level recorded 2026-09-22
ScalingLayer nice.py ran · metamorphic tier: deterministic MIT (permissive) · 73acddb22c061b6a · report fixture: signature x:Tensor/2/float, logdet:Tensor/0/float, invert:bool/0/bool · returned tuple · level recorded 2026-09-22
fmu2/NICE community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Coupling in 7 papers nice.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · feb422919519eb2a · report fixture: returned Coupling · level recorded 2026-09-22
NICE nice.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · b95df537e4a2a1f4 · report fixture: returned NICE · level recorded 2026-09-22
Scaling nice.py ran · metamorphic tier: deterministic MIT (permissive) · 618382e0d811f2d8 · report fixture: returned Scaling · level recorded 2026-09-22
gmum/nice_pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
NICEModel nice/models.py ran · metamorphic tier: deterministic BSD-3-Clause (permissive) · 7e47833eba9e3d69 · report fixture: returned NICEModel · level recorded 2026-09-22
jfcrenshaw/pzflow community (archive-listed) 7 samples, 6 ran (2 instrument-failed) · 1 unverified
Bijector pzflow/bijectors.py ran MIT (permissive) · 3927f3ad56e8701b · report fixture: returned Bijector · level recorded 2026-09-22
DenseReluNetwork pzflow/bijectors.py ran · our draft was wrong MIT (permissive) · bdbe5e7ec83debb6 · report fixture: signature out_dim:int/0/int, hidden_layers:int/0/int, hidden_dim:int/0/int · returned tuple · level recorded 2026-09-22
ForwardFunction pzflow/bijectors.py ran fingerprinted MIT (permissive) · 9d4c6ab46065ae74 · report fixture: returned ForwardFunction · level recorded 2026-09-22
InitFunction pzflow/bijectors.py ran MIT (permissive) · 7e3e6278ac1d8af6 · report fixture: returned InitFunction · level recorded 2026-09-22
InverseFunction pzflow/bijectors.py ran fingerprinted MIT (permissive) · e19df3b31e4e1bd2 · report fixture: returned InverseFunction · level recorded 2026-09-22
RationalQuadraticSpline pzflow/bijectors.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · d1680a8d472444f5 · report fixture: signature inputs:ArrayImpl/2/float, W:ArrayImpl/3/float, H:ArrayImpl/3/float, D:ArrayImpl/3/float, B:float/0/float, periodic:bool/0/bool, inverse:bool/0/bool · returned tuple · level recorded 2026-09-22
NeuralSplineCoupling pzflow/bijectors.py unverified MIT (permissive) · d79d72f0b9ce6c77 · report
paultsw/nice_pytorch community (archive-listed) 5 samples, 5 ran (2 instrument-failed) · 0 unverified
AdditiveCouplingLayer nice/models.py ran · metamorphic tier: deterministic fingerprinted BSD-3-Clause (permissive) · 2a75e5263cb27fc7 · report fixture: returned AdditiveCouplingLayer · level recorded 2026-09-22
NICEModel nice/models.py ran · metamorphic tier: deterministic BSD-3-Clause (permissive) · 288bd9ac482f455f · report fixture: returned NICEModel · level recorded 2026-09-22
_BaseCouplingLayer nice/models.py ran · metamorphic tier: deterministic BSD-3-Clause (permissive) · ede51f79ec51199b · report fixture: returned _BaseCouplingLayer · level recorded 2026-09-22
_build_relu_network nice/models.py ran · our draft was wrong BSD-3-Clause (permissive) · 419f30152991aee7 · report fixture: signature latent_dim:int/0/int, hidden_dim:int/0/int, num_layers:int/0/int · returned Sequential · level recorded 2026-09-22
_interleave nice/models.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted BSD-3-Clause (permissive) · acffc3df688ea63f · report fixture: signature first:Tensor/2/float, second:Tensor/2/float, order:str/0/str · returned Tensor · level recorded 2026-09-22
vincentstimper/normalizing-flows community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
AffineCoupling in 5 papers normflows/flows/affine/coupling.py ran · metamorphic tier: deterministic MIT (permissive) · 3c08d19a3ff50fa8 · report fixture: signature z:list/1/Tensor · returned tuple · level recorded 2026-09-22
zero_log_det_like_z normflows/flows/affine/coupling.py ran · our draft was wrong fingerprinted MIT (permissive) · 3c2a36e9a28c16f0 · report fixture: signature z:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Flow in 10 papers normflows/flows/affine/coupling.py unverified MIT (permissive) · 5886cd39dfbd797e · report
MaximeVandegar/Papers-in-100-Lines-of-Code community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
NICE NICE_Non_linear_Independent_Components_Estimation/NICE.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 1a1bcb9945e07fb5 · report fixture: signature x:Tensor/2/float · returned tuple · level recorded 2026-09-22
g4vrel/simple_ml community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
ACL NICE/nice.py ran MIT (permissive) · cdc21e5b776e57dd · report fixture: returned ACL · level recorded 2026-09-22
MLP in 375 papers NICE/nice.py ran MIT (permissive) · 33b882451180d1c9 · report fixture: returned MLP · level recorded 2026-09-22
NICE NICE/nice.py unverified MIT (permissive) · 8fca3630fcfef7f1 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

8 assemblies on this paper: 8 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

8 sibling assemblies for NICE (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for NICE (graph method: NICE). 5 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. NICEModel entry · level 1 · ran · 288bd9ac482f455f
  2. AdditiveCouplingLayer helper · level 1 · ran · 2a75e5263cb27fc7
  3. _build_relu_network helper · level 1 · ran · our draft was wrong · 419f30152991aee7
  4. _BaseCouplingLayer helper · level 1 · ran · ede51f79ec51199b
  5. _interleave helper · level 1 · ran; the contract check could not run (RAISES) · acffc3df688ea63f

harvested Assembly for NICE (graph method: NICE). 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 8 siblings

  1. NICE entry · level 1 · ran · b95df537e4a2a1f4
  2. Coupling model · level 1 · ran · feb422919519eb2a
  3. Scaling model · level 1 · ran · 618382e0d811f2d8

harvested Assembly for NICE (graph method: NICE). 4 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. NICE entry · level 1 · ran · 797c85f9a30a07bd
  2. CouplingLayer model · level 1 · ran · a1e6e98c3d08e03f
  3. LogisticDistribution model · level 1 · ran · 5d1d5872e739c007
  4. ScalingLayer model · level 1 · ran · 73acddb22c061b6a

harvested Assembly for NICE (graph method: NICE). 5 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. NICEModel entry · level 1 · ran · 7e47833eba9e3d69
  2. AdditiveCouplingLayer model · level 1 · ran · 2a75e5263cb27fc7
  3. _build_relu_network helper · level 1 · ran · our draft was wrong · 419f30152991aee7
  4. _BaseCouplingLayer helper · level 1 · ran · ede51f79ec51199b
  5. _interleave helper · level 1 · ran; the contract check could not run (RAISES) · acffc3df688ea63f

harvested Assembly for NICE (graph method: NICE). 3 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 8 siblings

  1. NICE entry · level 0 · unverified · 8fca3630fcfef7f1
  2. ACL model · level 1 · ran · cdc21e5b776e57dd
  3. MLP model · level 1 · ran · 33b882451180d1c9

harvested Assembly for NICE (graph method: NICE). 7 bricks; individually on a fixture: 6 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. NeuralSplineCoupling entry · level 0 · unverified · d79d72f0b9ce6c77
  2. Bijector helper · level 1 · ran · 3927f3ad56e8701b
  3. DenseReluNetwork helper · level 1 · ran · our draft was wrong · bdbe5e7ec83debb6
  4. ForwardFunction helper · level 1 · ran · 9d4c6ab46065ae74
  5. InitFunction helper · level 1 · ran · 7e3e6278ac1d8af6
  6. InverseFunction helper · level 1 · ran · e19df3b31e4e1bd2
  7. RationalQuadraticSpline helper · level 1 · ran; the contract check could not run (RAISES) · d1680a8d472444f5

harvested Assembly for NICE (graph method: NICE). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. NICE entry · level 1 · ran · 1a1bcb9945e07fb5

harvested Assembly for NICE (graph method: NICE). 3 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. AffineCoupling entry · level 1 · ran · 3c08d19a3ff50fa8
  2. Flow helper · level 0 · unverified · 5886cd39dfbd797e
  3. zero_log_det_like_z helper · level 1 · ran · our draft was wrong · 3c2a36e9a28c16f0

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1410.8516") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: NICE

Affine CouplingNICE

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