Papers › Neural Conditional Probability for Uncertainty Quantification

Neural Conditional Probability for Uncertainty Quantification

1 Jul 2024arXiv:2407.01171archive 2025-07-28

Vladimir R. Kostic, Karim Lounici, Gregoire Pacreau, Pietro Novelli, Giacomo Turri, Massimiliano Pontil

We introduce Neural Conditional Probability (NCP), an operator-theoretic approach to learning conditional distributions with a focus on statistical inference tasks. NCP can be used to build conditional confidence regions and extract key statistics such as conditional quantiles, mean, and covariance. It offers streamlined learning via a single unconditional training phase, allowing efficient inference without the need for retraining even when conditioning changes. By leveraging the approximation capabilities of neural networks, NCP efficiently handles a wide variety of complex probability distributions. We provide theoretical guarantees that ensure both optimization consistency and statistical accuracy. In experiments, we show that NCP with a 2-hidden-layer network matches or outperforms leading methods. This demonstrates that a a minimalistic architecture with a theoretically grounded loss can achieve competitive results, even in the face of more complex architectures.

PaperPDFCode 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 22 code samples harvested from 3 repositories linked to this paper: 17 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 11 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 22 samples from 3 repositories, 17 ran (6 with no instrument failure; 11 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.

CSML-IIT-UCL/NCP found in paper text by SyntologySyntology: 10 samples, 9 ran (5 instrument-failed) · 1 unverified report
lee-group-cmu/NNKCDE found in paper text by SyntologySyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
lee-group-cmu/FlexCode found in paper text by SyntologySyntology: 10 samples, 7 ran (5 instrument-failed) · 3 unverified report
ZijunGao/LinCDE found in paper text by SyntologySyntology: not harvested 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

22 samples harvested: 17 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 11 where Syntology's instrument failed) · 5 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.

1ran · honoured contract
2ran · violated contract
7ran · our draft was wrong
4ran; the contract check could not run
3ran
5unverified

Licence: 22 of the 22 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 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”. For 1 sample 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.

CSML-IIT-UCL/NCP found in paper text by Syntology 10 samples, 9 ran (5 instrument-failed) · 1 unverified
NCPOperator NCP/model.py ran no licence file found · pointer only · 5a945c81cf02322b · report fixture: returned NCPOperator · level recorded 2026-09-22
SingularLayer NCP/model.py ran fingerprinted no licence file found · pointer only · 0eee2a4d029c1104 · report fixture: returned SingularLayer · level recorded 2026-09-22
TopKReturnType NCP/model.py ran no licence file found · pointer only · e3f9c741e1884e63 · report fixture: returned TopKReturnType · level recorded 2026-09-22
ensure_torch NCP/model.py ran · violated contract fingerprinted no licence file found · pointer only · a70a1a2899dfa603 · report fixture: signature x:list/1/float · returned Tensor · level recorded 2026-09-22
filter_reduced_rank_svals NCP/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 3a07f048b41f2cd1 · report fixture: signature values:Tensor/1/float, vectors:Tensor/2/float · returned tuple · level recorded 2026-09-22
frnp NCP/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 6cca2cf1db8a2456 · report fixture: signature x:ndarray/2/float, device:NoneType/0/? · returned Tensor · level recorded 2026-09-22
sqrtmh NCP/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f8320b9a55f263b9 · report fixture: signature A:Tensor/2/float · returned Tensor · level recorded 2026-09-22
tonp in 10 papers NCP/model.py ran · our draft was wrong no licence file found · pointer only · 12f203b46fecc22d · report fixture: signature x:Tensor/2/float · returned ndarray · level recorded 2026-09-22
topk in 19 papers NCP/model.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 5cb70d0fe9e95c27 · report fixture: signature vec:Tensor/1/float, k:int/0/int · returned TopKReturnType · level recorded 2026-09-22
cross_cov NCP/model.py unverified no licence file found · pointer only · ed348884e63a844a · report
lee-group-cmu/NNKCDE found in paper text by Syntology 2 samples, 1 ran (1 instrument-failed) · 1 unverified
kde in 6 papers python/src/nnkcde/core.py ran; the contract check could not run (RAISES) no licence file found · pointer only · ef6f976bc872ec2c · report fixture: signature responses:ndarray/2/float, grid:ndarray/2/float, bandwidth:str/0/str · returned ndarray · level recorded 2026-09-22
NNKCDE python/src/nnkcde/core.py unverified no licence file found · pointer only · 8104876ddda996f6 · report
lee-group-cmu/FlexCode found in paper text by Syntology 10 samples, 7 ran (5 instrument-failed) · 3 unverified
box_transform src/flexcode/core.py ran · violated contract fingerprinted GPL-2.0 (copyleft) · pointer only · 32abafc5e441e582 · report fixture: signature z:ndarray/1/float, z_min:float/0/float, z_max:float/0/float · returned ndarray · level recorded 2026-09-22
cde_loss src/flexcode/core.py ran; the contract check could not run (RAISES) GPL-2.0 (copyleft) · pointer only · 10792a494a7f3b4b · report fixture: signature cde_estimates:ndarray/2/float, z_grid:ndarray/1/float, true_z:ndarray/1/float · returned float64 · level recorded 2026-09-22
cosine_basis src/flexcode/core.py ran · our draft was wrong fingerprinted GPL-2.0 (copyleft) · pointer only · 617ff62972595603 · report fixture: signature responses:ndarray/2/float, n_basis:int/0/int · returned ndarray · level recorded 2026-09-22
fourier_basis src/flexcode/core.py ran · our draft was wrong fingerprinted GPL-2.0 (copyleft) · pointer only · 67ec048966977d12 · report fixture: signature responses:ndarray/2/float, n_basis:int/0/int · returned ndarray · level recorded 2026-09-22
make_grid in 27 papers src/flexcode/core.py ran · honoured contract fingerprinted GPL-2.0 (copyleft) · pointer only · 83826ed517001ce4 · report fixture: signature n_grid:int/0/int, z_min:float/0/float, z_max:float/0/float · returned ndarray · level recorded 2026-09-22
tensor_basis src/flexcode/core.py ran · our draft was wrong GPL-2.0 (copyleft) · pointer only · 8dc81d781fb203c8 · report fixture: signature responses:ndarray/2/float, n_basis:list/1/int, basis_fn:callable/0/? · returned ndarray · level recorded 2026-09-22
wavelet_basis src/flexcode/core.py ran; the contract check could not run (RAISES) GPL-2.0 (copyleft) · pointer only · 3d2fc4ac3ae78854 · report fixture: signature responses:ndarray/1/float, n_basis:int/0/int, family:str/0/str · returned ndarray · level recorded 2026-09-22
BasisCoefs src/flexcode/core.py unverified GPL-2.0 (copyleft) · pointer only · 092df1eff806e58d · report
FlexCodeModel src/flexcode/core.py unverified GPL-2.0 (copyleft) · pointer only · 3e6c220b84182e13 · report
evaluate_basis src/flexcode/core.py unverified GPL-2.0 (copyleft) · pointer only · bc3221ff9022ccf8 · 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.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for Neural Conditional Probability (NCP) (graph method: Neural Conditional Probability (NCP)). 10 bricks; individually on a fixture: 9 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. NCPOperator entry · level 1 · ran · 5a945c81cf02322b
  2. SingularLayer helper · level 1 · ran · 0eee2a4d029c1104
  3. cross_cov helper · level 0 · unverified · ed348884e63a844a
  4. ensure_torch helper · level 1 · ran · violated contract · a70a1a2899dfa603
  5. filter_reduced_rank_svals helper · level 1 · ran · our draft was wrong · 3a07f048b41f2cd1
  6. sqrtmh helper · level 1 · ran · our draft was wrong · f8320b9a55f263b9
  7. tonp helper · level 1 · ran · our draft was wrong · 12f203b46fecc22d
  8. frnp helper · level 1 · ran · our draft was wrong · 6cca2cf1db8a2456
  9. topk helper · level 1 · ran; the contract check could not run (RAISES) · 5cb70d0fe9e95c27
  10. TopKReturnType helper · level 1 · ran · e3f9c741e1884e63

harvested Assembly for Neural Conditional Probability (NCP) (graph method: Neural Conditional Probability (NCP)). 10 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. FlexCodeModel entry · level 0 · unverified · 3e6c220b84182e13
  2. BasisCoefs helper · level 0 · unverified · 092df1eff806e58d
  3. box_transform helper · level 1 · ran · violated contract · 32abafc5e441e582
  4. cde_loss loss · level 1 · ran; the contract check could not run (RAISES) · 10792a494a7f3b4b
  5. evaluate_basis helper · level 0 · unverified · bc3221ff9022ccf8
  6. make_grid helper · level 1 · ran · honoured contract · 83826ed517001ce4
  7. cosine_basis helper · level 1 · ran · our draft was wrong · 617ff62972595603
  8. fourier_basis helper · level 1 · ran · our draft was wrong · 67ec048966977d12
  9. tensor_basis helper · level 1 · ran · our draft was wrong · 8dc81d781fb203c8
  10. wavelet_basis helper · level 1 · ran; the contract check could not run (RAISES) · 3d2fc4ac3ae78854

harvested Assembly for Neural Conditional Probability (NCP) (graph method: Neural Conditional Probability (NCP)). 2 bricks; individually on a fixture: 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. The assembly has not been run end-to-end.

one of 3 siblings

  1. NNKCDE entry · level 0 · unverified · 8104876ddda996f6
  2. kde helper · level 1 · ran; the contract check could not run (RAISES) · ef6f976bc872ec2c

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="2407.01171") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Uncertainty Quantification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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