Papers › Normalizing Flows for Knockoff-free Controlled Feature Selection

Normalizing Flows for Knockoff-free Controlled Feature Selection

3 Jun 2021arXiv:2106.01528archive 2025-07-28

Derek Hansen, Brian Manzo, Jeffrey Regier

Controlled feature selection aims to discover the features a response depends on while limiting the false discovery rate (FDR) to a predefined level. Recently, multiple deep-learning-based methods have been proposed to perform controlled feature selection through the Model-X knockoff framework. We demonstrate, however, that these methods often fail to control the FDR for two reasons. First, these methods often learn inaccurate models of features. Second, the "swap" property, which is required for knockoffs to be valid, is often not well enforced. We propose a new procedure called FlowSelect to perform controlled feature selection that does not suffer from either of these two problems. To more accurately model the features, FlowSelect uses normalizing flows, the state-of-the-art method for density estimation. Instead of enforcing the "swap" property, FlowSelect uses a novel MCMC-based procedure to calculate p-values for each feature directly. Asymptotically, FlowSelect computes valid p-values. Empirically, FlowSelect consistently controls the FDR on both synthetic and semi-synthetic benchmarks, whereas competing knockoff-based approaches do not. FlowSelect also demonstrates greater power on these benchmarks. Additionally, FlowSelect correctly infers the genetic variants associated with specific soybean traits from GWAS data.

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.

Syntology holds a reference implementation of FLOWSELECT, generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='FLOWSELECT') (how to connect); the free check have('2106.01528') needs no token.

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

Code

The archive's official repository (dereklhansen/flowselect) was not harvested; the 33 samples below come from 3 repositories the archive does not mark official.

Syntology 33 code samples harvested from 3 repositories linked to this paper: 25 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 13 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 6 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 33 samples from 3 repositories, 25 ran (12 with no instrument failure; 13 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.

dereklhansen/flowselect officialmentioned in papermentioned on GitHubpytorchSyntology: 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

33 samples harvested: 25 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 13 where Syntology's instrument failed) · 8 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
7ran · our draft was wrong
6ran; the contract check could not run
9ran
8unverified

Licence: 11 of the 33 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 3 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. 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.

msesia/deepknockoffs found in paper text by Syntology 10 samples, 8 ran (5 instrument-failed) · 2 unverified
Net in 54 papers DeepKnockoffs/DeepKnockoffs/machine.py ran · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only · 44a37c78381afc80 · report fixture: returned Net · level recorded 2026-09-22
_mix_rbf_kernel DeepKnockoffs/DeepKnockoffs/machine.py ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 48dd34f19c1766db · report fixture: signature X:Tensor/2/float, Y:Tensor/2/float, sigma_list:list/1/float · returned tuple · level recorded 2026-09-22
_mmd2 DeepKnockoffs/DeepKnockoffs/machine.py ran; the contract check could not run (RAISES) fingerprinted GPL-3.0 (copyleft) · pointer only · ce10f353f05f5250 · report fixture: signature K_XX:Tensor/2/float, K_XY:Tensor/2/float, K_YY:Tensor/2/float, const_diagonal:bool/0/bool, biased:bool/0/bool · returned Tensor · level recorded 2026-09-22
covariance_diff_biased DeepKnockoffs/DeepKnockoffs/machine.py ran · violated contract GPL-3.0 (copyleft) · pointer only · 2e39bc098a25ff99 · report fixture: signature X:Tensor/2/float, Xk:Tensor/2/float, SigmaHat:Tensor/2/float, Mask:Tensor/2/float, scale:float/0/float · returned Tensor · level recorded 2026-09-22
gen_batches DeepKnockoffs/DeepKnockoffs/machine.py ran · honoured contract fingerprinted GPL-3.0 (copyleft) · pointer only · a10785afdd1943d9 · report fixture: signature n_samples:int/0/int, batch_size:int/0/int, n_reps:int/0/int · returned list · level recorded 2026-09-22
mix_rbf_mmd2 in 6 papers DeepKnockoffs/DeepKnockoffs/machine.py ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 661038d37be136e9 · report fixture: signature X:Tensor/2/float, Y:Tensor/2/float, sigma_list:list/1/float, biased:bool/0/bool · returned Tensor · level recorded 2026-09-22
mix_rbf_mmd2_loss DeepKnockoffs/DeepKnockoffs/machine.py ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 6817b2d2b5a8ba50 · report fixture: signature X:Tensor/2/float, Y:Tensor/2/float, sigma_list:list/1/float, biased:bool/0/bool · returned Tensor · level recorded 2026-09-22
norm in 120 papers
census: 23 implementations from 26 papers, 15 distinct outputs across 6 buckets, one shared input per bucket this sample: bucket 1 of 6, arg 1: rank 2, kind float, dtype float32
DeepKnockoffs/DeepKnockoffs/machine.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted GPL-3.0 (copyleft) · pointer only · e1d9c760ce9d1c42 · report fixture: signature X:Tensor/2/float, p:int/0/int · returned Tensor · level recorded 2026-09-22
KnockoffMachine DeepKnockoffs/DeepKnockoffs/machine.py unverified GPL-3.0 (copyleft) · pointer only · e61b4c8c3d64412e · report
save_checkpoint in 36 papers DeepKnockoffs/DeepKnockoffs/machine.py unverified GPL-3.0 (copyleft) · pointer only · 96f1fefe68df3674 · report
tansey/hrt found in paper text by Syntology 22 samples, 17 ran (8 instrument-failed) · 5 unverified
BootstrapConditionalModel pyhrt/hrt.py ran MIT (permissive) · 5c388071175a785e · report fixture: returned BootstrapConditionalModel · level recorded 2026-09-22
CrossValidationSampler pyhrt/hrt.py ran MIT (permissive) · db6d9a8444f8edbd · report fixture: returned CrossValidationSampler · level recorded 2026-09-22
DiscreteBootstrapConditionalModel pyhrt/hrt.py ran MIT (permissive) · befe2dc54f127a04 · report fixture: returned DiscreteBootstrapConditionalModel · level recorded 2026-09-22
DiscreteClassifierNetwork pyhrt/hrt.py ran fingerprinted MIT (permissive) · aa9395158d2da40a · report fixture: returned DiscreteClassifierNetwork · level recorded 2026-09-22
GaussianMixtureModel pyhrt/hrt.py ran MIT (permissive) · d01652f4c7968e16 · report fixture: returned GaussianMixtureModel · level recorded 2026-09-22
HoldoutSampler pyhrt/hrt.py ran MIT (permissive) · 02fd42887a52a943 · report fixture: returned HoldoutSampler · level recorded 2026-09-22
MixtureDensityNetwork pyhrt/hrt.py ran fingerprinted MIT (permissive) · cbe098cac4a6fd68 · report fixture: returned MixtureDensityNetwork · level recorded 2026-09-22
MultinomialModel pyhrt/hrt.py ran MIT (permissive) · e117979a67e9dbec · report fixture: returned MultinomialModel · level recorded 2026-09-22
batches pyhrt/hrt.py ran · our draft was wrong MIT (permissive) · ff0fb920ccf5b064 · report fixture: signature indices:ndarray/1/int, batch_size:int/0/int, shuffle:bool/0/bool · returned generator · level recorded 2026-09-22
create_folds in 5 papers pyhrt/hrt.py ran · our draft was wrong fingerprinted MIT (permissive) · d9996f0a1157eaa1 · report fixture: signature X:ndarray/2/int, k:int/0/int · returned list · level recorded 2026-09-22
ks_test pyhrt/hrt.py ran · honoured contract fingerprinted MIT (permissive) · a929f8158e0f37f5 · report fixture: signature ksstat:float/0/float, nsamples:int/0/int, ntrials:int/0/int · returned float64 · level recorded 2026-09-22
logsumexp in 55 papers
census: 8 implementations from 12 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
pyhrt/hrt.py ran · our draft was wrong MIT (permissive) · c73bee7360661346 · report fixture: signature inputs:Tensor/2/float, dim:int/0/int, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-22
matrix_str pyhrt/hrt.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · db0aefbe8dbc29a8 · report fixture: signature p:ndarray/2/float, decimal_places:int/0/int, ignore:NoneType/0/?, label_columns:bool/0/bool · returned str · level recorded 2026-09-22
pretty_str pyhrt/hrt.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · ab49a597c1aff75c · report fixture: signature p:Tensor/2/float, decimal_places:int/0/int, ignore:NoneType/0/?, label_columns:bool/0/bool · returned str · level recorded 2026-09-22
sample_holdout_dists pyhrt/hrt.py ran · our draft was wrong MIT (permissive) · 45caf0e3cf7297ea · report fixture: signature dists:list/1/MockDistribution, model:NoneType/0/?, quantiles:list/1/int · returned tuple · level recorded 2026-09-22
tv_test pyhrt/hrt.py ran; the contract check could not run (RAISES) MIT (permissive) · b4c04d0603c1c2db · report fixture: signature tvstat:float/0/float, marginals:ndarray/1/float, nsamples:int/0/int, ntrials:int/0/int · returned float64 · level recorded 2026-09-22
vector_str pyhrt/hrt.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · e69ab4938b9c4680 · report fixture: signature p:list/1/float, decimal_places:int/0/int, ignore:list/1/float · returned str · level recorded 2026-09-22
calibrate_continuous pyhrt/hrt.py unverified MIT (permissive) · c7dde2181bd90c3f · report
calibrate_discrete pyhrt/hrt.py unverified MIT (permissive) · 450d25e7824a48dc · report
fit_classifier pyhrt/hrt.py unverified MIT (permissive) · 0cddd24f3b7ed39a · report
fit_mdn pyhrt/hrt.py unverified MIT (permissive) · 4d0755e27691fb59 · report
hrt pyhrt/hrt.py unverified MIT (permissive) · 2e296d67a46288e5 · report
firmai/tsgan found in paper text by Syntology 1 sample, 0 ran · 1 unverified
KnockoffGAN alg/knockoffgan/KnockoffGAN.py unverified licence not identified · pointer only · a78618a3a2bcc9c2 · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". 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. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

3 assemblies on this paper: 2 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for FLOWSELECT (graph method: FLOWSELECT), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. metropolis_hastings_acceptance_ratio entry · level 2 · ran · our draft was wrong · aa8e13184a001df379d42d094838939f5fd13d1aa08190f8e38cf3e7a2af8c3a

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

harvested Assembly for FLOWSELECT (graph method: FLOWSELECT). 10 bricks; individually on a fixture: 8 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. KnockoffMachine entry · level 0 · unverified · e61b4c8c3d64412e
  2. Net model · level 1 · ran · 44a37c78381afc80
  3. covariance_diff_biased loss · level 1 · ran · violated contract · 2e39bc098a25ff99
  4. gen_batches helper · level 1 · ran · honoured contract · a10785afdd1943d9
  5. mix_rbf_mmd2_loss helper · level 1 · ran · our draft was wrong · 6817b2d2b5a8ba50
  6. norm helper · level 1 · ran; the contract check could not run (RAISES) · e1d9c760ce9d1c42
  7. save_checkpoint helper · level 0 · unverified · 96f1fefe68df3674
  8. mix_rbf_mmd2 helper · level 1 · ran · our draft was wrong · 661038d37be136e9
  9. _mix_rbf_kernel helper · level 1 · ran · our draft was wrong · 48dd34f19c1766db
  10. _mmd2 helper · level 1 · ran; the contract check could not run (RAISES) · ce10f353f05f5250

harvested Assembly for FLOWSELECT (graph method: FLOWSELECT). 22 bricks; individually on a fixture: 17 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. hrt entry · level 0 · unverified · 2e296d67a46288e5
  2. calibrate_continuous model · level 0 · unverified · c7dde2181bd90c3f
  3. calibrate_discrete model · level 0 · unverified · 450d25e7824a48dc
  4. pretty_str helper · level 1 · ran; the contract check could not run (RAISES) · ab49a597c1aff75c
  5. BootstrapConditionalModel helper · level 1 · ran · 5c388071175a785e
  6. CrossValidationSampler sampler · level 1 · ran · db6d9a8444f8edbd
  7. HoldoutSampler sampler · level 1 · ran · 02fd42887a52a943
  8. create_folds helper · level 1 · ran · our draft was wrong · d9996f0a1157eaa1
  9. fit_mdn helper · level 0 · unverified · 4d0755e27691fb59
  10. ks_test helper · level 1 · ran · honoured contract · a929f8158e0f37f5
  11. DiscreteBootstrapConditionalModel helper · level 1 · ran · befe2dc54f127a04
  12. fit_classifier helper · level 0 · unverified · 0cddd24f3b7ed39a
  13. tv_test helper · level 1 · ran; the contract check could not run (RAISES) · b4c04d0603c1c2db
  14. matrix_str helper · level 1 · ran; the contract check could not run (RAISES) · db0aefbe8dbc29a8
  15. vector_str helper · level 1 · ran; the contract check could not run (RAISES) · e69ab4938b9c4680
  16. sample_holdout_dists helper · level 1 · ran · our draft was wrong · 45caf0e3cf7297ea
  17. MixtureDensityNetwork helper · level 1 · ran · cbe098cac4a6fd68
  18. batches helper · level 1 · ran · our draft was wrong · ff0fb920ccf5b064
  19. logsumexp helper · level 1 · ran · our draft was wrong · c73bee7360661346
  20. DiscreteClassifierNetwork helper · level 1 · ran · aa9395158d2da40a
  21. GaussianMixtureModel helper · level 1 · ran · d01652f4c7968e16
  22. MultinomialModel helper · level 1 · ran · e117979a67e9dbec

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="2106.01528") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Density Estimationfeature selection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Feature Selection

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