Papers › Learning Group Importance using the Differentiable Hypergeometric Distribution

Learning Group Importance using the Differentiable Hypergeometric Distribution

3 Mar 2022arXiv:2203.01629archive 2025-07-28

Thomas M. Sutter, Laura Manduchi, Alain Ryser, Julia E. Vogt

Partitioning a set of elements into subsets of a priori unknown sizes is essential in many applications. These subset sizes are rarely explicitly learned - be it the cluster sizes in clustering applications or the number of shared versus independent generative latent factors in weakly-supervised learning. Probability distributions over correct combinations of subset sizes are non-differentiable due to hard constraints, which prohibit gradient-based optimization. In this work, we propose the differentiable hypergeometric distribution. The hypergeometric distribution models the probability of different group sizes based on their relative importance. We introduce reparameterizable gradients to learn the importance between groups and highlight the advantage of explicitly learning the size of subsets in two typical applications: weakly-supervised learning and clustering. In both applications, we outperform previous approaches, which rely on suboptimal heuristics to model the unknown size of groups.

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 11 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 5 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: official repository: 11 samples from 1 repository, 6 ran (1 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.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 6 samples that ran has no recorded date.

thomassutter/mvhg officialmentioned in papermentioned on GitHubpytorchSyntology: 11 samples, 6 ran (5 instrument-failed) · 5 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

11 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 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
3ran · our draft was wrong
2ran; the contract check could not run
5unverified

Licence: 0 of the 11 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 thomassutter/mvhg. “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.

thomassutter/mvhg official repository 11 samples, 6 ran (5 instrument-failed) · 5 unverified
calc_group_w_m mvhg/tf_fmvhg.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · fc3dba973f801ca8 · report fixture: signature m_group:EagerTensor/3/float, log_w_group:EagerTensor/3/float · returned tuple · level recorded 2026-09-22
get_dataloader in 111 papers main_minimal_app.py ran · our draft was wrong MIT (permissive) · d30acb3cc58f6973 · report fixture: signature samples:ndarray/2/float, w_all:Tensor/1/float, batch_size:int/0/int · returned tuple · level recorded, date not recorded
get_hside_check mvhg/tf_fmvhg.py ran · our draft was wrong MIT (permissive) · 76f62156d24e3bbe · report fixture: signature n:SymbolicTensor/2/float, x_i:SymbolicTensor/2/float, m_r:SymbolicTensor/2/float · returned SymbolicTensor · level recorded 2026-09-22
gumbel_softmax in 82 papers
census: 19 implementations from 20 papers, 12 distinct outputs across 2 buckets, one shared input per bucket
mvhg/tf_fmvhg.py ran · honoured contract MIT (permissive) · 6145a3352a4a5eba · report fixture: signature logits:SymbolicTensor/3/float, temp:float/0/float, hard:bool/0/bool, add_noise:bool/0/bool · returned tuple · level recorded 2026-09-22
heaviside in 8 papers mvhg/tf_fmvhg.py ran · our draft was wrong MIT (permissive) · 2d35babdf0eed62d · report fixture: signature x:SymbolicTensor/2/float, g:Graph/0/? · returned SymbolicTensor · level recorded 2026-09-22
sample_gumbel in 62 papers mvhg/tf_fmvhg.py ran; the contract check could not run (RAISES) MIT (permissive) · e3b566f38adb8596 · report fixture: signature shape:tuple/1/int, eps:float/0/float · returned EagerTensor · level recorded 2026-09-22
create_data in 5 papers main_minimal_app.py unverified MIT (permissive) · e9004c814450d0d7 · report
get_log_p_x_i mvhg/tf_fmvhg.py unverified MIT (permissive) · 8c62b9743c2ad649 · report
get_logits in 19 papers mvhg/tf_fmvhg.py unverified MIT (permissive) · 96e425bda34c91d8 · report
get_probability mvhg/tf_fmvhg.py unverified MIT (permissive) · 6b46f86f168667b7 · report
pmf_noncentral_fmvhg mvhg/tf_fmvhg.py unverified MIT (permissive) · 121b9b77441dfd95 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

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

  1. pmf_noncentral_fmvhg entry · level 0 · unverified · 121b9b77441dfd95
  2. calc_group_w_m helper · level 1 · ran; the contract check could not run (RAISES) · fc3dba973f801ca8
  3. get_hside_check helper · level 1 · ran · our draft was wrong · 76f62156d24e3bbe
  4. get_logits helper · level 0 · unverified · 96e425bda34c91d8
  5. get_probability helper · level 0 · unverified · 6b46f86f168667b7
  6. gumbel_softmax helper · level 1 · ran · honoured contract · 6145a3352a4a5eba
  7. heaviside helper · level 1 · ran · our draft was wrong · 2d35babdf0eed62d
  8. get_log_p_x_i helper · level 0 · unverified · 8c62b9743c2ad649
  9. sample_gumbel helper · level 1 · ran; the contract check could not run (RAISES) · e3b566f38adb8596

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="2203.01629") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ClusteringSelection biasWeakly-supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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