Papers › Variational Sparse Coding with Learned Thresholding

Variational Sparse Coding with Learned Thresholding

7 May 2022arXiv:2205.03665archive 2025-07-28

Kion Fallah, Christopher J. Rozell

Sparse coding strategies have been lauded for their parsimonious representations of data that leverage low dimensional structure. However, inference of these codes typically relies on an optimization procedure with poor computational scaling in high-dimensional problems. For example, sparse inference in the representations learned in the high-dimensional intermediary layers of deep neural networks (DNNs) requires an iterative minimization to be performed at each training step. As such, recent, quick methods in variational inference have been proposed to infer sparse codes by learning a distribution over the codes with a DNN. In this work, we propose a new approach to variational sparse coding that allows us to learn sparse distributions by thresholding samples, avoiding the use of problematic relaxations. We first evaluate and analyze our method by training a linear generator, showing that it has superior performance, statistical efficiency, and gradient estimation compared to other sparse distributions. We then compare to a standard variational autoencoder using a DNN generator on the Fashion MNIST and CelebA datasets

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 16 code samples harvested from 2 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 2 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: 8 samples from 1 repository, 3 ran (2 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 8 samples from 1 repository, 3 ran (0 with no instrument failure; 3 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.

kfallah/variational-sparse-coding officialmentioned in paperpytorchSyntology: 8 samples, 3 ran (1 instrument-failed) · 5 unverified report
kfallah/manifold-contrastive mentioned on GitHubpytorchSyntology: 8 samples, 3 ran (3 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

16 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 10 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 · our draft was wrong
2ran; the contract check could not run
2ran
10unverified

Licence: 16 of the 16 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 2 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”. “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.

kfallah/variational-sparse-coding official repository 8 samples, 3 ran (1 instrument-failed) · 5 unverified
ConvEncoder in 12 papers model/lista.py ran · metamorphic tier: invariant no licence file found · pointer only · 903ea2efea36342b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
MLPEncoder in 8 papers model/lista.py ran · metamorphic tier: invariant no licence file found · pointer only · 06232d415e12a510 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
soft_threshold in 12 papers
census: 4 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
model/lista.py ran · our draft was wrong fingerprinted no licence file found · pointer only · b082bfb3081bcf63 · report fixture: signature c:Tensor/2/float, zeta:Tensor/2/float · returned Tensor · level recorded 2026-09-22
VIEncoder model/lista.py unverified no licence file found · pointer only · b5cc5a076789ea2e · report
VIEncoderLISTA model/lista.py unverified no licence file found · pointer only · bb9d074b88eaaf89 · report
compute_kl in 14 papers model/reparameterization.py unverified no licence file found · pointer only · 592a9f533df33a85 · report
fixed_kl model/reparameterization.py unverified no licence file found · pointer only · 9c18a4838eab1610 · report
vamp_kl model/reparameterization.py unverified no licence file found · pointer only · f293d4bd17b84527 · report
kfallah/manifold-contrastive community (archive-listed) 8 samples, 3 ran (3 instrument-failed) · 5 unverified
draw_noise_samples src/model/manifold/vi_encoder.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 6c049df661812c5c · report fixture: signature distribution:str/0/str, shape:tuple/1/int, device:device/0/? · returned Tensor · level recorded 2026-09-22
reparameterize in 38 papers
census: 12 implementations from 17 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
src/model/manifold/vi_encoder.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 3522556f6aac7d0a · report fixture: signature distribution:str/0/str, distribution_params:dict/0/?, noise:Tensor/2/float, lambda_prior:float/0/float · returned Tensor · level recorded 2026-09-22
soft_threshold in 12 papers
census: 4 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
src/model/manifold/vi_encoder.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 63e0ab2c6652828b · report fixture: signature c:Tensor/2/float, zeta:float/0/float · returned Tensor · level recorded 2026-09-22
CoefficientEncoder src/model/manifold/vi_encoder.py unverified no licence file found · pointer only · 693c2208d67c25f2 · report
DistributionData src/model/manifold/vi_encoder.py unverified no licence file found · pointer only · 09a8466928f23739 · report
VariationalEncoderConfig src/model/manifold/vi_encoder.py unverified no licence file found · pointer only · 77036ddc9499e731 · report
infer_coefficients src/model/manifold/vi_encoder.py unverified no licence file found · pointer only · ee0aa4c2748a9421 · 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.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

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

one of 2 siblings

  1. VIEncoderLISTA entry · level 0 · unverified · bb9d074b88eaaf89
  2. VIEncoder model · level 0 · unverified · b5cc5a076789ea2e
  3. soft_threshold update_rule · level 1 · ran · our draft was wrong · b082bfb3081bcf63
  4. ConvEncoder helper · level 1 · ran · 903ea2efea36342b
  5. MLPEncoder helper · level 1 · ran · 06232d415e12a510

harvested Assembly for Variational Sparse Coding with Learned Thresholding (graph method: Variational Sparse Coding with Learned Thresholding). 9 bricks; individually on a fixture: 4 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; 3 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. CoefficientEncoder entry · level 0 · unverified · 693c2208d67c25f2
  2. DistributionData helper · level 0 · unverified · 09a8466928f23739
  3. VariationalEncoderConfig helper · level 0 · unverified · 77036ddc9499e731
  4. draw_noise_samples helper · level 1 · ran; the contract check could not run (RAISES) · 6c049df661812c5c
  5. infer_coefficients model · level 0 · unverified · ee0aa4c2748a9421
  6. reparameterize model · level 1 · ran; the contract check could not run (RAISES) · 3522556f6aac7d0a
  7. compute_loss helper · level 0 · unverified · 81df6932691462ff
  8. get_lr helper · level 1 · ran · honoured contract · 7337f1f5ff01dcd0
  9. soft_threshold helper · level 1 · ran · our draft was wrong · 63e0ab2c6652828b

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="2205.03665") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Variational Inference

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Variational Inference

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