Papers › Partially Stochastic Infinitely Deep Bayesian Neural Networks

Partially Stochastic Infinitely Deep Bayesian Neural Networks

5 Feb 2024arXiv:2402.03495archive 2025-07-28

Sergio Calvo-Ordonez, Matthieu Meunier, Francesco Piatti, Yuantao Shi

In this paper, we present Partially Stochastic Infinitely Deep Bayesian Neural Networks, a novel family of architectures that integrates partial stochasticity into the framework of infinitely deep neural networks. Our new class of architectures is designed to improve the computational efficiency of existing architectures at training and inference time. To do this, we leverage the advantages of partial stochasticity in the infinite-depth limit which include the benefits of full stochasticity e.g. robustness, uncertainty quantification, and memory efficiency, whilst improving their limitations around computational complexity. We present a variety of architectural configurations, offering flexibility in network design including different methods for weight partition. We also provide mathematical guarantees on the expressivity of our models by establishing that our network family qualifies as Universal Conditional Distribution Approximators. Lastly, empirical evaluations across multiple tasks show that our proposed architectures achieve better downstream task performance and uncertainty quantification than their counterparts while being significantly more efficient. The code can be found at https://github.com/Sergio20f/part_stoch_inf_deep

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 17 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 10 ran (1 with no instrument failure; 9 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. 2 of the 10 samples that ran have no recorded date.

sergio20f/part_stoch_inf_deep officialmentioned in paperjaxSyntology: 17 samples, 10 ran (9 instrument-failed) · 7 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

17 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 7 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 · violated contract
9ran · our draft was wrong
7unverified

Licence: 17 of the 17 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 sergio20f/part_stoch_inf_deep. “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.

sergio20f/part_stoch_inf_deep official repository 17 samples, 10 ran (9 instrument-failed) · 7 unverified
Affine in 6 papers arch.py ran · our draft was wrong fingerprinted no licence file found · pointer only · ee1ec0c589cadd7b · report fixture: signature mult:float/0/float, const:float/0/float · returned tuple · level recorded, date not recorded
BayesianLayer layers.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 1af23d057bd94033 · report fixture: signature layer:tuple/1/callable · returned tuple · level recorded 2026-09-22
Swish_ arch.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 02c69963c3739b67 · report fixture: signature out_dim:int/0/int, beta_init:float/0/float · returned tuple · level recorded, date not recorded
_sdeint layers.py ran · our draft was wrong no licence file found · pointer only · 28d92f354d62dd3f · report fixture: signature f:callable/0/?, g:callable/0/?, s_init:ArrayImpl/1/float, bm_dim:int/0/int, ts:ArrayImpl/1/float, rng:ArrayImpl/1/int · returned ArrayImpl · level recorded 2026-09-22
aug_init layers.py ran · our draft was wrong no licence file found · pointer only · f43d0d8a644ed2d0 · report fixture: signature W0:dict/0/?, _inputs:dict/0/? · returned tuple · level recorded 2026-09-22
augmented_post_drift layers.py ran · our draft was wrong no licence file found · pointer only · 679a1d2ba3db5a0c · report fixture: signature rng:ArrayImpl/1/int, state_unravel_fn:callable/0/?, param_unravel_fn:callable/0/?, driftx_apply_fn:callable/0/?, prior_driftw_apply_fn:callable/0/?, driftw0_apply_fn:callable/0/?, driftw_apply_fn:callable/0/?, diff_apply_fn:callable/0/?, W_driftwt:dict/0/?, W_priorwt:dict/0/?, W_diffusion:dict/0/?, W0_post:dict/0/?, setting:dict/0/?, t:float/0/float, aug:ArrayImpl/1/float, eps:float/0/float · returned ArrayImpl · level recorded 2026-09-22
augmented_prior_drift layers.py ran · our draft was wrong no licence file found · pointer only · d001641b4d745458 · report fixture: signature state_unravel_fn:callable/0/?, param_unravel_fn:callable/0/?, driftx_apply_fn:callable/0/?, prior_driftw_apply_fn:callable/0/?, diff_apply_fn:callable/0/?, W_priorwt:ArrayImpl/2/float, W_diffusion:ArrayImpl/2/float, setting:dict/0/?, t:ArrayImpl/0/float, aug:ArrayImpl/1/float, eps:ArrayImpl/0/float · returned ArrayImpl · level recorded 2026-09-22
normal_kldiv layers.py ran · violated contract fingerprinted no licence file found · pointer only · 056538899cff555a · report fixture: signature mu1:ArrayImpl/2/float, mu2:ArrayImpl/2/float, logsigma1:ArrayImpl/2/float, logsigma2:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-22
sdeint layers.py ran · our draft was wrong no licence file found · pointer only · d647b684f6582805 · report fixture: signature f:callable/0/?, g:callable/0/?, s_init:ArrayImpl/1/float, bm_dim:int/0/int, ts:ArrayImpl/1/float, rng:ArrayImpl/1/int · returned ArrayImpl · level recorded 2026-09-22
variance_scaling in 31 papers layers.py ran · our draft was wrong no licence file found · pointer only · e761de9f4c477057 · report fixture: signature scale:float/0/float, mode:str/0/str, distribution:str/0/str, in_axis:int/0/int, out_axis:int/0/int, dtype:callable/0/? · returned function · level recorded 2026-09-22
SDELayer layers.py unverified no licence file found · pointer only · dc9013835f0ceb5d · report
_compute_fans layers.py unverified no licence file found · pointer only · ec8cea005cc836bb · report
augmented_diffusion layers.py unverified no licence file found · pointer only · f017d3e029807254 · report
he_normal_stdev layers.py unverified no licence file found · pointer only · b5fc14c86b45c4ce · report
predict in 126 papers sdebnn_classification.py unverified no licence file found · pointer only · 2d96f5e14250dac3 · report
sep_loss sdebnn_classification.py unverified no licence file found · pointer only · 528631e2109308f6 · 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 Partially Stochastic Infinitely Deep Bayesian Neural Networks (graph method: Partially Stochastic Infinitely Deep Bayesian Neural Networks). 12 bricks; individually on a fixture: 8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. SDELayer entry · level 0 · unverified · dc9013835f0ceb5d
  2. BayesianLayer helper · level 1 · ran · our draft was wrong · 1af23d057bd94033
  3. _sdeint helper · level 1 · ran · our draft was wrong · 28d92f354d62dd3f
  4. aug_init helper · level 1 · ran · our draft was wrong · f43d0d8a644ed2d0
  5. augmented_diffusion model · level 0 · unverified · f017d3e029807254
  6. augmented_post_drift model · level 1 · ran · our draft was wrong · 679a1d2ba3db5a0c
  7. augmented_prior_drift model · level 1 · ran · our draft was wrong · d001641b4d745458
  8. he_normal_stdev helper · level 0 · unverified · b5fc14c86b45c4ce
  9. sdeint helper · level 1 · ran · our draft was wrong · d647b684f6582805
  10. normal_kldiv helper · level 1 · ran · violated contract · 056538899cff555a
  11. variance_scaling helper · level 1 · ran · our draft was wrong · e761de9f4c477057
  12. _compute_fans helper · level 0 · unverified · ec8cea005cc836bb

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="2402.03495") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Computational EfficiencyUncertainty Quantification

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