Papers › Are Bayesian neural networks intrinsically good at out-of-distribution detection?

Are Bayesian neural networks intrinsically good at out-of-distribution detection?

26 Jul 2021arXiv:2107.12248archive 2025-07-28

Christian Henning, Francesco D'Angelo, Benjamin F. Grewe

The need to avoid confident predictions on unfamiliar data has sparked interest in out-of-distribution (OOD) detection. It is widely assumed that Bayesian neural networks (BNN) are well suited for this task, as the endowed epistemic uncertainty should lead to disagreement in predictions on outliers. In this paper, we question this assumption and provide empirical evidence that proper Bayesian inference with common neural network architectures does not necessarily lead to good OOD detection. To circumvent the use of approximate inference, we start by studying the infinite-width case, where Bayesian inference can be exact considering the corresponding Gaussian process. Strikingly, the kernels induced under common architectural choices lead to uncertainties that do not reflect the underlying data generating process and are therefore unsuited for OOD detection. Finally, we study finite-width networks using HMC, and observe OOD behavior that is consistent with the infinite-width case. Overall, our study discloses fundamental problems when naively using BNNs for OOD detection and opens interesting avenues for future research.

PaperPDFCodeCode Syntology ran

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 12 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 12 samples from 1 repository, 11 ran (11 with no instrument failure; 0 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

chrhenning/uncertainty_based_ood mentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 11 ran (0 instrument-failed) · 1 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

12 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 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.

11ran
1unverified

Licence: 0 of the 12 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 chrhenning/uncertainty_based_ood. “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.

chrhenning/uncertainty_based_ood community (archive-listed) 12 samples, 11 ran (0 instrument-failed) · 1 unverified
analytic_v_gaussian nngp/rbf_net.py ran fingerprinted Apache-2.0 (permissive) · 6e378b4df81a058c · report fixture: signature X:Tensor/2/float, sigma2_u:float/0/float, bandwidth:float/0/float · returned Tensor · level recorded 2026-09-24
calc_regression_acc utils/misc.py ran fingerprinted Apache-2.0 (permissive) · ef6d55e8d0d4a731 · report fixture: signature predictions:Tensor/1/float, targets:Tensor/1/float, thld:float/0/float · returned Tensor · level recorded 2026-09-24
cholesky_adaptive_noise nngp/nngp.py ran Apache-2.0 (permissive) · 57d4f077483e5f9e · report fixture: signature K_train:Tensor/2/float, var:float/0/float, var_step:float/0/float · returned tuple · level recorded 2026-09-24
cosine_1l_kernel nngp/mlp_kernel.py ran fingerprinted Apache-2.0 (permissive) · d0cf47683cde9160 · report fixture: signature X:Tensor/2/float, sigma2_w:float/0/float, sigma2_b:float/0/float · returned Tensor · level recorded 2026-09-24
eval_grid_2d utils/misc.py ran Apache-2.0 (permissive) · bbd76be30158bd1b · report fixture: signature x_range:tuple/1/int, y_range:tuple/1/int, res_per_unit:int/0/int, verbose:bool/0/bool · returned tuple · level recorded 2026-09-24
inference_with_isotropic_gaussian_ll nngp/nngp.py ran Apache-2.0 (permissive) · f10a9936b81c32ba · report fixture: signature Y:Tensor/1/float, K_train:Tensor/2/float, K_test:Tensor/1/float, K_all:Tensor/2/float, var:float/0/float, L_mat:NoneType/0/?, return_cov:bool/0/bool · returned tuple · level recorded 2026-09-24
init_kernel nngp/mlp_kernel.py ran fingerprinted Apache-2.0 (permissive) · 64aad04d13588379 · report fixture: signature X:Tensor/2/float, sigma2_w:float/0/float, sigma2_b:float/0/float · returned Tensor · level recorded 2026-09-24
mc_v_gaussian nngp/rbf_net.py ran Apache-2.0 (permissive) · 897640ff43709859 · report fixture: signature X:Tensor/2/float, sigma2_u:float/0/float, bandwidth:float/0/float, num_samples:int/0/int · returned Tensor · level recorded 2026-09-24
rbf in 19 papers
census: 4 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
nngp/standard_kernels.py ran fingerprinted Apache-2.0 (permissive) · 61768d8e87c1b06d · report fixture: signature X:Tensor/2/float, length_scale:float/0/float · returned Tensor · level recorded 2026-09-24
regular_grid finite_width/ridgelet_prior.py ran Apache-2.0 (permissive) · 3c790a7efb74000c · report fixture: signature cube_size:int/0/int, res_per_dim:int/0/int, grid_dim:int/0/int, device:NoneType/0/? · returned Tensor · level recorded 2026-09-24
relu_recursion_lee nngp/mlp_kernel.py ran Apache-2.0 (permissive) · da5aabdd5b3d3cbe · report fixture: signature K_prev:Tensor/3/float, curr_layer:int/0/int, end_layer:int/0/int, sigma2_w:float/0/float, sigma2_b:float/0/float · returned Tensor · level recorded 2026-09-24
gen_inference_kernels nngp/nngp.py unverified Apache-2.0 (permissive) · 77214e4c21adc429 · report

Tasks

Bayesian InferenceOut of Distribution (OOD) DetectionOut-of-Distribution Detection

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