Papers › A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry

A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry

31 Dec 2023arXiv:2401.00611archive 2025-07-28

Tim Z. Xiao, Weiyang Liu, Robert Bamler

Bayesian neural networks (BNNs) are a principled approach to modeling predictive uncertainties in deep learning, which are important in safety-critical applications. Since exact Bayesian inference over the weights in a BNN is intractable, various approximate inference methods exist, among which sampling methods such as Hamiltonian Monte Carlo (HMC) are often considered the gold standard. While HMC provides high-quality samples, it lacks interpretable summary statistics because its sample mean and variance is meaningless in neural networks due to permutation symmetry. In this paper, we first show that the role of permutations can be meaningfully quantified by a number of transpositions metric. We then show that the recently proposed rebasin method allows us to summarize HMC samples into a compact representation that provides a meaningful explicit uncertainty estimate for each weight in a neural network, thus unifying sampling methods with variational inference. We show that this compact representation allows us to compare trained BNNs directly in weight space across sampling methods and variational inference, and to efficiently prune neural networks trained without explicit Bayesian frameworks by exploiting uncertainty estimates from HMC.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2401.00611")

Code

Syntology Ran 9 of 14 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 9 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

timxzz/abi_with_rebasin officialmentioned in papermentioned on GitHubpytorch 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

14 samples harvested; 9 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

9ran
5unverified

Licence: 14 of the 14 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 timxzz/abi_with_rebasin. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

agreement timxzz/abi_with_rebasin/metrics.py official repository ran fingerprinted no licence file found · pointer only · 10b8964e0c906ead · report
construct_config_string timxzz/abi_with_rebasin/MNIST_HMC.py official repository ran no licence file found · pointer only · 6da2c42649dcb1bb · report
cost_matrix timxzz/abi_with_rebasin/rebasin.py official repository ran no licence file found · pointer only · fe0567580758cd02 · report
load_hmc_samples timxzz/abi_with_rebasin/utils.py official repository ran no licence file found · pointer only · b74ad0eadfe95127 · report
object_to_flatten_dict timxzz/abi_with_rebasin/MNIST_HMC.py official repository ran no licence file found · pointer only · 3784325e58d559a6 · report
to_numpy timxzz/abi_with_rebasin/MNIST_models.py official repository ran no licence file found · pointer only · 2efb1c739594d5ee · report
total_variation_distance timxzz/abi_with_rebasin/metrics.py official repository ran fingerprinted no licence file found · pointer only · 5567788db47b69bc · report
train_bnn timxzz/abi_with_rebasin/MNIST_VI.py official repository ran no licence file found · pointer only · a930a033d7a52021 · report
w2_distance timxzz/abi_with_rebasin/metrics.py official repository ran no licence file found · pointer only · 570cf6f632bc4a19 · report
acts_cost_matrix timxzz/abi_with_rebasin/rebasin.py official repository unverified no licence file found · pointer only · be95ccb8d35d9e3a · report
closest_permutation_by_activation timxzz/abi_with_rebasin/rebasin.py official repository unverified no licence file found · pointer only · 0c008d33347d27ce · report
load_hmc_hyperparameters timxzz/abi_with_rebasin/MNIST_HMC.py official repository unverified no licence file found · pointer only · 1e4d817efd08ff72 · report
train timxzz/abi_with_rebasin/MNIST_net_matching.py official repository unverified no licence file found · pointer only · ec9c68eaf082f7f3 · report
train_bnn_step timxzz/abi_with_rebasin/MNIST_VI.py official repository unverified no licence file found · pointer only · 3ac55ecfd1624ca5 · report

Tasks

Bayesian InferenceVariational Inference

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