SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.07673 · ICML · 2022

Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling

Jeffrey Pennington, Jiri Hron, Jascha Sohl-Dickstein, Roman Novak

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2206.07673.json · badge: /api/ran/2206.07673.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
lucia-pezzetti/function-space-mcmc-for-wide-bnns community
Papers with Code archive
1 ran · 2 no recorded run
google/wide_bnn_sampling community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
_get_ident_energy_fn Ran
ran; our contract draft was wrong, not the code
lucia-pezzetti/function-space-mcmc-for-wide-bnns/src/reparametrisation.py
pointer only (licence: NONE) · get_code("2fcbb2a775c11e15")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lucia-pezzetti/function-space-mcmc-for-wide-bnns when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

_get_nngp_energy_fn Not yet run
unverified (harvested, no recorded run)
lucia-pezzetti/function-space-mcmc-for-wide-bnns/src/reparametrisation.py
pointer only (licence: NONE) · get_code("1fa337aaaa358263")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lucia-pezzetti/function-space-mcmc-for-wide-bnns when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

_get_nngp_energy_fn Not yet run
unverified (harvested, no recorded run)
google/wide_bnn_sampling/wide_bnn_sampling/reparametrisation.py
code served (permissive licence) · get_code("72acd12153e4d535")
How it ran

no invocation recorded.

get_energy_fn Not yet run
unverified (harvested, no recorded run)
lucia-pezzetti/function-space-mcmc-for-wide-bnns/src/reparametrisation.py
pointer only (licence: NONE) · get_code("33ef9d6b7bcff3d1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lucia-pezzetti/function-space-mcmc-for-wide-bnns when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce repriorisation, a data-dependent reparameterisation which transforms a Bayesian neural network (BNN) posterior to a distribution whose KL divergence to the BNN prior vanishes as layer widths grow. The repriorisation map acts directly on parameters, and its analytic simplicity complements the known neural network Gaussian process (NNGP) behaviour of wide BNNs in function space. Exploiting the repriorisation, we develop a Markov chain Monte Carlo (MCMC) posterior sampling algorithm which mixes faster the wider the BNN. This contrasts with the typically poor performance of MCMC in high dimensions. We observe up to 50x higher effective sample size relative to no reparametrisation for both fully-connected and residual networks. Improvements are achieved at all widths, with the margin between reparametrised and standard BNNs growing with layer width.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2206.07673")
get_code_for_paper("2206.07673")
have("2206.07673")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2206.07673.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2206.07673.svg)](https://syntology.ai/paper/2206.07673)

Connect an agent — have() is free.