SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.07753 · ICML · 2023

Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks

Jongseok Lee, Rudolph Triebel, Daniel Cremers, Dominik Schnaus

arXiv · PDF · Open in the Atlas

Code that ran

5 of 10 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; 5 failures of our instrument; 5 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/2307.07753.json · badge: /api/ran/2307.07753.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
DLR-RM/BPNN canonical (classifier label)
classifier basis: census
5 ran · 5 no recorded run
FunctionStatusWhere it lives
lenet5 Ran
ran; our contract draft was wrong, not the code
DLR-RM/BPNN/src/curvature/lenet5.py
pointer only (licence: GPL-3.0) · get_code("95ce48cf157d31ee")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, DLR-RM/BPNN, is not in the permissive set Syntology serves inline. 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.

nested_module_dict Ran
ran; our contract draft was wrong, not the code
DLR-RM/BPNN/src/bpnn/pnn.py
pointer only (licence: GPL-3.0) · get_code("2e385df3141c14ac")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, DLR-RM/BPNN, is not in the permissive set Syntology serves inline. 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.

nll_cls Ran
ran; our contract draft was wrong, not the code
DLR-RM/BPNN/src/bpnn/utils.py
pointer only (licence: GPL-3.0) · get_code("a69b5d550b745fb9")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, DLR-RM/BPNN, is not in the permissive set Syntology serves inline. 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.

nll_reg Ran
ran; our contract draft was wrong, not the code
DLR-RM/BPNN/src/bpnn/utils.py
pointer only (licence: GPL-3.0) · get_code("7a14dc9886409c12")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, DLR-RM/BPNN, is not in the permissive set Syntology serves inline. 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.

power_method_sum_kronecker_products_rank_1 Ran
ran; our contract draft was wrong, not the code
DLR-RM/BPNN/src/curvature/utils.py
pointer only (licence: GPL-3.0) · get_code("6784abf28118d102")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, DLR-RM/BPNN, is not in the permissive set Syntology serves inline. 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.

accuracy Not yet run
unverified (harvested, no recorded run)
DLR-RM/BPNN/src/bpnn/utils.py
pointer only (licence: GPL-3.0) · get_code("d1d60175a8cdd4c2")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, DLR-RM/BPNN, is not in the permissive set Syntology serves inline. 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.

dataset_step_pnn Not yet run
unverified (harvested, no recorded run)
DLR-RM/BPNN/src/bpnn/pnn.py
pointer only (licence: GPL-3.0) · get_code("4e7a77446f19cbd8")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, DLR-RM/BPNN, is not in the permissive set Syntology serves inline. 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.

dataset_step_ppnn Not yet run
unverified (harvested, no recorded run)
DLR-RM/BPNN/src/bpnn/pnn.py
pointer only (licence: GPL-3.0) · get_code("1b273971a01e4d5f")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, DLR-RM/BPNN, is not in the permissive set Syntology serves inline. 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_eigenvalues Not yet run
unverified (harvested, no recorded run)
DLR-RM/BPNN/src/curvature/utils.py
pointer only (licence: GPL-3.0) · get_code("f9d6c400b14f0bba")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, DLR-RM/BPNN, is not in the permissive set Syntology serves inline. 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_eigenvectors Not yet run
unverified (harvested, no recorded run)
DLR-RM/BPNN/src/curvature/utils.py
pointer only (licence: GPL-3.0) · get_code("bb518932c78f4fb4")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, DLR-RM/BPNN, is not in the permissive set Syntology serves inline. 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 10 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

In this work, we propose a novel prior learning method for advancing generalization and uncertainty estimation in deep neural networks. The key idea is to exploit scalable and structured posteriors of neural networks as informative priors with generalization guarantees. Our learned priors provide expressive probabilistic representations at large scale, like Bayesian counterparts of pretrained models on ImageNet, and further produce non-vacuous generalization bounds. We also extend this idea to a continual learning framework, where the favorable properties of our priors are desirable. Major enablers are our technical contributions: (1) the sums-of-Kronecker-product computations, and (2) the derivations and optimizations of tractable objectives that lead to improved generalization bounds. Empirically, we exhaustively show the effectiveness of this method for uncertainty estimation and generalization. * Equal contribution 1 TU Munich 2 MCML 3 DLR 4 KIT. Correspondence to: Dominik Schnaus

For agents

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

get_harvested_code_for_paper("2307.07753")
get_code_for_paper("2307.07753")
have("2307.07753")

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

curl https://syntology.ai/api/ran/2307.07753.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.07753.svg)](https://syntology.ai/paper/2307.07753)

Connect an agent — have() is free.