Papers › Temperature Optimization for Bayesian Deep Learning

Temperature Optimization for Bayesian Deep Learning

8 Oct 2024arXiv:2410.05757archive 2025-07-28

Kenyon Ng, Chris van der Heide, Liam Hodgkinson, Susan Wei

The Cold Posterior Effect (CPE) is a phenomenon in Bayesian Deep Learning (BDL), where tempering the posterior to a cold temperature often improves the predictive performance of the posterior predictive distribution (PPD). Although the term `CPE' suggests colder temperatures are inherently better, the BDL community increasingly recognizes that this is not always the case. Despite this, there remains no systematic method for finding the optimal temperature beyond grid search. In this work, we propose a data-driven approach to select the temperature that maximizes test log-predictive density, treating the temperature as a model parameter and estimating it directly from the data. We empirically demonstrate that our method performs comparably to grid search, at a fraction of the cost, across both regression and classification tasks. Finally, we highlight the differing perspectives on CPE between the BDL and Generalized Bayes communities: while the former primarily emphasizes the predictive performance of the PPD, the latter prioritizes the utility of the posterior under model misspecification; these distinct objectives lead to different temperature preferences.

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 15 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 11 ran (5 with no instrument failure; 6 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.

weiyaw/tempered-posteriors officialjaxMITSyntology: 15 samples, 11 ran (6 instrument-failed) · 4 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

15 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
6ran · our draft was wrong
3ran
4unverified

Licence: 0 of the 15 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 weiyaw/tempered-posteriors. “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.

weiyaw/tempered-posteriors official repository 15 samples, 11 ran (6 instrument-failed) · 4 unverified
add_classficiation datasets/download_data.py ran · our draft was wrong MIT (permissive) · 9b436ef2d0792040 · report fixture: signature C:ClassificationDataset/0/? · returned ClassificationDataset · level recorded 2026-09-24
add_regression datasets/download_data.py ran · our draft was wrong MIT (permissive) · 5cadf1fc3261f6c0 · report fixture: signature C:RegressionDataset/0/? · returned RegressionDataset · level recorded 2026-09-24
filter_args in 5 papers inference.py ran MIT (permissive) · 52941c123cdcadee · report fixture: signature args_dict:dict/0/?, fn:callable/0/?, exclude:list/1/empty · returned tuple · level recorded 2026-09-24
flatdict main-empirical.py ran · our draft was wrong MIT (permissive) · ad3ede600b6e930f · report fixture: signature x:dict/0/? · returned str · level recorded 2026-09-24
is_numeric in 28 papers training.py ran · violated contract fingerprinted MIT (permissive) · 0d4d5d0d375201d6 · report fixture: signature x:int/0/int · returned bool · level recorded 2026-09-24
log_prob_tree training.py ran · honoured contract MIT (permissive) · 2afc2e44e4aa1fe0 · report fixture: signature tree_z:dict/0/?, dist:Normal/0/? · returned ArrayImpl · level recorded 2026-09-24
make_constant_lr_schedule_with_cosine_burnin sgmcmc.py ran MIT (permissive) · 1910403f272fdc73 · report fixture: signature init_lr:float/0/float, final_lr:float/0/float, burnin_steps:int/0/int · returned function · level recorded 2026-09-24
make_cosine_schedule sgmcmc.py ran MIT (permissive) · 013661d041de5d86 · report fixture: signature init_lr:float/0/float, total_steps:int/0/int, final_lr:float/0/float · returned function · level recorded 2026-09-24
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
datasets/download_data.py ran · our draft was wrong fingerprinted MIT (permissive) · cba0faabe1fa7dc7 · report fixture: signature X:ndarray/2/float · returned tuple · level recorded 2026-09-24
read_from_local utils.py ran · our draft was wrong MIT (permissive) · 67ca4f13b861a952 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24
sample_X_grid data.py ran · our draft was wrong MIT (permissive) · 536d78b9441ea597 · report fixture: signature dim_x:tuple/1/int, n_samples:int/0/int · returned ArrayImpl · level recorded 2026-09-24
calc_normal_logprob_resid metrics.py unverified MIT (permissive) · b18d120529093966 · report
flatten_dict in 72 papers visual_utils.py unverified MIT (permissive) · 91345e63f4999e0e · report
normal_like_tree sgmcmc.py unverified MIT (permissive) · bace351d40c0081c · report
sample_tree data.py unverified MIT (permissive) · ee368fc45143d54a · report

Tasks

Deep Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CPE

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