Papers › PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning

PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning

21 Jun 2023NeurIPS 2023 11arXiv:2306.12370archive 2025-07-28

Neeratyoy Mallik, Edward Bergman, Carl Hvarfner, Danny Stoll, Maciej Janowski, Marius Lindauer, Luigi Nardi, Frank Hutter

Hyperparameters of Deep Learning (DL) pipelines are crucial for their downstream performance. While a large number of methods for Hyperparameter Optimization (HPO) have been developed, their incurred costs are often untenable for modern DL. Consequently, manual experimentation is still the most prevalent approach to optimize hyperparameters, relying on the researcher's intuition, domain knowledge, and cheap preliminary explorations. To resolve this misalignment between HPO algorithms and DL researchers, we propose PriorBand, an HPO algorithm tailored to DL, able to utilize both expert beliefs and cheap proxy tasks. Empirically, we demonstrate PriorBand's efficiency across a range of DL benchmarks and show its gains under informative expert input and robustness against poor expert beliefs

PaperPDFConference PDFCodeCode 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 18 code samples harvested from 2 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 15 ran (13 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 2 ran (2 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 between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

automl/mf-prior-exp officialmentioned in paperMITSyntology: 15 samples, 15 ran (2 instrument-failed) · 0 unverified report
automl/neps mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 2 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

18 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 2 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
15ran
1unverified

Licence: 0 of the 18 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

automl/mf-prior-exp official repository 15 samples, 15 ran (2 instrument-failed) · 0 unverified
all_possibilities src/mf_prior_experiments/plotting_types.py ran MIT (permissive) · 9192955c312ae37c · report fixture: signature experiment_group:str/0/str, base_path:PosixPath/0/?, ignore_benchmarks:NoneType/0/?, ignore_algorithms:NoneType/0/?, ignore_seeds:NoneType/0/? · returned tuple · level recorded 2026-09-26
esc create_search_space_latex_tables.py ran · our draft was wrong fingerprinted MIT (permissive) · 521590451f559465 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-24
form_cliques src/mf_prior_experiments/configs/plotting/reference_cd_plot.py ran MIT (permissive) · 485e24706d0bc281 · report fixture: signature p_values:list/1/tuple, nnames:ndarray/1/<U6 · returned generator · level recorded 2026-09-26
get_classifier_comparison_df src/mf_prior_experiments/configs/plotting/reference_cd_plot.py ran MIT (permissive) · d75619a62bb93bfd · report fixture: signature df_perf:DataFrame/0/?, performance_metric_column_name:str/0/str, classifiers:list/1/str · returned tuple · level recorded 2026-09-26
get_gpu_srun_command src/mf_prior_experiments/submit.py ran fingerprinted MIT (permissive) · 68479544e1d267da · report fixture: signature cmd:str/0/str, nworkers:int/0/int · returned list · level recorded 2026-09-26
get_xticks src/mf_prior_experiments/plot_styles.py ran MIT (permissive) · cd2202bc8caa7ef9 · report fixture: signature xrange:tuple/1/int, ticks:int/0/int · returned list · level recorded 2026-09-26
graph_ranks src/mf_prior_experiments/configs/plotting/reference_cd_plot.py ran MIT (permissive) · 6e8538f8df30e1c1 · report fixture: returned Axes · level recorded 2026-09-26
indent in 6 papers create_search_space_latex_tables.py ran · our draft was wrong fingerprinted MIT (permissive) · 0d7883b0a60445e8 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-24
is_gpu_partition src/mf_prior_experiments/submit.py ran MIT (permissive) · 2cbdb7e1d95eb0d8 · report fixture: signature args:Args/0/? · returned bool · level recorded 2026-09-26
load_losses prior_overlap_plots/plot.py ran MIT (permissive) · 1f15321b5cf9dfc4 · report fixture: returned list · level recorded 2026-09-26
parse_argument_string src/mf_prior_experiments/submit.py ran MIT (permissive) · cd8bb972126e1971 · report fixture: signature args:ArgumentsConfig/0/? · returned tuple · level recorded 2026-09-26
partition in 17 papers prior_overlap_plots/plot.py ran MIT (permissive) · 3e0c43061f67298a · report fixture: signature xs:list/1/int, key:callable/0/? · returned tuple · level recorded 2026-09-26
prior_renaming prior_overlap_plots/plot.py ran fingerprinted MIT (permissive) · 7272cfc4622b66c1 · report fixture: signature benchmark:str/0/str, prior:str/0/str · returned str · level recorded 2026-09-26
regret_normalize src/mf_prior_experiments/plotting_types.py ran MIT (permissive) · 692b3abc04a5ce4e · report fixture: signature values:Series/1/float, bounds:DataFrame/0/?, stationary:bool/0/bool · returned Series · level recorded 2026-09-26
wrap in 19 papers create_search_space_latex_tables.py ran MIT (permissive) · c9e8014f8c628603 · report fixture: signature o:int/0/int, s:str/0/str · returned str · level recorded 2026-09-24
automl/neps community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
is_nullable neps/env.py ran Apache-2.0 (permissive) · ccb398a46d556c96 · report fixture: signature e:str/0/str · returned bool · level recorded 2026-09-24
yaml_or_json neps/env.py ran Apache-2.0 (permissive) · 84aa58b2c77c3c6f · report fixture: signature e:str/0/str · returned str · level recorded 2026-09-24
get_env in 13 papers neps/env.py unverified Apache-2.0 (permissive) · ea229fa5e083a401 · report

Tasks

Deep LearningHyperparameter Optimization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

HPO

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