Automatic Exploration of Machine Learning Experiments on OpenML

Bernd Bischl; Daniel K\"uhn; Janek Thomas; Philipp Probst

Automatic Exploration of Machine Learning Experiments on OpenML

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1806.10961 v3 pith:OC3HZGOJ submitted 2018-06-28 stat.ML cs.DBcs.LG

Daniel Kühn , Philipp Probst , Janek Thomas , Bernd Bischl This is my paper · ORCID

classification stat.MLcs.DBcs.LG

keywords datasetdifferentlearningmachineopenmlalgorithmautomaticdata

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

Understanding the influence of hyperparameters on the performance of a machine learning algorithm is an important scientific topic in itself and can help to improve automatic hyperparameter tuning procedures. Unfortunately, experimental meta data for this purpose is still rare. This paper presents a large, free and open dataset addressing this problem, containing results on 38 OpenML data sets, six different machine learning algorithms and many different hyperparameter configurations. Results where generated by an automated random sampling strategy, termed the OpenML Random Bot. Each algorithm was cross-validated up to 20.000 times per dataset with different hyperparameters settings, resulting in a meta dataset of around 2.5 million experiments overall.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

PIPES: A Meta-dataset of Machine Learning Pipelines
cs.LG 2025-09 conditional novelty 6.0 of 10

PIPES is a new meta-dataset containing results of 9,408 combinations of imputation, encoding, scaling, feature preprocessing, and classification techniques on 280 successfully processed datasets.

Pith tools