A Large-Scale Neutral Comparison Study of Survival Models on Low-Dimensional Data

Authors

Affiliations

Lukas Burk

Leibniz Institute for Prevention Research and Epidemiology - BIPS

LMU Munich

Munich Center for Machine Learning (MCML)

University of Bremen

John Zobolas

Bernd Bischl

LMU Munich

Munich Center for Machine Learning (MCML)

Andreas Bender

LMU Munich

Munich Center for Machine Learning (MCML)

Marvin N. Wright

Leibniz Institute for Prevention Research and Epidemiology - BIPS

University of Bremen

Raphael Sonabend

This site aggregates additional results and metadata accompanying the benchmark project.
All code is available on GitHub.
Note that this page belongs to the most recent version of the project. A previous version from 2024 is available here.

Downloading Results

Results can be downloaded from the web.

Files are suffixed with the associated tuning measure unless already combined, where harrell_c,isbs indicates results for learners which are not at all or not explicitly tuned during the experiment but rather use an internal mechanism, i.e. Kaplan-Meier or CoxBoost (see learner table on Metadata)

• scores are individual scores per outer resampling iteration
• bma_ (BenchmarkAggr) are intermediate results and are only relevant if these mlr3 objects are specifically required.

See also the table of measures for a list of measures and their abbreviated and full names.

Table 1: Index of most relevant result files for download

File	Description
scores.rds	Scores for all learners, tasks and measures for individual outer resampling iterations
archives.zip	ZIP file of all tuning archives produced during the benchmark (over 19000) in CSV files for each combination of learner, task, tuning measure, and resampling iteration